diff --git "a/checkpoint-2671200/trainer_state.json" "b/checkpoint-2671200/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2671200/trainer_state.json" @@ -0,0 +1,31607 @@ +{ + "best_metric": 3.9721450805664062, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/npi-sent-neg/lstm/0/checkpoints/checkpoint-2671200", + "epoch": 1.0250006060157382, + "eval_steps": 10, + "global_step": 2671200, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 4.999998362119627e-05, + "loss": 10.8186, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 7.553, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 7.0592, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 6.9948, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 6.948, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 6.9162, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 6.7528, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 6.641, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 6.5477, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 6.473, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 6.4158, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 6.3505, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 6.2821, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989098268236324e-05, + "loss": 6.2031, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988259673485272e-05, + "loss": 6.1533, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.98742107873422e-05, + "loss": 6.0877, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986582483983168e-05, + "loss": 6.0439, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985743889232116e-05, + "loss": 5.9966, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984905294481064e-05, + "loss": 5.9585, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984066699730012e-05, + "loss": 5.9177, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.8838, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 5.8444, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 5.8116, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 5.7794, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 5.7602, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790384069844466e-05, + "loss": 5.7233, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9781998122333946e-05, + "loss": 5.6991, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773612174823426e-05, + "loss": 5.6725, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 5.6432, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 5.6329, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748470711095595e-05, + "loss": 5.6088, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.974008476358507e-05, + "loss": 5.5993, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.973169881607455e-05, + "loss": 5.5635, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.972331286856403e-05, + "loss": 5.5524, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.9714943299857244e-05, + "loss": 5.5409, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 5.5228, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 5.5022, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968980183612942e-05, + "loss": 5.4685, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.96814158886189e-05, + "loss": 5.4697, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967302994110837e-05, + "loss": 5.4366, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966464399359785e-05, + "loss": 5.4386, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965625804608733e-05, + "loss": 5.4212, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964787209857681e-05, + "loss": 5.4101, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963948615106629e-05, + "loss": 5.3925, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 5.3855, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962273063484898e-05, + "loss": 5.3848, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.961434468733847e-05, + "loss": 5.3673, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960595873982795e-05, + "loss": 5.363, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959757279231743e-05, + "loss": 5.3348, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.958918684480691e-05, + "loss": 5.3217, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958080089729639e-05, + "loss": 5.3314, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957241494978587e-05, + "loss": 5.3156, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956404538107908e-05, + "loss": 5.3077, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.955567581237229e-05, + "loss": 5.2786, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.954728986486177e-05, + "loss": 5.2929, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.953890391735125e-05, + "loss": 5.2686, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530517969840727e-05, + "loss": 5.2897, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522132022330207e-05, + "loss": 5.2401, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.9513746074819686e-05, + "loss": 5.2521, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.9505360127309166e-05, + "loss": 5.2318, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949699055860238e-05, + "loss": 5.2208, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948860461109186e-05, + "loss": 5.2221, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.948023504238507e-05, + "loss": 5.2075, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947184909487455e-05, + "loss": 5.1871, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946346314736403e-05, + "loss": 5.1891, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945507719985351e-05, + "loss": 5.208, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944669125234299e-05, + "loss": 5.1806, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.94383216836362e-05, + "loss": 5.1691, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942993573612568e-05, + "loss": 5.1589, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942154978861516e-05, + "loss": 5.1426, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.941316384110464e-05, + "loss": 5.1579, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404794272397856e-05, + "loss": 5.1498, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396408324887336e-05, + "loss": 5.1414, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388038756180545e-05, + "loss": 5.1477, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379652808670025e-05, + "loss": 5.1318, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371266861159505e-05, + "loss": 5.1268, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362897292452714e-05, + "loss": 5.1051, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354511344942194e-05, + "loss": 5.1052, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346125397431674e-05, + "loss": 5.0958, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337739449921154e-05, + "loss": 5.0873, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329353502410634e-05, + "loss": 5.0878, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.9320967554900114e-05, + "loss": 5.0846, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.9312581607389594e-05, + "loss": 5.0857, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.9304195659879074e-05, + "loss": 5.0759, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.9295809712368554e-05, + "loss": 5.0512, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.9287423764858034e-05, + "loss": 5.0608, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.9279037817347514e-05, + "loss": 5.0619, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.9270651869836994e-05, + "loss": 5.063, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.92622823011302e-05, + "loss": 5.0407, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925389635361968e-05, + "loss": 5.0444, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924551040610916e-05, + "loss": 5.0357, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923712445859864e-05, + "loss": 5.027, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922873851108812e-05, + "loss": 5.0221, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.92203525635776e-05, + "loss": 5.0192, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921196661606708e-05, + "loss": 5.0048, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920358066855656e-05, + "loss": 5.0142, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919521109984978e-05, + "loss": 4.9967, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918684153114299e-05, + "loss": 4.9891, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917845558363247e-05, + "loss": 4.9853, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917006963612195e-05, + "loss": 4.9887, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.916168368861143e-05, + "loss": 4.9828, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915329774110091e-05, + "loss": 4.9678, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.9144928172394116e-05, + "loss": 4.97, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136542224883596e-05, + "loss": 4.9575, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128156277373076e-05, + "loss": 4.9601, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119770329862556e-05, + "loss": 4.9375, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.9111400761155765e-05, + "loss": 4.9463, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.9103014813645245e-05, + "loss": 4.94, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909462886613473e-05, + "loss": 4.9354, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908625929742794e-05, + "loss": 4.9402, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907787334991742e-05, + "loss": 4.9329, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.90694874024069e-05, + "loss": 4.912, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906110145489638e-05, + "loss": 4.9222, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905271550738586e-05, + "loss": 4.924, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904432955987534e-05, + "loss": 4.9163, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903594361236482e-05, + "loss": 4.9159, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.90275576648543e-05, + "loss": 4.9069, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901917171734378e-05, + "loss": 4.902, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901078576983326e-05, + "loss": 4.891, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.900239982232274e-05, + "loss": 4.8984, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994013874812214e-05, + "loss": 4.8945, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985660684909166e-05, + "loss": 4.8782, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977274737398646e-05, + "loss": 4.8804, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968888789888125e-05, + "loss": 4.8756, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960519221181335e-05, + "loss": 4.883, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952133273670815e-05, + "loss": 4.8598, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943747326160294e-05, + "loss": 4.8656, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935361378649774e-05, + "loss": 4.853, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.8926975431139254e-05, + "loss": 4.8599, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918589483628734e-05, + "loss": 4.8494, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910203536118214e-05, + "loss": 4.8632, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890181758860769e-05, + "loss": 4.851, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.88934480199009e-05, + "loss": 4.844, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888506207239038e-05, + "loss": 4.8432, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.88766925036836e-05, + "loss": 4.8375, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886830655617308e-05, + "loss": 4.8448, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885992060866256e-05, + "loss": 4.8437, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885153466115204e-05, + "loss": 4.8339, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884316509244525e-05, + "loss": 4.8289, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883477914493473e-05, + "loss": 4.8303, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882639319742421e-05, + "loss": 4.8183, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881800724991369e-05, + "loss": 4.8061, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.880962130240316e-05, + "loss": 4.815, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880123535489264e-05, + "loss": 4.8067, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879284940738212e-05, + "loss": 4.7986, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.87844634598716e-05, + "loss": 4.798, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877607751236109e-05, + "loss": 4.7965, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.87677079436543e-05, + "loss": 4.7984, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875932199614378e-05, + "loss": 4.8001, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875093604863326e-05, + "loss": 4.7883, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.753722667694092, + "eval_runtime": 297.919, + "eval_samples_per_second": 1280.855, + "eval_steps_per_second": 40.028, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.8742566479926466e-05, + "loss": 4.7777, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.8734180532415946e-05, + "loss": 4.7753, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.8725794584905426e-05, + "loss": 4.7861, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.8717408637394906e-05, + "loss": 4.7783, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709022689884386e-05, + "loss": 4.7805, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700653121177595e-05, + "loss": 4.7634, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.8692267173667075e-05, + "loss": 4.7647, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683881226156555e-05, + "loss": 4.759, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.867549527864604e-05, + "loss": 4.7636, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.866710933113552e-05, + "loss": 4.7644, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.8658723383625e-05, + "loss": 4.7605, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865033743611448e-05, + "loss": 4.7656, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.864195148860396e-05, + "loss": 4.7361, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.863356554109344e-05, + "loss": 4.7466, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862517959358292e-05, + "loss": 4.7404, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.86167936460724e-05, + "loss": 4.7309, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.8608407698561874e-05, + "loss": 4.7451, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860005450865882e-05, + "loss": 4.7345, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.85916685611483e-05, + "loss": 4.7316, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858329899244151e-05, + "loss": 4.7522, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.8574913044930995e-05, + "loss": 4.7317, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.8566527097420475e-05, + "loss": 4.7278, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558141149909955e-05, + "loss": 4.7262, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.8549755202399435e-05, + "loss": 4.7386, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.8541369254888915e-05, + "loss": 4.7188, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.8532983307378395e-05, + "loss": 4.7154, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.8524597359867875e-05, + "loss": 4.7148, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851621141235735e-05, + "loss": 4.711, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.8507841843650564e-05, + "loss": 4.71, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.8499455896140044e-05, + "loss": 4.7026, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.8491069948629524e-05, + "loss": 4.7243, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.8482684001119e-05, + "loss": 4.7044, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847429805360848e-05, + "loss": 4.7026, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846592848490169e-05, + "loss": 4.7048, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845755891619491e-05, + "loss": 4.7023, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844917296868439e-05, + "loss": 4.6963, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.844078702117387e-05, + "loss": 4.6777, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843240107366335e-05, + "loss": 4.6842, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842401512615282e-05, + "loss": 4.6713, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.84156291786423e-05, + "loss": 4.6881, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840724323113178e-05, + "loss": 4.6769, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.839885728362126e-05, + "loss": 4.68, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839047133611074e-05, + "loss": 4.6711, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838208538860022e-05, + "loss": 4.6752, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.83736994410897e-05, + "loss": 4.6791, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836532987238292e-05, + "loss": 4.67, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.83569439248724e-05, + "loss": 4.6746, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834855797736188e-05, + "loss": 4.6606, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834017202985136e-05, + "loss": 4.6562, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.833178608234084e-05, + "loss": 4.6653, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.832340013483032e-05, + "loss": 4.6606, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.83150141873198e-05, + "loss": 4.667, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.830662823980928e-05, + "loss": 4.6373, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.8298258671102486e-05, + "loss": 4.6617, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.8289872723591966e-05, + "loss": 4.6371, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.8281503154885175e-05, + "loss": 4.6708, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273117207374655e-05, + "loss": 4.6332, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.8264731259864135e-05, + "loss": 4.6492, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.8256345312353615e-05, + "loss": 4.6379, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8247959364843095e-05, + "loss": 4.6292, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823957341733258e-05, + "loss": 4.6351, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823118746982206e-05, + "loss": 4.6342, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.8222801522311535e-05, + "loss": 4.6158, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.821443195360475e-05, + "loss": 4.6226, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820604600609423e-05, + "loss": 4.6382, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.819766005858371e-05, + "loss": 4.624, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.8189274111073184e-05, + "loss": 4.6218, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.81809045423664e-05, + "loss": 4.6186, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817251859485588e-05, + "loss": 4.6063, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816413264734535e-05, + "loss": 4.6248, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.815574669983483e-05, + "loss": 4.62, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.814736075232432e-05, + "loss": 4.6213, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.8139007562421265e-05, + "loss": 4.6285, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.8130621614910745e-05, + "loss": 4.6234, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.8122235667400224e-05, + "loss": 4.6199, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.8113849719889704e-05, + "loss": 4.5992, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.8105463772379184e-05, + "loss": 4.6108, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809707782486866e-05, + "loss": 4.605, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.808869187735814e-05, + "loss": 4.5942, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808030592984762e-05, + "loss": 4.6048, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.80719199823371e-05, + "loss": 4.6041, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.8063550413630307e-05, + "loss": 4.6135, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.8055164466119786e-05, + "loss": 4.6043, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.8046794897413e-05, + "loss": 4.584, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803840894990248e-05, + "loss": 4.5928, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.803002300239196e-05, + "loss": 4.603, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.802163705488144e-05, + "loss": 4.6049, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801325110737092e-05, + "loss": 4.5946, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.80048651598604e-05, + "loss": 4.5987, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.799649559115361e-05, + "loss": 4.5934, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.798810964364309e-05, + "loss": 4.5815, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.797972369613257e-05, + "loss": 4.5883, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.797133774862205e-05, + "loss": 4.5879, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.796295180111153e-05, + "loss": 4.5774, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.795458223240474e-05, + "loss": 4.5928, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.794619628489423e-05, + "loss": 4.575, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.793781033738371e-05, + "loss": 4.5723, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792942438987319e-05, + "loss": 4.5741, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792103844236267e-05, + "loss": 4.5811, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.791265249485215e-05, + "loss": 4.5785, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.790426654734163e-05, + "loss": 4.5667, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.7895880599831107e-05, + "loss": 4.5663, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.7887494652320587e-05, + "loss": 4.5614, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.7879108704810067e-05, + "loss": 4.5712, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.7870722757299546e-05, + "loss": 4.5476, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.786233680978902e-05, + "loss": 4.5558, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.7853967241082236e-05, + "loss": 4.565, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.7845581293571715e-05, + "loss": 4.5587, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.7837211724864925e-05, + "loss": 4.5587, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.782882577735441e-05, + "loss": 4.5572, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782043982984389e-05, + "loss": 4.5471, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781205388233337e-05, + "loss": 4.556, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.780368431362658e-05, + "loss": 4.5537, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779529836611606e-05, + "loss": 4.553, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.778691241860554e-05, + "loss": 4.5567, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777852647109502e-05, + "loss": 4.5559, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.777014052358449e-05, + "loss": 4.5462, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.776175457607397e-05, + "loss": 4.5402, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775336862856345e-05, + "loss": 4.5509, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.774499905985666e-05, + "loss": 4.5447, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773661311234615e-05, + "loss": 4.5318, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772822716483563e-05, + "loss": 4.5421, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.771984121732511e-05, + "loss": 4.5356, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771145526981459e-05, + "loss": 4.5459, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770306932230407e-05, + "loss": 4.5295, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769468337479355e-05, + "loss": 4.5369, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768629742728303e-05, + "loss": 4.5144, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767792785857624e-05, + "loss": 4.538, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766954191106572e-05, + "loss": 4.5253, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766117234235893e-05, + "loss": 4.5435, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765278639484841e-05, + "loss": 4.5336, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764440044733789e-05, + "loss": 4.531, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.763601449982737e-05, + "loss": 4.5212, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762762855231685e-05, + "loss": 4.5243, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761924260480633e-05, + "loss": 4.5351, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761087303609954e-05, + "loss": 4.5393, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.760248708858902e-05, + "loss": 4.5278, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.75941011410785e-05, + "loss": 4.5237, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758571519356798e-05, + "loss": 4.5221, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.757732924605746e-05, + "loss": 4.5189, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.756894329854694e-05, + "loss": 4.5113, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.756055735103642e-05, + "loss": 4.5196, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.755218778232963e-05, + "loss": 4.5119, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.754380183481911e-05, + "loss": 4.5069, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.753541588730859e-05, + "loss": 4.5095, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.752702993979807e-05, + "loss": 4.5075, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.751864399228755e-05, + "loss": 4.5108, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.751027442358077e-05, + "loss": 4.5118, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.750188847607025e-05, + "loss": 4.5088, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.475302696228027, + "eval_runtime": 295.3079, + "eval_samples_per_second": 1292.18, + "eval_steps_per_second": 40.382, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.749350252855973e-05, + "loss": 4.4942, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748511658104921e-05, + "loss": 4.4973, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747673063353868e-05, + "loss": 4.5066, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746834468602816e-05, + "loss": 4.5038, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.745995873851764e-05, + "loss": 4.5091, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.745157279100712e-05, + "loss": 4.4866, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.74431868434966e-05, + "loss": 4.4975, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.743480089598608e-05, + "loss": 4.4891, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.742641494847556e-05, + "loss": 4.4978, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741802900096504e-05, + "loss": 4.4982, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740964305345452e-05, + "loss": 4.4991, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.7401257105944e-05, + "loss": 4.4996, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739287115843348e-05, + "loss": 4.4754, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.7384501589726696e-05, + "loss": 4.4845, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.7376115642216176e-05, + "loss": 4.4863, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.7367729694705656e-05, + "loss": 4.4776, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.7359343747195135e-05, + "loss": 4.4885, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.7350957799684615e-05, + "loss": 4.4801, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.7342571852174095e-05, + "loss": 4.48, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733418590466357e-05, + "loss": 4.5073, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732579995715305e-05, + "loss": 4.4793, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731741400964253e-05, + "loss": 4.4829, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.730902806213201e-05, + "loss": 4.4795, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730064211462149e-05, + "loss": 4.4944, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.7292272545914704e-05, + "loss": 4.4736, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728390297720791e-05, + "loss": 4.472, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727551702969739e-05, + "loss": 4.4748, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726713108218687e-05, + "loss": 4.4763, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725874513467635e-05, + "loss": 4.4668, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725035918716583e-05, + "loss": 4.4694, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724197323965531e-05, + "loss": 4.4861, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723360367094852e-05, + "loss": 4.4728, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.7225217723438e-05, + "loss": 4.4693, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721683177592748e-05, + "loss": 4.475, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720846220722069e-05, + "loss": 4.4704, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720007625971017e-05, + "loss": 4.4669, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719169031219965e-05, + "loss": 4.4494, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.718330436468914e-05, + "loss": 4.4634, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.717491841717862e-05, + "loss": 4.447, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.71665324696681e-05, + "loss": 4.4617, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.715814652215758e-05, + "loss": 4.4536, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.714976057464706e-05, + "loss": 4.4612, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714137462713654e-05, + "loss": 4.453, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.7133021437233476e-05, + "loss": 4.4553, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.7124635489722956e-05, + "loss": 4.458, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.7116249542212436e-05, + "loss": 4.4559, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.7107863594701916e-05, + "loss": 4.4604, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.7099477647191396e-05, + "loss": 4.4454, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.7091091699680876e-05, + "loss": 4.4397, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.7082705752170356e-05, + "loss": 4.457, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.707433618346357e-05, + "loss": 4.4485, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706595023595305e-05, + "loss": 4.4521, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705756428844253e-05, + "loss": 4.431, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704917834093201e-05, + "loss": 4.4565, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704079239342149e-05, + "loss": 4.43, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703240644591097e-05, + "loss": 4.4617, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.702402049840045e-05, + "loss": 4.4222, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015634550889924e-05, + "loss": 4.4472, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.7007248603379404e-05, + "loss": 4.4354, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.6998862655868884e-05, + "loss": 4.4333, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.6990476708358364e-05, + "loss": 4.4319, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.6982090760847844e-05, + "loss": 4.4354, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697372119214106e-05, + "loss": 4.4184, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696533524463054e-05, + "loss": 4.4239, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.6956965675923756e-05, + "loss": 4.4344, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694857972841323e-05, + "loss": 4.4315, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694019378090271e-05, + "loss": 4.4241, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.6931824212195925e-05, + "loss": 4.423, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.69234382646854e-05, + "loss": 4.4186, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691505231717488e-05, + "loss": 4.4273, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690666636966436e-05, + "loss": 4.4269, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689828042215384e-05, + "loss": 4.4286, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.688989447464332e-05, + "loss": 4.4373, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.68815085271328e-05, + "loss": 4.4361, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687312257962228e-05, + "loss": 4.4337, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.6864753010915494e-05, + "loss": 4.4117, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.6856367063404974e-05, + "loss": 4.4232, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6847981115894454e-05, + "loss": 4.4254, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.6839595168383934e-05, + "loss": 4.4072, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.6831209220873414e-05, + "loss": 4.4212, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.6822823273362894e-05, + "loss": 4.4194, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.6814437325852373e-05, + "loss": 4.429, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.6806051378341853e-05, + "loss": 4.4202, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679768180963506e-05, + "loss": 4.4017, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678931224092827e-05, + "loss": 4.4145, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678092629341775e-05, + "loss": 4.4203, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.677254034590723e-05, + "loss": 4.4248, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676415439839671e-05, + "loss": 4.4169, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675578482968993e-05, + "loss": 4.4227, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674739888217941e-05, + "loss": 4.4185, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.673901293466889e-05, + "loss": 4.4025, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673062698715837e-05, + "loss": 4.4166, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.672224103964785e-05, + "loss": 4.4096, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671385509213733e-05, + "loss": 4.402, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.6705485523430536e-05, + "loss": 4.423, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.6697099575920016e-05, + "loss": 4.4047, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.6688713628409496e-05, + "loss": 4.3965, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.6680327680898976e-05, + "loss": 4.405, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.6671941733388456e-05, + "loss": 4.4113, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.6663555785877936e-05, + "loss": 4.4096, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.6655186217171145e-05, + "loss": 4.4004, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664681664846436e-05, + "loss": 4.3942, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663843070095384e-05, + "loss": 4.3941, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663004475344332e-05, + "loss": 4.4058, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.66216588059328e-05, + "loss": 4.3811, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661327285842228e-05, + "loss": 4.3936, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660488691091176e-05, + "loss": 4.3997, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.6596500963401234e-05, + "loss": 4.3944, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.6588115015890714e-05, + "loss": 4.3943, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.6579729068380194e-05, + "loss": 4.3962, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.6571343120869674e-05, + "loss": 4.3874, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.6562957173359154e-05, + "loss": 4.393, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655458760465237e-05, + "loss": 4.3933, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654620165714185e-05, + "loss": 4.3904, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.653781570963133e-05, + "loss": 4.3973, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652942976212081e-05, + "loss": 4.3978, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.652106019341402e-05, + "loss": 4.3935, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.65126742459035e-05, + "loss": 4.3799, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650428829839298e-05, + "loss": 4.3887, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649590235088246e-05, + "loss": 4.3871, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648751640337194e-05, + "loss": 4.3748, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647913045586142e-05, + "loss": 4.3902, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647076088715463e-05, + "loss": 4.3759, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.646237493964411e-05, + "loss": 4.3903, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645398899213359e-05, + "loss": 4.3751, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644560304462307e-05, + "loss": 4.3838, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.6437217097112554e-05, + "loss": 4.365, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.642884752840576e-05, + "loss": 4.3846, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642046158089524e-05, + "loss": 4.3705, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.641207563338472e-05, + "loss": 4.3915, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.64036896858742e-05, + "loss": 4.3868, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.639530373836368e-05, + "loss": 4.3797, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.638691779085316e-05, + "loss": 4.3694, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637854822214637e-05, + "loss": 4.3743, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637016227463585e-05, + "loss": 4.3868, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636177632712533e-05, + "loss": 4.3923, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.635339037961481e-05, + "loss": 4.3774, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.634500443210429e-05, + "loss": 4.3786, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633661848459377e-05, + "loss": 4.3771, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632823253708325e-05, + "loss": 4.3755, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.631986296837647e-05, + "loss": 4.3671, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631147702086595e-05, + "loss": 4.3709, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.630309107335542e-05, + "loss": 4.3696, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.62947051258449e-05, + "loss": 4.3644, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.628631917833438e-05, + "loss": 4.3651, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.627793323082386e-05, + "loss": 4.369, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626954728331334e-05, + "loss": 4.3627, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626117771460655e-05, + "loss": 4.3693, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625279176709603e-05, + "loss": 4.3647, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 4.341277122497559, + "eval_runtime": 300.372, + "eval_samples_per_second": 1270.395, + "eval_steps_per_second": 39.701, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624440581958551e-05, + "loss": 4.3616, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623601987207499e-05, + "loss": 4.3538, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.6227633924564476e-05, + "loss": 4.3705, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.6219247977053956e-05, + "loss": 4.361, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.6210862029543436e-05, + "loss": 4.3702, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.6202476082032916e-05, + "loss": 4.348, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.6194106513326125e-05, + "loss": 4.3599, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.6185720565815605e-05, + "loss": 4.3488, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.6177350997108814e-05, + "loss": 4.3648, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.6168965049598294e-05, + "loss": 4.3605, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.6160579102087774e-05, + "loss": 4.3626, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.6152193154577254e-05, + "loss": 4.3637, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.6143807207066734e-05, + "loss": 4.3417, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.6135421259556214e-05, + "loss": 4.3507, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.612705169084942e-05, + "loss": 4.351, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611866574333891e-05, + "loss": 4.3482, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.611027979582839e-05, + "loss": 4.3516, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.610189384831787e-05, + "loss": 4.352, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.609350790080735e-05, + "loss": 4.3449, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.608512195329683e-05, + "loss": 4.3786, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.607673600578631e-05, + "loss": 4.3471, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.606835005827578e-05, + "loss": 4.3499, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.6059980489569e-05, + "loss": 4.3513, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.605161092086221e-05, + "loss": 4.3616, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.604322497335169e-05, + "loss": 4.3433, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.603483902584117e-05, + "loss": 4.3483, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.602645307833065e-05, + "loss": 4.3438, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.6018083509623864e-05, + "loss": 4.3462, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.6009697562113344e-05, + "loss": 4.3361, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.6001311614602824e-05, + "loss": 4.3455, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.5992925667092303e-05, + "loss": 4.355, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598455609838551e-05, + "loss": 4.3473, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.597617015087499e-05, + "loss": 4.3465, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.596778420336447e-05, + "loss": 4.346, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.595941463465768e-05, + "loss": 4.3446, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.595102868714716e-05, + "loss": 4.3481, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.594264273963664e-05, + "loss": 4.3249, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.593425679212612e-05, + "loss": 4.3405, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.59258708446156e-05, + "loss": 4.3229, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.591748489710508e-05, + "loss": 4.3389, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.59091153283983e-05, + "loss": 4.3332, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590072938088778e-05, + "loss": 4.3407, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.589234343337726e-05, + "loss": 4.3328, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.588395748586673e-05, + "loss": 4.3318, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.587557153835621e-05, + "loss": 4.3399, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.586718559084569e-05, + "loss": 4.3358, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585879964333517e-05, + "loss": 4.3362, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585041369582465e-05, + "loss": 4.3297, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.584204412711786e-05, + "loss": 4.3156, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583365817960734e-05, + "loss": 4.3369, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582527223209682e-05, + "loss": 4.3288, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.58168862845863e-05, + "loss": 4.3319, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.5808516715879515e-05, + "loss": 4.3182, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.5800130768368995e-05, + "loss": 4.3408, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.5791744820858475e-05, + "loss": 4.3075, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.5783358873347955e-05, + "loss": 4.3444, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.5774972925837435e-05, + "loss": 4.3079, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.5766586978326915e-05, + "loss": 4.3267, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.5758201030816395e-05, + "loss": 4.3205, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.5749815083305875e-05, + "loss": 4.3193, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.5741429135795355e-05, + "loss": 4.3146, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.5733059567088564e-05, + "loss": 4.3265, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.572468999838177e-05, + "loss": 4.3017, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.571630405087125e-05, + "loss": 4.3088, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.570791810336074e-05, + "loss": 4.3236, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569953215585022e-05, + "loss": 4.3179, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.56911462083397e-05, + "loss": 4.313, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.568276026082918e-05, + "loss": 4.3128, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.567437431331866e-05, + "loss": 4.3015, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.566598836580814e-05, + "loss": 4.314, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.565763517590508e-05, + "loss": 4.3163, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.564924922839456e-05, + "loss": 4.3185, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.564086328088404e-05, + "loss": 4.3272, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.563247733337352e-05, + "loss": 4.3237, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.5624107764666726e-05, + "loss": 4.3237, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.5615721817156206e-05, + "loss": 4.3029, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.560735224844942e-05, + "loss": 4.3106, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.55989663009389e-05, + "loss": 4.3175, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.559058035342838e-05, + "loss": 4.2997, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.558219440591786e-05, + "loss": 4.3137, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557380845840734e-05, + "loss": 4.3086, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556543888970055e-05, + "loss": 4.3189, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.555706932099376e-05, + "loss": 4.3138, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.554869975228697e-05, + "loss": 4.2971, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.554031380477645e-05, + "loss": 4.3101, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553192785726593e-05, + "loss": 4.3096, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.5523541909755416e-05, + "loss": 4.3196, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.5515155962244896e-05, + "loss": 4.3116, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.5506770014734376e-05, + "loss": 4.3141, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.5498384067223856e-05, + "loss": 4.3166, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.5489998119713336e-05, + "loss": 4.2962, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.5481612172202816e-05, + "loss": 4.312, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.5473226224692296e-05, + "loss": 4.3011, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.5464840277181776e-05, + "loss": 4.3024, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.5456454329671256e-05, + "loss": 4.3156, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.5448068382160736e-05, + "loss": 4.3029, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.5439682434650216e-05, + "loss": 4.2916, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.543129648713969e-05, + "loss": 4.3007, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542291053962917e-05, + "loss": 4.3109, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541452459211865e-05, + "loss": 4.3083, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.540613864460813e-05, + "loss": 4.2976, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.539775269709761e-05, + "loss": 4.292, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.5389366749587095e-05, + "loss": 4.2926, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.5380997180880304e-05, + "loss": 4.306, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.5372611233369784e-05, + "loss": 4.279, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.5364225285859264e-05, + "loss": 4.2918, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.5355839338348744e-05, + "loss": 4.2994, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.5347469769641953e-05, + "loss": 4.2973, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.533910020093516e-05, + "loss": 4.2897, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.533071425342464e-05, + "loss": 4.2997, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.532232830591412e-05, + "loss": 4.29, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.53139423584036e-05, + "loss": 4.2915, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.530555641089308e-05, + "loss": 4.295, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.52971868421863e-05, + "loss": 4.2913, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.528880089467578e-05, + "loss": 4.3032, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.528041494716526e-05, + "loss": 4.2957, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.527202899965474e-05, + "loss": 4.2963, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.526364305214422e-05, + "loss": 4.282, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.525527348343743e-05, + "loss": 4.2923, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.524688753592691e-05, + "loss": 4.2912, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.523850158841639e-05, + "loss": 4.2789, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.523011564090587e-05, + "loss": 4.2926, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.522172969339535e-05, + "loss": 4.2827, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.521334374588483e-05, + "loss": 4.2922, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.5204974177178036e-05, + "loss": 4.2804, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.5196588229667516e-05, + "loss": 4.2897, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.5188202282157e-05, + "loss": 4.2642, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.517981633464648e-05, + "loss": 4.2922, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.517143038713596e-05, + "loss": 4.2778, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516304443962544e-05, + "loss": 4.2931, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515467487091865e-05, + "loss": 4.291, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.514628892340813e-05, + "loss": 4.2905, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513790297589761e-05, + "loss": 4.2723, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.512953340719082e-05, + "loss": 4.2849, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.51211474596803e-05, + "loss": 4.2909, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.511276151216978e-05, + "loss": 4.2961, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.510437556465926e-05, + "loss": 4.2861, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.509598961714874e-05, + "loss": 4.2846, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.508760366963822e-05, + "loss": 4.2851, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.50792177221277e-05, + "loss": 4.2864, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.507083177461718e-05, + "loss": 4.2718, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.506244582710666e-05, + "loss": 4.2788, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.505405987959614e-05, + "loss": 4.2766, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.504569031088935e-05, + "loss": 4.2731, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.503730436337883e-05, + "loss": 4.2738, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.502891841586831e-05, + "loss": 4.2823, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.502053246835779e-05, + "loss": 4.2713, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.5012162899651e-05, + "loss": 4.2757, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.500377695214048e-05, + "loss": 4.2824, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 4.258530616760254, + "eval_runtime": 297.5439, + "eval_samples_per_second": 1282.47, + "eval_steps_per_second": 40.078, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.499539100462996e-05, + "loss": 4.2631, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.498700505711944e-05, + "loss": 4.267, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.4978619109608925e-05, + "loss": 4.2794, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.4970233162098405e-05, + "loss": 4.2717, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.4961847214587885e-05, + "loss": 4.2845, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.4953461267077365e-05, + "loss": 4.2606, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.4945075319566845e-05, + "loss": 4.2694, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.4936689372056325e-05, + "loss": 4.2617, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.4928303424545805e-05, + "loss": 4.2765, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.4919917477035285e-05, + "loss": 4.2743, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.4911531529524765e-05, + "loss": 4.2669, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490314558201424e-05, + "loss": 4.282, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489475963450372e-05, + "loss": 4.2524, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.48863736869932e-05, + "loss": 4.2639, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487800411828641e-05, + "loss": 4.2673, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.486961817077589e-05, + "loss": 4.2584, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.4861232223265373e-05, + "loss": 4.2644, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.4852846275754853e-05, + "loss": 4.2646, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.484446032824433e-05, + "loss": 4.2614, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483609075953754e-05, + "loss": 4.2894, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482770481202702e-05, + "loss": 4.2625, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.48193188645165e-05, + "loss": 4.2616, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481093291700598e-05, + "loss": 4.2697, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480254696949546e-05, + "loss": 4.2754, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479416102198494e-05, + "loss": 4.2565, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478577507447442e-05, + "loss": 4.2672, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.47773891269639e-05, + "loss": 4.2564, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476900317945338e-05, + "loss": 4.2631, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476061723194286e-05, + "loss": 4.2535, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475223128443234e-05, + "loss": 4.2627, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474384533692182e-05, + "loss": 4.2745, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473547576821504e-05, + "loss": 4.2635, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472710619950825e-05, + "loss": 4.2614, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471872025199773e-05, + "loss": 4.2652, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.4710350683290936e-05, + "loss": 4.262, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.4701964735780416e-05, + "loss": 4.2643, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.4693578788269896e-05, + "loss": 4.244, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.4685192840759376e-05, + "loss": 4.2554, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.4676806893248856e-05, + "loss": 4.247, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.4668420945738336e-05, + "loss": 4.2524, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.4660034998227816e-05, + "loss": 4.2542, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.4651649050717296e-05, + "loss": 4.2588, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.4643263103206776e-05, + "loss": 4.2511, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463489353449999e-05, + "loss": 4.2544, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462650758698947e-05, + "loss": 4.2569, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461812163947895e-05, + "loss": 4.2539, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.4609735691968425e-05, + "loss": 4.2574, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.4601349744457905e-05, + "loss": 4.2505, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.4592963796947384e-05, + "loss": 4.2358, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.4584577849436864e-05, + "loss": 4.2578, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.4576191901926344e-05, + "loss": 4.2469, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.4567822333219554e-05, + "loss": 4.2547, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.455945276451277e-05, + "loss": 4.2415, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.455106681700225e-05, + "loss": 4.2547, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.454268086949173e-05, + "loss": 4.2327, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.453429492198121e-05, + "loss": 4.2635, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.452590897447069e-05, + "loss": 4.2314, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.451752302696017e-05, + "loss": 4.2429, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450913707944965e-05, + "loss": 4.2487, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450075113193913e-05, + "loss": 4.2388, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.449236518442861e-05, + "loss": 4.2411, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448399561572182e-05, + "loss": 4.2447, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.44756096682113e-05, + "loss": 4.2321, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446724009950451e-05, + "loss": 4.2299, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445885415199399e-05, + "loss": 4.2432, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445046820448347e-05, + "loss": 4.2431, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444208225697295e-05, + "loss": 4.2334, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443369630946243e-05, + "loss": 4.24, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.4425310361951914e-05, + "loss": 4.2219, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.4416924414441394e-05, + "loss": 4.2398, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.4408538466930874e-05, + "loss": 4.2406, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440016889822408e-05, + "loss": 4.2409, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439178295071356e-05, + "loss": 4.2493, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438341338200677e-05, + "loss": 4.2477, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437502743449625e-05, + "loss": 4.253, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436664148698573e-05, + "loss": 4.2274, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435825553947521e-05, + "loss": 4.2364, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.434986959196469e-05, + "loss": 4.2416, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.43415000232579e-05, + "loss": 4.2201, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433311407574738e-05, + "loss": 4.2421, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.432472812823687e-05, + "loss": 4.2354, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431634218072635e-05, + "loss": 4.2429, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.430795623321583e-05, + "loss": 4.2422, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.4299586664509036e-05, + "loss": 4.2228, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.4291200716998516e-05, + "loss": 4.2376, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.4282814769487996e-05, + "loss": 4.2344, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.4274428821977476e-05, + "loss": 4.244, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.4266042874466956e-05, + "loss": 4.2363, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.425765692695643e-05, + "loss": 4.2438, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.424927097944591e-05, + "loss": 4.2402, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424088503193539e-05, + "loss": 4.2267, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.4232515463228605e-05, + "loss": 4.2391, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.4224129515718085e-05, + "loss": 4.2259, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.42157599470113e-05, + "loss": 4.2344, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420737399950078e-05, + "loss": 4.2442, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419898805199026e-05, + "loss": 4.2271, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.4190602104479734e-05, + "loss": 4.2227, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.4182216156969214e-05, + "loss": 4.2276, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.417384658826243e-05, + "loss": 4.2348, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.41654606407519e-05, + "loss": 4.2407, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415707469324138e-05, + "loss": 4.2234, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.414868874573086e-05, + "loss": 4.2232, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414031917702408e-05, + "loss": 4.2193, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413193322951356e-05, + "loss": 4.2358, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412354728200304e-05, + "loss": 4.2086, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.4115177713296255e-05, + "loss": 4.2219, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.4106791765785735e-05, + "loss": 4.2296, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409840581827521e-05, + "loss": 4.2228, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409001987076469e-05, + "loss": 4.2199, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408163392325417e-05, + "loss": 4.2316, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407324797574365e-05, + "loss": 4.2199, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406487840703686e-05, + "loss": 4.2172, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405649245952634e-05, + "loss": 4.2266, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404810651201582e-05, + "loss": 4.2251, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.40397205645053e-05, + "loss": 4.232, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.4031334616994777e-05, + "loss": 4.229, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.4022948669484257e-05, + "loss": 4.2274, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401456272197374e-05, + "loss": 4.2127, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400617677446322e-05, + "loss": 4.2227, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.39977908269527e-05, + "loss": 4.2211, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398940487944218e-05, + "loss": 4.2076, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398103531073539e-05, + "loss": 4.2278, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397264936322487e-05, + "loss": 4.2105, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396426341571435e-05, + "loss": 4.2239, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395587746820383e-05, + "loss": 4.2171, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394750789949704e-05, + "loss": 4.2199, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393912195198652e-05, + "loss": 4.1988, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.3930736004476e-05, + "loss": 4.2196, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392235005696548e-05, + "loss": 4.2158, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.391396410945496e-05, + "loss": 4.2216, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.390559454074818e-05, + "loss": 4.222, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.389720859323766e-05, + "loss": 4.2268, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.388882264572714e-05, + "loss": 4.2037, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388043669821662e-05, + "loss": 4.2205, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.3872067129509826e-05, + "loss": 4.2278, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.3863681181999306e-05, + "loss": 4.2257, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.3855295234488786e-05, + "loss": 4.2197, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.3846909286978266e-05, + "loss": 4.2243, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.3838539718271475e-05, + "loss": 4.2167, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.3830153770760955e-05, + "loss": 4.2209, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.3821767823250435e-05, + "loss": 4.2017, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.3813381875739915e-05, + "loss": 4.2156, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.3804995928229395e-05, + "loss": 4.2084, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379662635952261e-05, + "loss": 4.2109, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378824041201209e-05, + "loss": 4.2111, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.3779854464501564e-05, + "loss": 4.2109, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.3771468516991044e-05, + "loss": 4.2102, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.3763082569480524e-05, + "loss": 4.2088, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.3754696621970004e-05, + "loss": 4.2205, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 4.202013969421387, + "eval_runtime": 284.1681, + "eval_samples_per_second": 1342.835, + "eval_steps_per_second": 41.965, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.374632705326321e-05, + "loss": 4.2062, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.373794110575269e-05, + "loss": 4.1998, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.372955515824217e-05, + "loss": 4.2128, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.372116921073165e-05, + "loss": 4.2115, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.371278326322113e-05, + "loss": 4.2127, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.370441369451435e-05, + "loss": 4.2021, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369602774700383e-05, + "loss": 4.2007, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368764179949331e-05, + "loss": 4.2024, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.367925585198279e-05, + "loss": 4.206, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.3670886283276e-05, + "loss": 4.216, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366250033576548e-05, + "loss": 4.204, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365411438825496e-05, + "loss": 4.2159, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.364572844074444e-05, + "loss": 4.1941, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.363734249323392e-05, + "loss": 4.1992, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.3628972924527126e-05, + "loss": 4.2062, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.3620586977016606e-05, + "loss": 4.1924, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.361221740830982e-05, + "loss": 4.2009, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.36038314607993e-05, + "loss": 4.2037, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.359544551328878e-05, + "loss": 4.196, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.358705956577826e-05, + "loss": 4.2245, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.357867361826774e-05, + "loss": 4.2056, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.357028767075722e-05, + "loss": 4.2022, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.35619017232467e-05, + "loss": 4.2064, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.355351577573618e-05, + "loss": 4.2151, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.354512982822566e-05, + "loss": 4.1943, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.353674388071514e-05, + "loss": 4.2038, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.352835793320462e-05, + "loss": 4.1997, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.35199719856941e-05, + "loss": 4.1973, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.351160241698731e-05, + "loss": 4.1901, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.350321646947679e-05, + "loss": 4.2038, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.349483052196627e-05, + "loss": 4.2133, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.348644457445575e-05, + "loss": 4.2025, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.3478075005748966e-05, + "loss": 4.2051, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.3469705437042175e-05, + "loss": 4.2018, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.3461335868335385e-05, + "loss": 4.1992, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.3452949920824865e-05, + "loss": 4.2032, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.3444563973314344e-05, + "loss": 4.1896, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.3436178025803824e-05, + "loss": 4.1919, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.3427792078293304e-05, + "loss": 4.1855, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.3419406130782784e-05, + "loss": 4.1912, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.3411020183272264e-05, + "loss": 4.1955, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.3402634235761744e-05, + "loss": 4.1986, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.3394248288251224e-05, + "loss": 4.1891, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.3385862340740704e-05, + "loss": 4.194, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.3377476393230184e-05, + "loss": 4.1998, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.3369090445719664e-05, + "loss": 4.195, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.336072087701287e-05, + "loss": 4.1979, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.335233492950235e-05, + "loss": 4.1919, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.334394898199183e-05, + "loss": 4.1756, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.333557941328505e-05, + "loss": 4.201, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.332719346577452e-05, + "loss": 4.1876, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.3318807518264e-05, + "loss": 4.1956, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331042157075348e-05, + "loss": 4.1835, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.33020520020467e-05, + "loss": 4.1938, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.329366605453618e-05, + "loss": 4.1757, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.328528010702566e-05, + "loss": 4.2015, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.3276910538318874e-05, + "loss": 4.1742, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.326852459080835e-05, + "loss": 4.1867, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.326013864329783e-05, + "loss": 4.1921, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.325175269578731e-05, + "loss": 4.1803, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.324336674827679e-05, + "loss": 4.1797, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.323498080076627e-05, + "loss": 4.1934, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.322659485325575e-05, + "loss": 4.1717, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.321820890574523e-05, + "loss": 4.1702, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.3209822958234707e-05, + "loss": 4.186, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.3201437010724187e-05, + "loss": 4.189, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.3193051063213666e-05, + "loss": 4.175, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.3184665115703146e-05, + "loss": 4.1859, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.317631192580009e-05, + "loss": 4.1617, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.316792597828957e-05, + "loss": 4.1789, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.315954003077905e-05, + "loss": 4.185, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.315115408326853e-05, + "loss": 4.1861, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.314276813575801e-05, + "loss": 4.1906, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.313438218824749e-05, + "loss": 4.1896, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.312599624073697e-05, + "loss": 4.1995, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.311761029322645e-05, + "loss": 4.1686, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.310922434571593e-05, + "loss": 4.1831, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.310087115581287e-05, + "loss": 4.1878, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.309248520830235e-05, + "loss": 4.1634, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.308409926079183e-05, + "loss": 4.1853, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.3075713313281316e-05, + "loss": 4.1795, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.3067327365770796e-05, + "loss": 4.1867, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.3058957797064005e-05, + "loss": 4.1871, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.3050571849553485e-05, + "loss": 4.1706, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.3042185902042965e-05, + "loss": 4.1775, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.3033799954532445e-05, + "loss": 4.1779, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.3025414007021925e-05, + "loss": 4.1913, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.3017028059511405e-05, + "loss": 4.177, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.3008642112000885e-05, + "loss": 4.1896, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.300025616449036e-05, + "loss": 4.1888, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.2991886595783574e-05, + "loss": 4.1728, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.2983500648273054e-05, + "loss": 4.1821, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.2975114700762534e-05, + "loss": 4.1709, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.296674513205575e-05, + "loss": 4.1816, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.295835918454523e-05, + "loss": 4.1915, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.294997323703471e-05, + "loss": 4.1695, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.294158728952418e-05, + "loss": 4.1734, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.293320134201366e-05, + "loss": 4.1695, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.292483177330688e-05, + "loss": 4.1827, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.291644582579636e-05, + "loss": 4.1908, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.290805987828583e-05, + "loss": 4.1718, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.289969030957905e-05, + "loss": 4.1698, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.289130436206853e-05, + "loss": 4.1626, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.288291841455801e-05, + "loss": 4.1846, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.287453246704749e-05, + "loss": 4.1538, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.286614651953697e-05, + "loss": 4.1709, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.285776057202645e-05, + "loss": 4.1711, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.284937462451593e-05, + "loss": 4.1745, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.284098867700541e-05, + "loss": 4.1679, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.283260272949489e-05, + "loss": 4.1751, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.282421678198437e-05, + "loss": 4.1704, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.281583083447385e-05, + "loss": 4.1647, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.280744488696333e-05, + "loss": 4.1739, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.2799075318256536e-05, + "loss": 4.1736, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.2790689370746016e-05, + "loss": 4.1786, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.2782303423235496e-05, + "loss": 4.1795, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.2773933854528705e-05, + "loss": 4.1719, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.276554790701819e-05, + "loss": 4.1627, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.275716195950767e-05, + "loss": 4.1698, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.274877601199715e-05, + "loss": 4.1715, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.274039006448663e-05, + "loss": 4.1595, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.273202049577984e-05, + "loss": 4.1723, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.272363454826932e-05, + "loss": 4.1595, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.27152486007588e-05, + "loss": 4.1711, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.270686265324828e-05, + "loss": 4.1668, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.269847670573776e-05, + "loss": 4.1668, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.269009075822724e-05, + "loss": 4.1534, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.2681704810716714e-05, + "loss": 4.1648, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.2673318863206194e-05, + "loss": 4.1654, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.2664932915695674e-05, + "loss": 4.1726, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.265656334698889e-05, + "loss": 4.1667, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264817739947837e-05, + "loss": 4.1743, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.263979145196785e-05, + "loss": 4.1559, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.263140550445733e-05, + "loss": 4.1687, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.2623035935750545e-05, + "loss": 4.1771, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.261464998824002e-05, + "loss": 4.173, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.26062640407295e-05, + "loss": 4.1712, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.259787809321898e-05, + "loss": 4.1757, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.258950852451219e-05, + "loss": 4.1634, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.258112257700167e-05, + "loss": 4.1721, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.257273662949115e-05, + "loss": 4.154, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256435068198063e-05, + "loss": 4.1665, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.255598111327384e-05, + "loss": 4.1582, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.254759516576332e-05, + "loss": 4.16, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.25392092182528e-05, + "loss": 4.1625, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253082327074228e-05, + "loss": 4.1581, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252243732323176e-05, + "loss": 4.1686, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.251408413332871e-05, + "loss": 4.1513, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.250569818581819e-05, + "loss": 4.174, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 4.160501956939697, + "eval_runtime": 290.4595, + "eval_samples_per_second": 1313.749, + "eval_steps_per_second": 41.056, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.249731223830766e-05, + "loss": 4.1538, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248892629079714e-05, + "loss": 4.1509, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248054034328662e-05, + "loss": 4.1652, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.24721543957761e-05, + "loss": 4.1635, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.246376844826558e-05, + "loss": 4.1646, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245538250075506e-05, + "loss": 4.1545, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.244699655324455e-05, + "loss": 4.1478, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243861060573403e-05, + "loss": 4.156, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243022465822351e-05, + "loss": 4.1585, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.242183871071299e-05, + "loss": 4.1664, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241345276320247e-05, + "loss": 4.1584, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240506681569195e-05, + "loss": 4.1641, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239668086818143e-05, + "loss": 4.1498, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238829492067091e-05, + "loss": 4.1511, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.237990897316038e-05, + "loss": 4.1576, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237152302564986e-05, + "loss": 4.1435, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236313707813934e-05, + "loss": 4.1521, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.235476750943255e-05, + "loss": 4.1572, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.234638156192203e-05, + "loss": 4.1497, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.2337995614411516e-05, + "loss": 4.1736, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.2329609666900996e-05, + "loss": 4.1635, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.2321223719390476e-05, + "loss": 4.152, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.2312837771879956e-05, + "loss": 4.1597, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.2304451824369436e-05, + "loss": 4.1701, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.2296065876858916e-05, + "loss": 4.1446, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.2287696308152125e-05, + "loss": 4.159, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.2279326739445334e-05, + "loss": 4.149, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.2270940791934814e-05, + "loss": 4.1508, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.2262554844424294e-05, + "loss": 4.1453, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.2254168896913774e-05, + "loss": 4.1545, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.2245782949403254e-05, + "loss": 4.1627, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223741338069647e-05, + "loss": 4.1556, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.222902743318595e-05, + "loss": 4.1607, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222064148567543e-05, + "loss": 4.1581, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221227191696864e-05, + "loss": 4.1485, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.220390234826185e-05, + "loss": 4.1562, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219551640075133e-05, + "loss": 4.1463, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.218713045324081e-05, + "loss": 4.144, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.217874450573029e-05, + "loss": 4.1407, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217035855821977e-05, + "loss": 4.1431, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216197261070925e-05, + "loss": 4.1489, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.215358666319873e-05, + "loss": 4.154, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.214520071568821e-05, + "loss": 4.1449, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.213681476817769e-05, + "loss": 4.1468, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.212842882066717e-05, + "loss": 4.154, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.212004287315665e-05, + "loss": 4.1484, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.2111656925646134e-05, + "loss": 4.1534, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.2103270978135614e-05, + "loss": 4.1459, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.2094901409428823e-05, + "loss": 4.127, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.20865154619183e-05, + "loss": 4.1582, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207812951440778e-05, + "loss": 4.1416, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.206974356689726e-05, + "loss": 4.153, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.2061357619386736e-05, + "loss": 4.1425, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.2052971671876216e-05, + "loss": 4.1428, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204460210316943e-05, + "loss": 4.1371, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.203621615565891e-05, + "loss": 4.1491, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.2027830208148385e-05, + "loss": 4.1342, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.201944426063787e-05, + "loss": 4.142, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.201105831312735e-05, + "loss": 4.1526, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200267236561683e-05, + "loss": 4.1315, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199428641810631e-05, + "loss": 4.1339, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.198590047059579e-05, + "loss": 4.1523, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.1977530901889e-05, + "loss": 4.1226, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196914495437848e-05, + "loss": 4.126, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.196075900686796e-05, + "loss": 4.1405, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195237305935744e-05, + "loss": 4.144, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194398711184692e-05, + "loss": 4.1333, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193561754314013e-05, + "loss": 4.1446, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192723159562961e-05, + "loss": 4.1202, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.1918862026922826e-05, + "loss": 4.1352, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.1910476079412306e-05, + "loss": 4.143, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.1902090131901786e-05, + "loss": 4.1414, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.1893704184391266e-05, + "loss": 4.1466, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.1885318236880746e-05, + "loss": 4.1477, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.1876948668173955e-05, + "loss": 4.1539, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.1868579099467164e-05, + "loss": 4.1278, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.1860193151956644e-05, + "loss": 4.1389, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185182358324986e-05, + "loss": 4.1442, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184343763573933e-05, + "loss": 4.1222, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183505168822881e-05, + "loss": 4.1412, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182666574071829e-05, + "loss": 4.1371, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181827979320778e-05, + "loss": 4.1453, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.180989384569726e-05, + "loss": 4.1428, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180150789818674e-05, + "loss": 4.1299, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.179312195067622e-05, + "loss": 4.1323, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.17847360031657e-05, + "loss": 4.1381, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.177635005565518e-05, + "loss": 4.1431, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.176796410814466e-05, + "loss": 4.1393, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.175957816063414e-05, + "loss": 4.1463, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175119221312362e-05, + "loss": 4.1455, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.17428062656131e-05, + "loss": 4.1337, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173443669690631e-05, + "loss": 4.1372, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.172605074939579e-05, + "loss": 4.1257, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171766480188527e-05, + "loss": 4.1459, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170927885437475e-05, + "loss": 4.1454, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170089290686423e-05, + "loss": 4.131, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169250695935371e-05, + "loss": 4.1298, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.168412101184319e-05, + "loss": 4.1257, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167573506433267e-05, + "loss": 4.141, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166734911682215e-05, + "loss": 4.1474, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165897954811536e-05, + "loss": 4.1297, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.165060997940857e-05, + "loss": 4.1294, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.1642224031898046e-05, + "loss": 4.1262, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.1633838084387526e-05, + "loss": 4.1383, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.1625452136877006e-05, + "loss": 4.1167, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.1617066189366486e-05, + "loss": 4.1281, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.1608680241855966e-05, + "loss": 4.1225, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160031067314918e-05, + "loss": 4.1384, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159192472563866e-05, + "loss": 4.1274, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158353877812814e-05, + "loss": 4.1363, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157515283061762e-05, + "loss": 4.129, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.15667668831071e-05, + "loss": 4.1218, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155838093559658e-05, + "loss": 4.1345, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.155001136688979e-05, + "loss": 4.1323, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154162541937927e-05, + "loss": 4.1365, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153323947186875e-05, + "loss": 4.1375, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152486990316196e-05, + "loss": 4.1261, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151648395565144e-05, + "loss": 4.1294, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150809800814092e-05, + "loss": 4.1225, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.14997120606304e-05, + "loss": 4.1318, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149132611311988e-05, + "loss": 4.1273, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.1482940165609366e-05, + "loss": 4.1276, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.1474554218098846e-05, + "loss": 4.115, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.1466168270588326e-05, + "loss": 4.1298, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.1457782323077806e-05, + "loss": 4.1247, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.1449396375567286e-05, + "loss": 4.1295, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.144101042805676e-05, + "loss": 4.1115, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.143262448054624e-05, + "loss": 4.1287, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.1424254911839455e-05, + "loss": 4.1228, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.1415885343132664e-05, + "loss": 4.137, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140751577442587e-05, + "loss": 4.1263, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.139912982691535e-05, + "loss": 4.1335, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139074387940483e-05, + "loss": 4.1156, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138235793189432e-05, + "loss": 4.1312, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137398836318753e-05, + "loss": 4.1358, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136560241567701e-05, + "loss": 4.1326, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135721646816649e-05, + "loss": 4.1314, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.134883052065597e-05, + "loss": 4.1358, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.134044457314545e-05, + "loss": 4.1243, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133205862563493e-05, + "loss": 4.1358, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132367267812441e-05, + "loss": 4.1152, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131528673061388e-05, + "loss": 4.1276, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.130690078310336e-05, + "loss": 4.1196, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.129851483559284e-05, + "loss": 4.123, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.129012888808232e-05, + "loss": 4.1189, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128175931937554e-05, + "loss": 4.1162, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127337337186502e-05, + "loss": 4.1278, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.12649874243545e-05, + "loss": 4.1159, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125660147684398e-05, + "loss": 4.137, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 4.129661560058594, + "eval_runtime": 300.887, + "eval_samples_per_second": 1268.22, + "eval_steps_per_second": 39.633, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.124821552933346e-05, + "loss": 4.1159, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.123982958182294e-05, + "loss": 4.1115, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.123144363431242e-05, + "loss": 4.1226, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.12230576868019e-05, + "loss": 4.123, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.1214688118095106e-05, + "loss": 4.1218, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.1206318549388315e-05, + "loss": 4.1192, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.1197932601877795e-05, + "loss": 4.1127, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.1189546654367275e-05, + "loss": 4.1161, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.1181160706856755e-05, + "loss": 4.1217, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.117277475934624e-05, + "loss": 4.1281, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.116440519063945e-05, + "loss": 4.1229, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.115601924312893e-05, + "loss": 4.1204, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.114763329561841e-05, + "loss": 4.1166, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.113924734810789e-05, + "loss": 4.1112, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.113086140059737e-05, + "loss": 4.1185, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.112247545308685e-05, + "loss": 4.1066, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.111408950557633e-05, + "loss": 4.1155, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.110571993686954e-05, + "loss": 4.1178, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.109733398935902e-05, + "loss": 4.1107, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.10889480418485e-05, + "loss": 4.1334, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.108056209433798e-05, + "loss": 4.1285, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.107217614682746e-05, + "loss": 4.1153, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.106379019931694e-05, + "loss": 4.1186, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.105540425180642e-05, + "loss": 4.1311, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.10470183042959e-05, + "loss": 4.1082, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.1038665114392845e-05, + "loss": 4.1215, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.1030279166882325e-05, + "loss": 4.1139, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.1021893219371805e-05, + "loss": 4.1127, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.1013507271861285e-05, + "loss": 4.107, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.1005137703154494e-05, + "loss": 4.1216, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.0996751755643974e-05, + "loss": 4.1216, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.0988365808133454e-05, + "loss": 4.1208, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.0979979860622933e-05, + "loss": 4.1233, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.0971593913112413e-05, + "loss": 4.1145, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.096320796560189e-05, + "loss": 4.1128, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.095482201809137e-05, + "loss": 4.1206, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.094643607058085e-05, + "loss": 4.1113, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.093805012307033e-05, + "loss": 4.1017, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.092966417555981e-05, + "loss": 4.1056, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.092127822804929e-05, + "loss": 4.1063, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.091289228053877e-05, + "loss": 4.1104, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.090452271183198e-05, + "loss": 4.1171, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.089613676432146e-05, + "loss": 4.1099, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.088775081681094e-05, + "loss": 4.1083, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.087936486930042e-05, + "loss": 4.1185, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.087099530059363e-05, + "loss": 4.1138, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086260935308311e-05, + "loss": 4.1161, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.08542234055726e-05, + "loss": 4.1123, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084583745806208e-05, + "loss": 4.0848, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.083745151055156e-05, + "loss": 4.125, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.082908194184477e-05, + "loss": 4.1034, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082069599433425e-05, + "loss": 4.1174, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081231004682373e-05, + "loss": 4.1037, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080392409931321e-05, + "loss": 4.1087, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.079553815180269e-05, + "loss": 4.1014, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078715220429217e-05, + "loss": 4.1127, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.0778766256781647e-05, + "loss": 4.1002, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.0770380309271127e-05, + "loss": 4.1042, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.0762010740564336e-05, + "loss": 4.1167, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.0753624793053816e-05, + "loss": 4.0993, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.0745238845543296e-05, + "loss": 4.0959, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.073686927683651e-05, + "loss": 4.1149, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.072848332932599e-05, + "loss": 4.0914, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.072009738181547e-05, + "loss": 4.0896, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071171143430495e-05, + "loss": 4.106, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.070334186559816e-05, + "loss": 4.1075, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.069495591808764e-05, + "loss": 4.0985, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.068656997057712e-05, + "loss": 4.1074, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.06781840230666e-05, + "loss": 4.0827, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.066979807555608e-05, + "loss": 4.1005, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.0661412128045553e-05, + "loss": 4.1087, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.065302618053503e-05, + "loss": 4.1051, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.064464023302452e-05, + "loss": 4.113, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.0636254285514e-05, + "loss": 4.1102, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.062788471680721e-05, + "loss": 4.1187, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.0619515148100425e-05, + "loss": 4.0912, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.0611129200589905e-05, + "loss": 4.107, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.060274325307938e-05, + "loss": 4.1065, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.059435730556886e-05, + "loss": 4.0915, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.058597135805834e-05, + "loss": 4.1015, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.0577601789351554e-05, + "loss": 4.1046, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.056921584184103e-05, + "loss": 4.1074, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.056082989433051e-05, + "loss": 4.1134, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.055244394681999e-05, + "loss": 4.092, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.0544057999309474e-05, + "loss": 4.0967, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.0535672051798954e-05, + "loss": 4.1035, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.052730248309216e-05, + "loss": 4.1079, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.051891653558164e-05, + "loss": 4.1065, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.051053058807112e-05, + "loss": 4.1077, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.05021446405606e-05, + "loss": 4.1097, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049375869305008e-05, + "loss": 4.1056, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.048538912434329e-05, + "loss": 4.1014, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.047700317683277e-05, + "loss": 4.0945, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.046861722932225e-05, + "loss": 4.1092, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.046023128181173e-05, + "loss": 4.1111, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.045186171310494e-05, + "loss": 4.1004, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.044347576559443e-05, + "loss": 4.0931, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.043508981808391e-05, + "loss": 4.0922, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.042670387057339e-05, + "loss": 4.1042, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.0418334301866596e-05, + "loss": 4.1159, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.0409948354356076e-05, + "loss": 4.0967, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.0401562406845556e-05, + "loss": 4.0978, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.0393176459335036e-05, + "loss": 4.0943, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.0384790511824516e-05, + "loss": 4.0994, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.0376420943117725e-05, + "loss": 4.0866, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.0368034995607205e-05, + "loss": 4.0966, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.0359649048096685e-05, + "loss": 4.0843, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.0351263100586165e-05, + "loss": 4.1022, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.0342877153075645e-05, + "loss": 4.0969, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.033450758436886e-05, + "loss": 4.0991, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.032613801566207e-05, + "loss": 4.0958, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.031775206815155e-05, + "loss": 4.0959, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.030936612064103e-05, + "loss": 4.096, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.030098017313051e-05, + "loss": 4.0982, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.029259422561999e-05, + "loss": 4.1015, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.028420827810947e-05, + "loss": 4.1052, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.027582233059895e-05, + "loss": 4.0933, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.026743638308843e-05, + "loss": 4.0988, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.025905043557791e-05, + "loss": 4.0914, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.025066448806738e-05, + "loss": 4.0965, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.02422949193606e-05, + "loss": 4.0962, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.0233925350653815e-05, + "loss": 4.0938, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.0225539403143295e-05, + "loss": 4.0854, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.0217153455632775e-05, + "loss": 4.0944, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.0208767508122255e-05, + "loss": 4.0975, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.0200381560611735e-05, + "loss": 4.0933, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.0191995613101214e-05, + "loss": 4.0751, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.018360966559069e-05, + "loss": 4.1002, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.017522371808017e-05, + "loss": 4.0879, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.016683777056965e-05, + "loss": 4.1027, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.015845182305913e-05, + "loss": 4.0949, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.015006587554861e-05, + "loss": 4.1001, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.0141696306841817e-05, + "loss": 4.0851, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.0133310359331297e-05, + "loss": 4.1004, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.012492441182078e-05, + "loss": 4.1021, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011653846431026e-05, + "loss": 4.1, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.010815251679974e-05, + "loss": 4.1003, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.009976656928922e-05, + "loss": 4.1003, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.009139700058243e-05, + "loss": 4.0935, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008301105307191e-05, + "loss": 4.1013, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.007462510556139e-05, + "loss": 4.082, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006623915805087e-05, + "loss": 4.0977, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005785321054035e-05, + "loss": 4.0855, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.004946726302983e-05, + "loss": 4.0945, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.004108131551931e-05, + "loss": 4.0833, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.003269536800879e-05, + "loss": 4.0861, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.0024325799302e-05, + "loss": 4.0918, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.001595623059522e-05, + "loss": 4.0882, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.00075702830847e-05, + "loss": 4.1041, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 4.105152130126953, + "eval_runtime": 293.6825, + "eval_samples_per_second": 1299.332, + "eval_steps_per_second": 40.605, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.999918433557418e-05, + "loss": 4.0824, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999079838806366e-05, + "loss": 4.0832, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998241244055314e-05, + "loss": 4.0871, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997402649304262e-05, + "loss": 4.0911, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.9965656924335826e-05, + "loss": 4.0923, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.9957270976825306e-05, + "loss": 4.0837, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.9948885029314786e-05, + "loss": 4.0881, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.9940499081804266e-05, + "loss": 4.0827, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.9932113134293746e-05, + "loss": 4.0853, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992372718678322e-05, + "loss": 4.1004, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.9915341239272706e-05, + "loss": 4.0871, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.9906955291762185e-05, + "loss": 4.0886, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.9898569344251665e-05, + "loss": 4.0862, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.9890183396741145e-05, + "loss": 4.077, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.9881797449230625e-05, + "loss": 4.0883, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.9873411501720105e-05, + "loss": 4.0752, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.9865025554209585e-05, + "loss": 4.0842, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.9856639606699065e-05, + "loss": 4.0897, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.9848253659188545e-05, + "loss": 4.0772, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.9839867711678025e-05, + "loss": 4.1002, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.9831481764167505e-05, + "loss": 4.0988, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.9823095816656985e-05, + "loss": 4.0851, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.981470986914646e-05, + "loss": 4.086, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.980632392163594e-05, + "loss": 4.0975, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.9797954352929154e-05, + "loss": 4.0849, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.9789568405418634e-05, + "loss": 4.0859, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.9781182457908114e-05, + "loss": 4.0853, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.9772796510397594e-05, + "loss": 4.0829, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.976444332049454e-05, + "loss": 4.0831, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.975605737298402e-05, + "loss": 4.0851, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.97476714254735e-05, + "loss": 4.0888, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.973930185676671e-05, + "loss": 4.0925, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973091590925619e-05, + "loss": 4.0912, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972252996174567e-05, + "loss": 4.0859, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.971414401423515e-05, + "loss": 4.0786, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.970577444552836e-05, + "loss": 4.091, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.969738849801784e-05, + "loss": 4.0819, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.9689002550507324e-05, + "loss": 4.0727, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.9680616602996804e-05, + "loss": 4.0753, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.9672230655486283e-05, + "loss": 4.0719, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.9663844707975763e-05, + "loss": 4.0797, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.9655458760465237e-05, + "loss": 4.0849, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.9647072812954717e-05, + "loss": 4.0828, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.9638686865444197e-05, + "loss": 4.0821, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.9630300917933676e-05, + "loss": 4.0818, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.9621914970423156e-05, + "loss": 4.0849, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.9613529022912636e-05, + "loss": 4.0831, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.9605159454205845e-05, + "loss": 4.0846, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.9596773506695325e-05, + "loss": 4.0559, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.9588387559184805e-05, + "loss": 4.0934, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.958000161167429e-05, + "loss": 4.0723, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.957161566416377e-05, + "loss": 4.09, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956322971665325e-05, + "loss": 4.0728, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.955486014794646e-05, + "loss": 4.077, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.954649057923967e-05, + "loss": 4.0724, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953810463172915e-05, + "loss": 4.0807, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.952971868421863e-05, + "loss": 4.0715, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952133273670811e-05, + "loss": 4.0732, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.951294678919759e-05, + "loss": 4.0861, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950456084168707e-05, + "loss": 4.0723, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949617489417655e-05, + "loss": 4.0619, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948778894666603e-05, + "loss": 4.0879, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.947940299915551e-05, + "loss": 4.0618, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.947101705164499e-05, + "loss": 4.0596, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.9462647482938206e-05, + "loss": 4.0778, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.9454261535427686e-05, + "loss": 4.077, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.9445875587917166e-05, + "loss": 4.0705, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.9437489640406646e-05, + "loss": 4.0766, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.9429103692896126e-05, + "loss": 4.0556, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.94207177453856e-05, + "loss": 4.0689, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.9412348176678815e-05, + "loss": 4.079, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.9403962229168295e-05, + "loss": 4.0737, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.939557628165777e-05, + "loss": 4.0868, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.9387206712950984e-05, + "loss": 4.0762, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.9378820765440464e-05, + "loss": 4.0886, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.9370434817929943e-05, + "loss": 4.0644, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.9362048870419423e-05, + "loss": 4.0767, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.9353662922908903e-05, + "loss": 4.0723, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.934527697539838e-05, + "loss": 4.0661, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.933689102788786e-05, + "loss": 4.0734, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.932850508037734e-05, + "loss": 4.0779, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.932011913286682e-05, + "loss": 4.0773, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.931174956416003e-05, + "loss": 4.0866, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.930336361664951e-05, + "loss": 4.0609, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.929497766913899e-05, + "loss": 4.0657, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.928659172162847e-05, + "loss": 4.0803, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927820577411795e-05, + "loss": 4.0779, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.926981982660743e-05, + "loss": 4.0764, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926143387909691e-05, + "loss": 4.0817, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925304793158639e-05, + "loss": 4.0767, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924469474168334e-05, + "loss": 4.079, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923630879417282e-05, + "loss": 4.0722, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.92279228466623e-05, + "loss": 4.0652, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.921953689915178e-05, + "loss": 4.0831, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.921115095164126e-05, + "loss": 4.075, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.920276500413074e-05, + "loss": 4.075, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.9194395435423946e-05, + "loss": 4.0684, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.9186009487913426e-05, + "loss": 4.0616, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.9177623540402906e-05, + "loss": 4.0733, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.9169237592892386e-05, + "loss": 4.0835, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.91608680241856e-05, + "loss": 4.0696, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.915248207667508e-05, + "loss": 4.0692, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.914409612916456e-05, + "loss": 4.0655, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.913572656045777e-05, + "loss": 4.0661, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912734061294725e-05, + "loss": 4.0648, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.911895466543673e-05, + "loss": 4.0624, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.911056871792621e-05, + "loss": 4.0587, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910218277041569e-05, + "loss": 4.075, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.909379682290517e-05, + "loss": 4.0695, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.908541087539465e-05, + "loss": 4.0684, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907702492788413e-05, + "loss": 4.0608, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.9068638980373604e-05, + "loss": 4.0706, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.906026941166682e-05, + "loss": 4.0711, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.90518834641563e-05, + "loss": 4.0696, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.9043497516645786e-05, + "loss": 4.0743, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.903511156913526e-05, + "loss": 4.0782, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.902672562162474e-05, + "loss": 4.0652, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.9018356052917955e-05, + "loss": 4.0739, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.900997010540743e-05, + "loss": 4.0585, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.900158415789691e-05, + "loss": 4.0694, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.899319821038639e-05, + "loss": 4.0677, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.898481226287587e-05, + "loss": 4.0639, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.897642631536535e-05, + "loss": 4.0608, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896804036785483e-05, + "loss": 4.0662, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.895965442034431e-05, + "loss": 4.0691, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.8951284851637524e-05, + "loss": 4.0669, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.8942898904127004e-05, + "loss": 4.0509, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.8934512956616484e-05, + "loss": 4.0684, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.8926127009105964e-05, + "loss": 4.0611, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.891775744039917e-05, + "loss": 4.0775, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.890937149288865e-05, + "loss": 4.0696, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890100192418186e-05, + "loss": 4.0678, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889261597667134e-05, + "loss": 4.0583, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888423002916082e-05, + "loss": 4.0733, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.88758440816503e-05, + "loss": 4.075, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886745813413978e-05, + "loss": 4.0735, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885908856543299e-05, + "loss": 4.0729, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885070261792248e-05, + "loss": 4.0717, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.884231667041196e-05, + "loss": 4.0659, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.8833947101705167e-05, + "loss": 4.0736, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.8825561154194647e-05, + "loss": 4.0548, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.8817175206684127e-05, + "loss": 4.0712, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.8808789259173606e-05, + "loss": 4.0609, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.8800403311663086e-05, + "loss": 4.0646, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.8792017364152566e-05, + "loss": 4.056, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.8783631416642046e-05, + "loss": 4.0578, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.8775245469131526e-05, + "loss": 4.0657, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.8766859521621006e-05, + "loss": 4.0637, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.8758473574110486e-05, + "loss": 4.0763, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 4.085753440856934, + "eval_runtime": 297.21, + "eval_samples_per_second": 1283.91, + "eval_steps_per_second": 40.123, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.8750087626599966e-05, + "loss": 4.0511, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.8741718057893175e-05, + "loss": 4.0575, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.8733332110382655e-05, + "loss": 4.0564, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.872494616287214e-05, + "loss": 4.0693, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.8716560215361615e-05, + "loss": 4.0664, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.8708174267851095e-05, + "loss": 4.0558, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.8699788320340575e-05, + "loss": 4.062, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.8691402372830055e-05, + "loss": 4.0557, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.8683016425319535e-05, + "loss": 4.0586, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.8674646856612744e-05, + "loss": 4.0751, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.8666260909102224e-05, + "loss": 4.061, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.865789134039544e-05, + "loss": 4.0592, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.864950539288491e-05, + "loss": 4.0689, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.864111944537439e-05, + "loss": 4.0457, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.863273349786388e-05, + "loss": 4.0597, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.862434755035336e-05, + "loss": 4.0499, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.861597798164657e-05, + "loss": 4.0596, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.860759203413605e-05, + "loss": 4.0612, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.859920608662553e-05, + "loss": 4.0496, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.859082013911501e-05, + "loss": 4.0728, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.858243419160449e-05, + "loss": 4.0738, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.857404824409397e-05, + "loss": 4.0629, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.856566229658345e-05, + "loss": 4.0638, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.855727634907293e-05, + "loss": 4.0654, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.854890678036614e-05, + "loss": 4.0609, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.854052083285562e-05, + "loss": 4.0555, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.85321348853451e-05, + "loss": 4.0624, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852374893783458e-05, + "loss": 4.0574, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.8515362990324064e-05, + "loss": 4.0545, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.850699342161727e-05, + "loss": 4.0599, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.849860747410675e-05, + "loss": 4.0614, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.849023790539996e-05, + "loss": 4.0704, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.848185195788944e-05, + "loss": 4.0644, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.847346601037892e-05, + "loss": 4.0636, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.84650800628684e-05, + "loss": 4.054, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.845671049416161e-05, + "loss": 4.0595, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.844832454665109e-05, + "loss": 4.0619, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.843993859914057e-05, + "loss": 4.0509, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.843155265163005e-05, + "loss": 4.0487, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.842316670411953e-05, + "loss": 4.0475, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.841478075660902e-05, + "loss": 4.0551, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.84063948090985e-05, + "loss": 4.0562, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.839800886158798e-05, + "loss": 4.0575, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.838962291407745e-05, + "loss": 4.0575, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.838123696656693e-05, + "loss": 4.0576, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.837285101905641e-05, + "loss": 4.0554, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.836448145034963e-05, + "loss": 4.057, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.83560955028391e-05, + "loss": 4.0648, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.834770955532858e-05, + "loss": 4.0285, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.833932360781806e-05, + "loss": 4.0624, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.833093766030754e-05, + "loss": 4.0512, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.8322568091600756e-05, + "loss": 4.0658, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.8314182144090236e-05, + "loss": 4.0492, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.8305796196579716e-05, + "loss": 4.0512, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.8297410249069195e-05, + "loss": 4.0435, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.8289024301558675e-05, + "loss": 4.0561, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.8280654732851885e-05, + "loss": 4.0527, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.8272268785341364e-05, + "loss": 4.0449, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.8263899216634574e-05, + "loss": 4.0617, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.8255513269124054e-05, + "loss": 4.0505, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.8247127321613534e-05, + "loss": 4.0339, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.8238741374103013e-05, + "loss": 4.0627, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.8230355426592493e-05, + "loss": 4.0417, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822196947908197e-05, + "loss": 4.0344, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.821359991037519e-05, + "loss": 4.0519, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.820521396286467e-05, + "loss": 4.0514, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.819682801535415e-05, + "loss": 4.041, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.818844206784363e-05, + "loss": 4.0573, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.818005612033311e-05, + "loss": 4.0338, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.817167017282259e-05, + "loss": 4.0402, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.816328422531207e-05, + "loss": 4.0546, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.815489827780155e-05, + "loss": 4.0477, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.814652870909476e-05, + "loss": 4.0624, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.813815914038797e-05, + "loss": 4.05, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.812977319287745e-05, + "loss": 4.063, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812138724536693e-05, + "loss": 4.0412, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.811300129785641e-05, + "loss": 4.0566, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810463172914962e-05, + "loss": 4.043, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.80962457816391e-05, + "loss": 4.0469, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808785983412858e-05, + "loss": 4.0455, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.807947388661806e-05, + "loss": 4.0523, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.807108793910754e-05, + "loss": 4.0523, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.806270199159702e-05, + "loss": 4.0645, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.80543160440865e-05, + "loss": 4.0354, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.804593009657598e-05, + "loss": 4.0431, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.803754414906546e-05, + "loss": 4.0537, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.802917458035867e-05, + "loss": 4.0546, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.802078863284815e-05, + "loss": 4.0493, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.801240268533763e-05, + "loss": 4.0601, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.800401673782711e-05, + "loss": 4.0501, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.799563079031659e-05, + "loss": 4.0566, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.798724484280607e-05, + "loss": 4.0521, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.797885889529555e-05, + "loss": 4.0403, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.797048932658876e-05, + "loss": 4.0555, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.7962119757881976e-05, + "loss": 4.0556, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.7953733810371456e-05, + "loss": 4.0505, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.7945347862860936e-05, + "loss": 4.0467, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.793696191535041e-05, + "loss": 4.0348, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.792857596783989e-05, + "loss": 4.0505, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.792019002032937e-05, + "loss": 4.0601, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.791180407281885e-05, + "loss": 4.0465, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.790341812530833e-05, + "loss": 4.0455, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.789503217779781e-05, + "loss": 4.0412, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.7886646230287296e-05, + "loss": 4.0411, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.7878260282776776e-05, + "loss": 4.0448, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.7869874335266256e-05, + "loss": 4.0385, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.7861488387755736e-05, + "loss": 4.0335, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.7853118819048945e-05, + "loss": 4.0517, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.7844732871538425e-05, + "loss": 4.0499, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.7836346924027905e-05, + "loss": 4.0403, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.7827960976517385e-05, + "loss": 4.0417, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.7819591407810594e-05, + "loss": 4.0443, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.78112218391038e-05, + "loss": 4.0507, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780283589159328e-05, + "loss": 4.0435, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.779444994408276e-05, + "loss": 4.055, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.778606399657225e-05, + "loss": 4.0526, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.777767804906173e-05, + "loss": 4.0398, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.776930848035494e-05, + "loss": 4.049, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.776092253284442e-05, + "loss": 4.038, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.77525365853339e-05, + "loss": 4.0446, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.774415063782338e-05, + "loss": 4.0479, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.773576469031286e-05, + "loss": 4.0395, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.772737874280234e-05, + "loss": 4.0356, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.771899279529182e-05, + "loss": 4.0451, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.77106068477813e-05, + "loss": 4.0462, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.770222090027077e-05, + "loss": 4.0457, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.7693867710367717e-05, + "loss": 4.0272, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.76854817628572e-05, + "loss": 4.042, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.767709581534668e-05, + "loss": 4.0372, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.766870986783616e-05, + "loss": 4.0527, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.766032392032564e-05, + "loss": 4.047, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.765193797281512e-05, + "loss": 4.0458, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.7643552025304596e-05, + "loss": 4.0324, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.7635166077794076e-05, + "loss": 4.0555, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.762681288789102e-05, + "loss": 4.0454, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.76184269403805e-05, + "loss": 4.0541, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.761004099286998e-05, + "loss": 4.0466, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.760165504535946e-05, + "loss": 4.049, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.759328547665267e-05, + "loss": 4.0426, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.758489952914215e-05, + "loss": 4.0548, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.757651358163164e-05, + "loss": 4.0279, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.756812763412112e-05, + "loss": 4.0511, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.75597416866106e-05, + "loss": 4.0375, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.755135573910007e-05, + "loss": 4.0407, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.754296979158955e-05, + "loss": 4.0338, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.753458384407903e-05, + "loss": 4.0374, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.752621427537224e-05, + "loss": 4.0417, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.751782832786172e-05, + "loss": 4.0446, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.75094423803512e-05, + "loss": 4.0498, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 4.069965839385986, + "eval_runtime": 296.5058, + "eval_samples_per_second": 1286.96, + "eval_steps_per_second": 40.218, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.750105643284068e-05, + "loss": 4.0297, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.749267048533016e-05, + "loss": 4.0363, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.748428453781964e-05, + "loss": 4.0329, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.747589859030912e-05, + "loss": 4.0476, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.7467512642798605e-05, + "loss": 4.0474, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.7459126695288085e-05, + "loss": 4.0326, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.7450740747777565e-05, + "loss": 4.037, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.7442354800267045e-05, + "loss": 4.0343, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.7433968852756525e-05, + "loss": 4.0388, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.7425582905246005e-05, + "loss": 4.0499, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.7417196957735485e-05, + "loss": 4.0384, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.740881101022496e-05, + "loss": 4.0391, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.740042506271444e-05, + "loss": 4.0467, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.739203911520392e-05, + "loss": 4.0256, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.73836531676934e-05, + "loss": 4.0347, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.737526722018288e-05, + "loss": 4.0262, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.736688127267236e-05, + "loss": 4.0382, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.735849532516184e-05, + "loss": 4.0419, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.735010937765132e-05, + "loss": 4.0272, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.7341739808944534e-05, + "loss": 4.0474, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.7333353861434014e-05, + "loss": 4.0514, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.7324967913923494e-05, + "loss": 4.0396, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.7316581966412974e-05, + "loss": 4.0435, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.7308196018902454e-05, + "loss": 4.0412, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.7299810071391934e-05, + "loss": 4.044, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.7291424123881414e-05, + "loss": 4.0326, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.7283038176370894e-05, + "loss": 4.0358, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.72746686076641e-05, + "loss": 4.0384, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.726628266015358e-05, + "loss": 4.0324, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.725789671264306e-05, + "loss": 4.0373, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.724951076513254e-05, + "loss": 4.0406, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.724112481762202e-05, + "loss": 4.0409, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.72327388701115e-05, + "loss": 4.0469, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722435292260098e-05, + "loss": 4.0403, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.72159833538942e-05, + "loss": 4.0328, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.720761378518741e-05, + "loss": 4.0374, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.719922783767689e-05, + "loss": 4.0409, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.719084189016637e-05, + "loss": 4.0257, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.718245594265585e-05, + "loss": 4.0276, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.717406999514532e-05, + "loss": 4.0309, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.71656840476348e-05, + "loss": 4.029, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.715729810012428e-05, + "loss": 4.0381, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.714891215261376e-05, + "loss": 4.033, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.714052620510324e-05, + "loss": 4.0388, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.713214025759272e-05, + "loss": 4.0302, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.7123770688885936e-05, + "loss": 4.0388, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.7115384741375416e-05, + "loss": 4.034, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.7106998793864896e-05, + "loss": 4.0434, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.7098612846354376e-05, + "loss": 4.0102, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.7090243277647585e-05, + "loss": 4.0375, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.7081857330137065e-05, + "loss": 4.0315, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.7073471382626545e-05, + "loss": 4.0435, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.7065085435116025e-05, + "loss": 4.0279, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.7056715866409234e-05, + "loss": 4.0294, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.7048329918898714e-05, + "loss": 4.0244, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.7039943971388194e-05, + "loss": 4.0327, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.7031558023877674e-05, + "loss": 4.0377, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.702317207636716e-05, + "loss": 4.0175, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.701478612885664e-05, + "loss": 4.0447, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.700640018134612e-05, + "loss": 4.0288, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.69980142338356e-05, + "loss": 4.0092, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.698964466512881e-05, + "loss": 4.041, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.698125871761829e-05, + "loss": 4.0216, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.697287277010777e-05, + "loss": 4.0112, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.696448682259725e-05, + "loss": 4.0329, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.695610087508673e-05, + "loss": 4.0306, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.694773130637994e-05, + "loss": 4.0166, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.693934535886942e-05, + "loss": 4.0391, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.69309594113589e-05, + "loss": 4.0103, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.692257346384838e-05, + "loss": 4.019, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.691418751633786e-05, + "loss": 4.0323, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.690580156882734e-05, + "loss": 4.0299, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689741562131682e-05, + "loss": 4.0392, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.68890296738063e-05, + "loss": 4.0311, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.688066010509951e-05, + "loss": 4.0422, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.687229053639272e-05, + "loss": 4.0217, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.68639045888822e-05, + "loss": 4.0363, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.6855518641371676e-05, + "loss": 4.0191, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.6847132693861156e-05, + "loss": 4.0248, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683876312515437e-05, + "loss": 4.0269, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.683037717764385e-05, + "loss": 4.0251, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.682199123013333e-05, + "loss": 4.0361, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.681360528262281e-05, + "loss": 4.0418, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.680521933511229e-05, + "loss": 4.0216, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.679683338760177e-05, + "loss": 4.0205, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.678844744009125e-05, + "loss": 4.0288, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.678006149258073e-05, + "loss": 4.0361, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.677169192387394e-05, + "loss": 4.0267, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.676330597636342e-05, + "loss": 4.0369, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.67549200288529e-05, + "loss": 4.0336, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.674653408134238e-05, + "loss": 4.0341, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.673814813383186e-05, + "loss": 4.028, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.672976218632134e-05, + "loss": 4.0218, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.672139261761455e-05, + "loss": 4.0334, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.6713006670104037e-05, + "loss": 4.0319, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.6704620722593516e-05, + "loss": 4.0327, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.6696251153886726e-05, + "loss": 4.0236, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.6687865206376206e-05, + "loss": 4.0137, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.6679479258865685e-05, + "loss": 4.0286, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.6671093311355165e-05, + "loss": 4.0397, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.6662707363844645e-05, + "loss": 4.0276, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.6654321416334125e-05, + "loss": 4.0239, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.6645935468823605e-05, + "loss": 4.0221, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.6637549521313085e-05, + "loss": 4.0188, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.6629163573802565e-05, + "loss": 4.0256, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.662077762629204e-05, + "loss": 4.0132, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.6612408057585254e-05, + "loss": 4.0169, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.6604022110074734e-05, + "loss": 4.027, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.6595636162564214e-05, + "loss": 4.0291, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.6587250215053694e-05, + "loss": 4.0235, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.6578864267543174e-05, + "loss": 4.0176, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.6570478320032654e-05, + "loss": 4.0206, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.656210875132587e-05, + "loss": 4.0317, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655372280381534e-05, + "loss": 4.0222, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.654533685630482e-05, + "loss": 4.0362, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.65369509087943e-05, + "loss": 4.0281, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652856496128378e-05, + "loss": 4.0228, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652017901377326e-05, + "loss": 4.0249, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.651180944506647e-05, + "loss": 4.0215, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.650342349755595e-05, + "loss": 4.024, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.649503755004544e-05, + "loss": 4.031, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.648665160253492e-05, + "loss": 4.0156, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.64782656550244e-05, + "loss": 4.0158, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.646987970751388e-05, + "loss": 4.0245, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.646149376000336e-05, + "loss": 4.0263, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.645312419129657e-05, + "loss": 4.0216, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.644473824378605e-05, + "loss": 4.0104, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.643635229627553e-05, + "loss": 4.0236, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.642796634876501e-05, + "loss": 4.0138, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.641958040125449e-05, + "loss": 4.0378, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.6411210832547697e-05, + "loss": 4.0239, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.6402824885037176e-05, + "loss": 4.0257, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.6394438937526656e-05, + "loss": 4.0129, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.6386052990016136e-05, + "loss": 4.0328, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.637766704250562e-05, + "loss": 4.0257, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.63692810949951e-05, + "loss": 4.0341, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636089514748458e-05, + "loss": 4.033, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.635252557877779e-05, + "loss": 4.0264, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.6344156010071e-05, + "loss": 4.0217, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.633577006256048e-05, + "loss": 4.0371, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.632738411504996e-05, + "loss": 4.0087, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.631899816753944e-05, + "loss": 4.0292, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.631061222002892e-05, + "loss": 4.0195, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.63022262725184e-05, + "loss": 4.0207, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.6293840325007874e-05, + "loss": 4.0144, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.628545437749736e-05, + "loss": 4.0155, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.627706842998684e-05, + "loss": 4.0166, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.626868248247632e-05, + "loss": 4.0274, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.626031291376953e-05, + "loss": 4.0274, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 4.05682373046875, + "eval_runtime": 298.482, + "eval_samples_per_second": 1278.439, + "eval_steps_per_second": 39.952, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.625192696625901e-05, + "loss": 4.0153, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.624354101874849e-05, + "loss": 4.0134, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.623515507123797e-05, + "loss": 4.0106, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.622676912372745e-05, + "loss": 4.0303, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.621838317621693e-05, + "loss": 4.0253, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.620999722870641e-05, + "loss": 4.0136, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.620161128119589e-05, + "loss": 4.0169, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.619322533368537e-05, + "loss": 4.0164, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.618485576497858e-05, + "loss": 4.0174, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617646981746806e-05, + "loss": 4.0257, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.616808386995754e-05, + "loss": 4.0242, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.6159714301250754e-05, + "loss": 4.0167, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.6151328353740234e-05, + "loss": 4.0284, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.6142942406229714e-05, + "loss": 4.0051, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.6134556458719194e-05, + "loss": 4.0173, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.6126170511208674e-05, + "loss": 4.0046, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.6117784563698154e-05, + "loss": 4.0206, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.6109398616187634e-05, + "loss": 4.0259, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.610102904748084e-05, + "loss": 4.0015, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.609264309997032e-05, + "loss": 4.0275, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.60842571524598e-05, + "loss": 4.0328, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.607587120494928e-05, + "loss": 4.0207, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.606750163624249e-05, + "loss": 4.0252, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.605911568873198e-05, + "loss": 4.0226, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.605072974122146e-05, + "loss": 4.0225, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.604234379371094e-05, + "loss": 4.0145, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.603395784620042e-05, + "loss": 4.0144, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.602558827749363e-05, + "loss": 4.0189, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.601720232998311e-05, + "loss": 4.0147, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.600881638247259e-05, + "loss": 4.0174, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.60004468137658e-05, + "loss": 4.0218, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.599206086625528e-05, + "loss": 4.0248, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598367491874476e-05, + "loss": 4.0191, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.597528897123424e-05, + "loss": 4.0269, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596690302372372e-05, + "loss": 4.0091, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595853345501693e-05, + "loss": 4.0212, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595014750750641e-05, + "loss": 4.024, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.594176155999589e-05, + "loss": 4.0009, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.5933375612485366e-05, + "loss": 4.0128, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.5924989664974846e-05, + "loss": 4.0113, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.591662009626806e-05, + "loss": 4.0086, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.5908234148757535e-05, + "loss": 4.017, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.5899848201247015e-05, + "loss": 4.0148, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.5891462253736495e-05, + "loss": 4.0165, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.5883076306225975e-05, + "loss": 4.0154, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.5874690358715455e-05, + "loss": 4.0174, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.5866304411204935e-05, + "loss": 4.0125, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.5857918463694414e-05, + "loss": 4.0231, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.58495325161839e-05, + "loss": 3.9955, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.584114656867338e-05, + "loss": 4.0183, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.583276062116286e-05, + "loss": 4.0084, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.582439105245607e-05, + "loss": 4.0258, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.581600510494555e-05, + "loss": 4.0096, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.580761915743503e-05, + "loss": 4.0065, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.579924958872824e-05, + "loss": 4.0082, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.579086364121772e-05, + "loss": 4.0137, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.57824776937072e-05, + "loss": 4.0186, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.577409174619668e-05, + "loss": 3.9975, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.576570579868616e-05, + "loss": 4.0244, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.575731985117564e-05, + "loss": 4.014, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.574893390366512e-05, + "loss": 3.9886, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.57405479561546e-05, + "loss": 4.0211, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.573216200864408e-05, + "loss": 4.0021, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.572377606113356e-05, + "loss": 3.9962, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.571539011362304e-05, + "loss": 4.0113, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.570700416611252e-05, + "loss": 4.0118, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.5698618218602e-05, + "loss": 4.0023, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.569024864989521e-05, + "loss": 4.02, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.5681879081188424e-05, + "loss": 3.9886, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.56734931336779e-05, + "loss": 4.0001, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.566510718616738e-05, + "loss": 4.0156, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.565672123865686e-05, + "loss": 4.0144, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.564833529114634e-05, + "loss": 4.0161, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.5639949343635823e-05, + "loss": 4.0138, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.5631563396125303e-05, + "loss": 4.0216, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.562319382741851e-05, + "loss": 4.0048, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.561480787990799e-05, + "loss": 4.0188, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.560642193239747e-05, + "loss": 4.0026, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.559803598488695e-05, + "loss": 4.0037, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.558965003737643e-05, + "loss": 4.0067, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.558128046866964e-05, + "loss": 4.0107, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.557289452115912e-05, + "loss": 4.0169, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.55645085736486e-05, + "loss": 4.023, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.555612262613808e-05, + "loss": 4.0053, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.554773667862756e-05, + "loss": 3.9991, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.553935073111704e-05, + "loss": 4.0103, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.553096478360652e-05, + "loss": 4.0189, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.5522578836096e-05, + "loss": 4.0057, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.551420926738922e-05, + "loss": 4.0189, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.5505839698682426e-05, + "loss": 4.0155, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.5497453751171906e-05, + "loss": 4.0154, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.5489067803661386e-05, + "loss": 4.0098, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.5480681856150866e-05, + "loss": 4.002, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.5472295908640346e-05, + "loss": 4.0175, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.5463909961129826e-05, + "loss": 4.0143, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.5455524013619306e-05, + "loss": 4.0117, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.5447138066108786e-05, + "loss": 4.0088, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.5438768497401995e-05, + "loss": 3.9943, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.5430382549891475e-05, + "loss": 4.0101, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.542201298118469e-05, + "loss": 4.0217, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.541362703367417e-05, + "loss": 4.0097, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.540524108616365e-05, + "loss": 4.0067, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.539685513865313e-05, + "loss": 4.0044, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.538846919114261e-05, + "loss": 4.0047, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.538009962243582e-05, + "loss": 4.006, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.53717136749253e-05, + "loss": 4.0, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.536332772741478e-05, + "loss": 3.9999, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.535494177990426e-05, + "loss": 4.008, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.534655583239373e-05, + "loss": 4.0103, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.533818626368695e-05, + "loss": 4.0078, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.532980031617643e-05, + "loss": 4.0044, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.532141436866591e-05, + "loss": 4.0002, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.531302842115539e-05, + "loss": 4.0133, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.530464247364487e-05, + "loss": 4.005, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.5296272904938084e-05, + "loss": 4.0168, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.528788695742756e-05, + "loss": 4.0087, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.527950100991704e-05, + "loss": 4.006, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527111506240652e-05, + "loss": 4.0094, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.526274549369973e-05, + "loss": 4.0042, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.5254359546189206e-05, + "loss": 4.0061, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.5245973598678686e-05, + "loss": 4.013, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.5237587651168166e-05, + "loss": 4.0003, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.5229201703657646e-05, + "loss": 3.9992, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.522081575614713e-05, + "loss": 4.0065, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.521242980863661e-05, + "loss": 4.007, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.520404386112609e-05, + "loss": 4.0045, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.51956742924193e-05, + "loss": 3.9954, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.518728834490878e-05, + "loss": 4.0024, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.517890239739826e-05, + "loss": 3.9992, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.517051644988774e-05, + "loss": 4.0189, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.516214688118095e-05, + "loss": 4.0035, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.515377731247416e-05, + "loss": 4.0123, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.514539136496364e-05, + "loss": 3.9979, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.513700541745312e-05, + "loss": 4.0133, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.51286194699426e-05, + "loss": 4.008, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.5120249901235816e-05, + "loss": 4.0143, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.5111863953725296e-05, + "loss": 4.0156, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.5103478006214776e-05, + "loss": 4.0083, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.5095092058704256e-05, + "loss": 4.0086, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.5086706111193736e-05, + "loss": 4.0156, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.5078320163683216e-05, + "loss": 3.9974, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.5069934216172696e-05, + "loss": 4.0105, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.5061548268662175e-05, + "loss": 4.0035, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.5053178699955385e-05, + "loss": 4.0032, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.5044792752444865e-05, + "loss": 3.9954, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.5036406804934344e-05, + "loss": 4.003, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.5028020857423824e-05, + "loss": 3.9992, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.501965128871704e-05, + "loss": 4.0023, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.501128172001025e-05, + "loss": 4.0103, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 4.0456647872924805, + "eval_runtime": 298.5671, + "eval_samples_per_second": 1278.074, + "eval_steps_per_second": 39.941, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.500289577249973e-05, + "loss": 4.0105, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.499450982498921e-05, + "loss": 3.9929, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.498612387747869e-05, + "loss": 3.9965, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497773792996817e-05, + "loss": 4.0092, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.496935198245765e-05, + "loss": 4.0045, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.496096603494713e-05, + "loss": 4.0014, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.495258008743661e-05, + "loss": 4.0062, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.494419413992609e-05, + "loss": 3.9988, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.493580819241557e-05, + "loss": 3.9978, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.492742224490504e-05, + "loss": 4.0051, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.491903629739452e-05, + "loss": 4.0119, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.4910650349884e-05, + "loss": 3.9987, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.490226440237349e-05, + "loss": 4.0128, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.489387845486297e-05, + "loss": 3.9847, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.488549250735245e-05, + "loss": 4.0005, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.487710655984193e-05, + "loss": 3.9886, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.486872061233141e-05, + "loss": 4.0037, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.486033466482089e-05, + "loss": 4.0087, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.485194871731037e-05, + "loss": 3.9853, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.484356276979985e-05, + "loss": 4.008, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.483519320109306e-05, + "loss": 4.0177, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482682363238627e-05, + "loss": 4.0023, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.481843768487575e-05, + "loss": 4.0075, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.4810051737365227e-05, + "loss": 4.0068, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.4801665789854707e-05, + "loss": 4.0074, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.479329622114792e-05, + "loss": 3.9985, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.47849102736374e-05, + "loss": 3.9954, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.477652432612688e-05, + "loss": 4.0033, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.476813837861636e-05, + "loss": 3.9981, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.475976880990957e-05, + "loss": 4.0, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.475138286239905e-05, + "loss": 4.0083, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.474299691488853e-05, + "loss": 4.0066, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.473461096737801e-05, + "loss": 4.0008, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.472622501986749e-05, + "loss": 4.0122, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.471783907235697e-05, + "loss": 3.9964, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.470946950365018e-05, + "loss": 4.0046, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.470108355613966e-05, + "loss": 4.0004, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469269760862914e-05, + "loss": 3.9866, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468431166111863e-05, + "loss": 3.9962, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467592571360811e-05, + "loss": 3.996, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466753976609758e-05, + "loss": 3.9912, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.465915381858706e-05, + "loss": 4.0021, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465076787107654e-05, + "loss": 4.0012, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.4642398302369756e-05, + "loss": 3.9997, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.463401235485923e-05, + "loss": 3.9987, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.462562640734871e-05, + "loss": 4.0041, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.461724045983819e-05, + "loss": 3.993, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.460885451232767e-05, + "loss": 4.0068, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.4600501322424614e-05, + "loss": 3.9827, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.4592115374914094e-05, + "loss": 3.9993, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.458372942740358e-05, + "loss": 3.9943, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.4575343479893054e-05, + "loss": 4.0112, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.4566957532382534e-05, + "loss": 3.9949, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.4558571584872014e-05, + "loss": 3.9887, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.4550185637361494e-05, + "loss": 3.9945, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.4541799689850974e-05, + "loss": 3.9959, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.453343012114418e-05, + "loss": 4.0063, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.452504417363366e-05, + "loss": 3.9772, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.451667460492687e-05, + "loss": 4.0106, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.450828865741635e-05, + "loss": 3.9985, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.449990270990583e-05, + "loss": 3.9736, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449153314119905e-05, + "loss": 4.004, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.448314719368853e-05, + "loss": 3.9861, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.447476124617801e-05, + "loss": 3.9788, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.446637529866749e-05, + "loss": 3.9917, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.445798935115697e-05, + "loss": 3.9974, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.444960340364645e-05, + "loss": 3.9901, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.444121745613593e-05, + "loss": 3.9962, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.443283150862541e-05, + "loss": 3.9783, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442444556111489e-05, + "loss": 3.9801, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.441605961360437e-05, + "loss": 3.9983, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.440767366609385e-05, + "loss": 4.0016, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.439928771858333e-05, + "loss": 4.0015, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.4390918149876536e-05, + "loss": 3.9961, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.4382532202366016e-05, + "loss": 4.0047, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.4374146254855496e-05, + "loss": 3.9905, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.436576030734498e-05, + "loss": 3.9983, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435739073863819e-05, + "loss": 3.9902, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.434900479112767e-05, + "loss": 3.9892, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.434063522242088e-05, + "loss": 3.9926, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433224927491036e-05, + "loss": 3.9883, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.432386332739984e-05, + "loss": 4.0043, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.431547737988932e-05, + "loss": 4.0061, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.43070914323788e-05, + "loss": 3.9951, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.429870548486828e-05, + "loss": 3.9768, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.429031953735776e-05, + "loss": 3.9955, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.428194996865097e-05, + "loss": 3.9992, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.427356402114045e-05, + "loss": 3.9924, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.4265178073629936e-05, + "loss": 4.0011, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.4256792126119416e-05, + "loss": 4.0023, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.424840617860889e-05, + "loss": 3.9961, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.424002023109837e-05, + "loss": 3.9971, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.423163428358785e-05, + "loss": 3.9862, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.422324833607733e-05, + "loss": 4.0026, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.421486238856681e-05, + "loss": 3.9964, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.420649281986002e-05, + "loss": 4.0, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.41981068723495e-05, + "loss": 3.9899, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.418972092483898e-05, + "loss": 3.9795, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.418133497732846e-05, + "loss": 3.9937, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.4172965408621674e-05, + "loss": 4.0068, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.416459583991489e-05, + "loss": 3.9976, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.415620989240436e-05, + "loss": 3.9839, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.414782394489384e-05, + "loss": 3.9941, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.413943799738332e-05, + "loss": 3.9855, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.413106842867654e-05, + "loss": 3.9894, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.412269885996975e-05, + "loss": 3.9882, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.411431291245923e-05, + "loss": 3.9842, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.410592696494871e-05, + "loss": 3.9893, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.409754101743818e-05, + "loss": 3.9935, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.40891714487314e-05, + "loss": 3.9919, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.408078550122088e-05, + "loss": 3.9855, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407239955371036e-05, + "loss": 3.9869, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.406401360619984e-05, + "loss": 3.9955, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.405562765868932e-05, + "loss": 3.9922, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.40472417111788e-05, + "loss": 3.9961, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.403885576366828e-05, + "loss": 3.9918, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.403046981615776e-05, + "loss": 3.9943, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.402208386864724e-05, + "loss": 3.9936, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401369792113672e-05, + "loss": 3.988, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.40053119736262e-05, + "loss": 3.9934, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.399692602611568e-05, + "loss": 3.995, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.3988556457408886e-05, + "loss": 3.9843, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.3980186888702095e-05, + "loss": 3.989, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397180094119158e-05, + "loss": 3.9855, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.396341499368106e-05, + "loss": 3.993, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.395502904617054e-05, + "loss": 3.991, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.394664309866002e-05, + "loss": 3.9816, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.39382571511495e-05, + "loss": 3.9834, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.392987120363898e-05, + "loss": 3.9844, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.392148525612846e-05, + "loss": 4.0035, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.391311568742167e-05, + "loss": 3.992, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.390472973991115e-05, + "loss": 3.9934, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.389634379240063e-05, + "loss": 3.9839, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.388795784489011e-05, + "loss": 3.9961, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.387958827618332e-05, + "loss": 3.9947, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.3871218707476535e-05, + "loss": 3.9964, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.3862832759966015e-05, + "loss": 3.9993, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.3854446812455495e-05, + "loss": 3.9917, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.3846060864944975e-05, + "loss": 3.9977, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.3837674917434455e-05, + "loss": 4.0002, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.3829288969923935e-05, + "loss": 3.98, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.3820903022413415e-05, + "loss": 3.995, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3812517074902895e-05, + "loss": 3.9882, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.3804147506196104e-05, + "loss": 3.9908, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.3795761558685584e-05, + "loss": 3.9808, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.3787375611175064e-05, + "loss": 3.9885, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.3778989663664544e-05, + "loss": 3.9833, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.377062009495775e-05, + "loss": 3.9887, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.376225052625097e-05, + "loss": 3.9939, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 4.037088394165039, + "eval_runtime": 299.6362, + "eval_samples_per_second": 1273.514, + "eval_steps_per_second": 39.798, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.375386457874045e-05, + "loss": 3.9904, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.374547863122993e-05, + "loss": 3.9768, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.373709268371941e-05, + "loss": 3.9827, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.372870673620889e-05, + "loss": 3.9944, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.372032078869837e-05, + "loss": 3.9877, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.371193484118784e-05, + "loss": 3.9889, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.370356527248106e-05, + "loss": 3.988, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.369517932497054e-05, + "loss": 3.9821, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.368679337746002e-05, + "loss": 3.9823, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.367840742994949e-05, + "loss": 3.9947, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.367002148243897e-05, + "loss": 3.9932, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.366163553492845e-05, + "loss": 3.9877, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.365324958741794e-05, + "loss": 4.0004, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.364486363990742e-05, + "loss": 3.9672, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.3636494071200626e-05, + "loss": 3.9852, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.3628108123690106e-05, + "loss": 3.974, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.3619738554983316e-05, + "loss": 3.9901, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.3611352607472795e-05, + "loss": 3.9908, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.3602966659962275e-05, + "loss": 3.9759, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.3594580712451755e-05, + "loss": 3.9844, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.3586194764941235e-05, + "loss": 4.0084, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.3577808817430715e-05, + "loss": 3.9861, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.3569439248723924e-05, + "loss": 3.9916, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.3561053301213404e-05, + "loss": 3.9936, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.355266735370289e-05, + "loss": 3.9937, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.354428140619237e-05, + "loss": 3.982, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.353589545868185e-05, + "loss": 3.9806, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.352750951117133e-05, + "loss": 3.9869, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.351912356366081e-05, + "loss": 3.9826, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.351073761615029e-05, + "loss": 3.9854, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.35023680474435e-05, + "loss": 3.9924, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.349398209993298e-05, + "loss": 3.9916, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.348561253122619e-05, + "loss": 3.9905, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.347722658371567e-05, + "loss": 3.994, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.346884063620515e-05, + "loss": 3.983, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.346047106749836e-05, + "loss": 3.991, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.3452085119987845e-05, + "loss": 3.9917, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.3443699172477325e-05, + "loss": 3.9684, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.3435313224966805e-05, + "loss": 3.9869, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.3426927277456285e-05, + "loss": 3.9767, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.3418541329945765e-05, + "loss": 3.9758, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.3410155382435245e-05, + "loss": 3.9873, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.3401769434924724e-05, + "loss": 3.9929, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.3393383487414204e-05, + "loss": 3.9778, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.3385013918707414e-05, + "loss": 3.9858, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.3376627971196893e-05, + "loss": 3.9902, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.3368242023686373e-05, + "loss": 3.9787, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.3359856076175853e-05, + "loss": 3.9911, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.3351470128665327e-05, + "loss": 3.9704, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.334308418115481e-05, + "loss": 3.9817, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.333469823364429e-05, + "loss": 3.9845, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.332631228613377e-05, + "loss": 3.993, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.331792633862325e-05, + "loss": 3.9818, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.330955676991646e-05, + "loss": 3.9734, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.330117082240594e-05, + "loss": 3.9787, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.329278487489542e-05, + "loss": 3.9781, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.32843989273849e-05, + "loss": 3.9927, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.327602935867811e-05, + "loss": 3.9662, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.326764341116759e-05, + "loss": 3.9921, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.325925746365707e-05, + "loss": 3.9817, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.325087151614655e-05, + "loss": 3.9655, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.324250194743977e-05, + "loss": 3.9862, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.3234132378732976e-05, + "loss": 3.9737, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.3225746431222456e-05, + "loss": 3.9653, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.3217360483711936e-05, + "loss": 3.9741, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.3208974536201416e-05, + "loss": 3.9847, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.3200588588690896e-05, + "loss": 3.9799, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.3192202641180376e-05, + "loss": 3.9727, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.3183816693669856e-05, + "loss": 3.9702, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.3175430746159336e-05, + "loss": 3.9687, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.3167061177452545e-05, + "loss": 3.9819, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.3158691608745754e-05, + "loss": 3.9844, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.3150305661235234e-05, + "loss": 3.9843, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.314191971372472e-05, + "loss": 3.9886, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.31335337662142e-05, + "loss": 3.9852, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.312514781870368e-05, + "loss": 3.9778, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.311676187119316e-05, + "loss": 3.9835, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.310839230248637e-05, + "loss": 3.9783, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.310000635497585e-05, + "loss": 3.9765, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.309162040746533e-05, + "loss": 3.9728, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.308323445995481e-05, + "loss": 3.9744, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.307484851244429e-05, + "loss": 3.9905, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.306646256493377e-05, + "loss": 3.9893, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.305807661742325e-05, + "loss": 3.9844, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.304969066991273e-05, + "loss": 3.9623, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.304132110120594e-05, + "loss": 3.9808, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.3032951532499154e-05, + "loss": 3.9871, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.302458196379236e-05, + "loss": 3.9815, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.301619601628184e-05, + "loss": 3.9815, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.300781006877132e-05, + "loss": 3.9919, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.29994241212608e-05, + "loss": 3.982, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.299103817375028e-05, + "loss": 3.9802, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.298265222623976e-05, + "loss": 3.9763, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.297426627872924e-05, + "loss": 3.9867, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.296588033121872e-05, + "loss": 3.9827, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.29574943837082e-05, + "loss": 3.9889, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.294912481500141e-05, + "loss": 3.9733, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.294073886749089e-05, + "loss": 3.97, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.293236929878411e-05, + "loss": 3.9769, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.292398335127359e-05, + "loss": 3.9895, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.291559740376307e-05, + "loss": 3.984, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.290721145625255e-05, + "loss": 3.9727, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.289882550874203e-05, + "loss": 3.9779, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.289043956123151e-05, + "loss": 3.9699, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.288205361372099e-05, + "loss": 3.9768, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.287366766621046e-05, + "loss": 3.9739, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.286528171869994e-05, + "loss": 3.9718, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.285689577118942e-05, + "loss": 3.9798, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.284852620248264e-05, + "loss": 3.9784, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.284014025497211e-05, + "loss": 3.9762, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.283175430746159e-05, + "loss": 3.9727, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.2823368359951076e-05, + "loss": 3.9725, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.2814998791244286e-05, + "loss": 3.9824, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.2806612843733766e-05, + "loss": 3.9791, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.2798226896223246e-05, + "loss": 3.9851, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.2789840948712725e-05, + "loss": 3.9749, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.2781455001202205e-05, + "loss": 3.9842, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.2773085432495415e-05, + "loss": 3.9794, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.2764699484984894e-05, + "loss": 3.9716, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.2756313537474374e-05, + "loss": 3.9809, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.2747927589963854e-05, + "loss": 3.9782, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.2739541642453334e-05, + "loss": 3.9692, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.2731155694942814e-05, + "loss": 3.9734, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.2722769747432294e-05, + "loss": 3.9751, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.2714383799921774e-05, + "loss": 3.9767, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.270601423121499e-05, + "loss": 3.9701, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.269762828370447e-05, + "loss": 3.9713, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.268924233619395e-05, + "loss": 3.9686, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.268087276748716e-05, + "loss": 3.972, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.267248681997664e-05, + "loss": 3.988, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.266410087246612e-05, + "loss": 3.9808, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.26557149249556e-05, + "loss": 3.9805, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.264732897744508e-05, + "loss": 3.9705, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.263894302993456e-05, + "loss": 3.9827, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.263057346122777e-05, + "loss": 3.9826, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.262218751371725e-05, + "loss": 3.9842, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.261380156620673e-05, + "loss": 3.9815, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.260541561869621e-05, + "loss": 3.9803, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.2597029671185695e-05, + "loss": 3.9844, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.2588660102478904e-05, + "loss": 3.9866, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.2580274154968384e-05, + "loss": 3.9694, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.257190458626159e-05, + "loss": 3.9765, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.256351863875107e-05, + "loss": 3.9765, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.255513269124055e-05, + "loss": 3.9763, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.254674674373003e-05, + "loss": 3.967, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.253836079621951e-05, + "loss": 3.9755, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.252997484870899e-05, + "loss": 3.9674, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.2521588901198466e-05, + "loss": 3.9823, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.2513202953687946e-05, + "loss": 3.9743, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 4.029031276702881, + "eval_runtime": 305.381, + "eval_samples_per_second": 1249.557, + "eval_steps_per_second": 39.05, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.250483338498116e-05, + "loss": 3.9827, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.249644743747065e-05, + "loss": 3.9659, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.248806148996012e-05, + "loss": 3.9693, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.24796755424496e-05, + "loss": 3.9816, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.247128959493908e-05, + "loss": 3.9749, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.246290364742856e-05, + "loss": 3.9743, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.245451769991804e-05, + "loss": 3.9694, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.244613175240752e-05, + "loss": 3.9679, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.2437745804897e-05, + "loss": 3.9707, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.242935985738648e-05, + "loss": 3.9804, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.242097390987596e-05, + "loss": 3.9784, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.241258796236544e-05, + "loss": 3.9762, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.240420201485492e-05, + "loss": 3.9841, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.23958160673444e-05, + "loss": 3.9579, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.238743011983388e-05, + "loss": 3.9701, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.237904417232336e-05, + "loss": 3.9637, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.237067460361658e-05, + "loss": 3.9764, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.236228865610606e-05, + "loss": 3.9699, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.2353902708595537e-05, + "loss": 3.9671, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.234551676108501e-05, + "loss": 3.9721, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.233713081357449e-05, + "loss": 3.9914, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.2328761244867706e-05, + "loss": 3.9765, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.2320375297357186e-05, + "loss": 3.9768, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.231198934984666e-05, + "loss": 3.9782, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.230360340233614e-05, + "loss": 3.9865, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.229521745482562e-05, + "loss": 3.9637, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.2286847886118835e-05, + "loss": 3.9697, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.227847831741205e-05, + "loss": 3.9767, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.227009236990153e-05, + "loss": 3.9651, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.226170642239101e-05, + "loss": 3.9702, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.2253320474880483e-05, + "loss": 3.9763, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.2244934527369963e-05, + "loss": 3.9786, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.2236548579859443e-05, + "loss": 3.9772, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.222816263234892e-05, + "loss": 3.9785, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.22197766848384e-05, + "loss": 3.9701, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.221140711613161e-05, + "loss": 3.9811, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220302116862109e-05, + "loss": 3.9733, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.219463522111057e-05, + "loss": 3.9566, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.218624927360005e-05, + "loss": 3.9758, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.217786332608954e-05, + "loss": 3.9611, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.216947737857902e-05, + "loss": 3.9637, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.21610914310685e-05, + "loss": 3.9731, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.215270548355798e-05, + "loss": 3.979, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.214431953604746e-05, + "loss": 3.9627, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.213593358853694e-05, + "loss": 3.9785, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.212756401983015e-05, + "loss": 3.9729, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.211917807231963e-05, + "loss": 3.971, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.211079212480911e-05, + "loss": 3.9767, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.210240617729859e-05, + "loss": 3.9583, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.209402022978807e-05, + "loss": 3.9693, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.208565066108128e-05, + "loss": 3.9714, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.207726471357076e-05, + "loss": 3.9759, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.206887876606024e-05, + "loss": 3.9697, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.206049281854972e-05, + "loss": 3.9581, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.20521068710392e-05, + "loss": 3.9643, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.2043720923528677e-05, + "loss": 3.9649, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.2035334976018157e-05, + "loss": 3.9853, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.2026949028507636e-05, + "loss": 3.9504, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.201859583860458e-05, + "loss": 3.9792, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.201020989109406e-05, + "loss": 3.9697, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.200182394358354e-05, + "loss": 3.9536, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.1993437996073015e-05, + "loss": 3.9714, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.1985052048562495e-05, + "loss": 3.9651, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.1976666101051975e-05, + "loss": 3.9535, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.1968280153541454e-05, + "loss": 3.9553, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.195989420603094e-05, + "loss": 3.9759, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.195152463732415e-05, + "loss": 3.9665, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.194313868981363e-05, + "loss": 3.959, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.193475274230311e-05, + "loss": 3.9523, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.192636679479259e-05, + "loss": 3.9567, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.19179972260858e-05, + "loss": 3.9691, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.190961127857528e-05, + "loss": 3.972, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.190122533106476e-05, + "loss": 3.9691, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.189283938355424e-05, + "loss": 3.9753, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.188446981484745e-05, + "loss": 3.9715, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.187608386733693e-05, + "loss": 3.9713, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.186769791982641e-05, + "loss": 3.9662, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.1859311972315895e-05, + "loss": 3.9623, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.1850926024805375e-05, + "loss": 3.9638, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.1842540077294855e-05, + "loss": 3.9649, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.1834170508588064e-05, + "loss": 3.9628, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.1825784561077544e-05, + "loss": 3.9726, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.1817398613567024e-05, + "loss": 3.9815, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.1809012666056504e-05, + "loss": 3.9697, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.1800626718545984e-05, + "loss": 3.95, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.179225714983919e-05, + "loss": 3.9667, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.178387120232867e-05, + "loss": 3.9723, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.177548525481815e-05, + "loss": 3.9728, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.176709930730763e-05, + "loss": 3.9642, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.175872973860085e-05, + "loss": 3.9788, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.175036016989406e-05, + "loss": 3.9711, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.174197422238354e-05, + "loss": 3.9663, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173358827487302e-05, + "loss": 3.9629, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.17252023273625e-05, + "loss": 3.975, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.171681637985198e-05, + "loss": 3.9676, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.170843043234146e-05, + "loss": 3.9753, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.170004448483094e-05, + "loss": 3.9614, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.169165853732042e-05, + "loss": 3.9582, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.1683288968613626e-05, + "loss": 3.9645, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.1674903021103106e-05, + "loss": 3.977, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.1666517073592586e-05, + "loss": 3.9708, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.1658131126082066e-05, + "loss": 3.9603, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.1649745178571546e-05, + "loss": 3.9628, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.164135923106103e-05, + "loss": 3.9563, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.1632973283550506e-05, + "loss": 3.9688, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.1624587336039986e-05, + "loss": 3.9573, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.16162177673332e-05, + "loss": 3.9574, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.1607831819822675e-05, + "loss": 3.9661, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.1599445872312155e-05, + "loss": 3.9654, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.1591059924801635e-05, + "loss": 3.9664, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.158270673489858e-05, + "loss": 3.9629, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.157432078738806e-05, + "loss": 3.9575, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.156593483987754e-05, + "loss": 3.9671, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.155754889236702e-05, + "loss": 3.9696, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.15491629448565e-05, + "loss": 3.9658, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.154077699734598e-05, + "loss": 3.9676, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.153239104983546e-05, + "loss": 3.9711, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.152400510232494e-05, + "loss": 3.963, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.151561915481442e-05, + "loss": 3.958, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.15072332073039e-05, + "loss": 3.9686, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.149884725979338e-05, + "loss": 3.9646, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.149046131228286e-05, + "loss": 3.9554, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.148209174357607e-05, + "loss": 3.9637, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.147370579606555e-05, + "loss": 3.9612, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.146531984855503e-05, + "loss": 3.9673, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.145693390104451e-05, + "loss": 3.956, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.144854795353399e-05, + "loss": 3.9644, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.1440178384827204e-05, + "loss": 3.9576, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.1431808816120413e-05, + "loss": 3.9598, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.1423422868609893e-05, + "loss": 3.9692, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.1415036921099373e-05, + "loss": 3.9719, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.140665097358885e-05, + "loss": 3.9623, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.139826502607833e-05, + "loss": 3.958, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.138987907856781e-05, + "loss": 3.9713, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.138149313105729e-05, + "loss": 3.9672, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.137310718354677e-05, + "loss": 3.9702, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.136473761483998e-05, + "loss": 3.9718, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.135635166732946e-05, + "loss": 3.9658, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.134796571981894e-05, + "loss": 3.9728, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.133957977230842e-05, + "loss": 3.974, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.133121020360164e-05, + "loss": 3.9564, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.132282425609112e-05, + "loss": 3.9639, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.131445468738433e-05, + "loss": 3.9624, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.130606873987381e-05, + "loss": 3.9622, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.129768279236329e-05, + "loss": 3.9576, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.128929684485277e-05, + "loss": 3.9613, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.128091089734225e-05, + "loss": 3.9543, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.127252494983173e-05, + "loss": 3.9703, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.1264171759928665e-05, + "loss": 3.9629, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 4.0221428871154785, + "eval_runtime": 301.2896, + "eval_samples_per_second": 1266.526, + "eval_steps_per_second": 39.58, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.1255785812418145e-05, + "loss": 3.9618, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.1247399864907625e-05, + "loss": 3.9607, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.123901391739711e-05, + "loss": 3.9533, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.123062796988659e-05, + "loss": 3.9675, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.122224202237607e-05, + "loss": 3.9641, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.121385607486555e-05, + "loss": 3.9637, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120547012735503e-05, + "loss": 3.9566, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.119708417984451e-05, + "loss": 3.9545, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.118871461113772e-05, + "loss": 3.9623, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.11803286636272e-05, + "loss": 3.9646, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.117194271611668e-05, + "loss": 3.9659, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.116357314740989e-05, + "loss": 3.9623, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.115518719989937e-05, + "loss": 3.9748, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.114680125238885e-05, + "loss": 3.9431, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.113841530487833e-05, + "loss": 3.9577, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.113002935736781e-05, + "loss": 3.9501, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.112164340985729e-05, + "loss": 3.9599, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.111325746234677e-05, + "loss": 3.96, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.110487151483625e-05, + "loss": 3.9548, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.109648556732573e-05, + "loss": 3.9574, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.108809961981521e-05, + "loss": 3.9809, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.107971367230469e-05, + "loss": 3.9651, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.10713441035979e-05, + "loss": 3.9602, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.106295815608738e-05, + "loss": 3.968, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.105457220857686e-05, + "loss": 3.9722, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.104618626106634e-05, + "loss": 3.9559, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.103780031355582e-05, + "loss": 3.954, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.10294143660453e-05, + "loss": 3.9658, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.1021044797338514e-05, + "loss": 3.9535, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.1012658849827994e-05, + "loss": 3.9605, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.1004272902317474e-05, + "loss": 3.9617, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.0995886954806954e-05, + "loss": 3.9689, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.0987501007296434e-05, + "loss": 3.9645, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.0979115059785914e-05, + "loss": 3.9625, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.0970729112275394e-05, + "loss": 3.9593, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.09623595435686e-05, + "loss": 3.9706, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.095397359605808e-05, + "loss": 3.9635, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.094558764854756e-05, + "loss": 3.9432, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.093720170103704e-05, + "loss": 3.963, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.092881575352652e-05, + "loss": 3.9491, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.0920429806016e-05, + "loss": 3.9556, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.091206023730921e-05, + "loss": 3.958, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.09036742897987e-05, + "loss": 3.9652, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.089528834228817e-05, + "loss": 3.9557, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.088690239477765e-05, + "loss": 3.958, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.087853282607087e-05, + "loss": 3.9654, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.087014687856035e-05, + "loss": 3.9544, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.0861777309853556e-05, + "loss": 3.9684, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.0853391362343036e-05, + "loss": 3.9456, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.0845005414832516e-05, + "loss": 3.9514, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.0836619467321996e-05, + "loss": 3.9609, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.082823351981147e-05, + "loss": 3.9614, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.081984757230095e-05, + "loss": 3.9599, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.0811461624790436e-05, + "loss": 3.9433, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.0803075677279916e-05, + "loss": 3.9559, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.0794689729769396e-05, + "loss": 3.9489, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.0786303782258876e-05, + "loss": 3.9734, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.0777917834748356e-05, + "loss": 3.9364, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.0769531887237836e-05, + "loss": 3.9663, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.0761145939727316e-05, + "loss": 3.9571, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.0752776371020525e-05, + "loss": 3.9413, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.0744390423510005e-05, + "loss": 3.9575, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.0736004475999485e-05, + "loss": 3.9539, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.0727618528488965e-05, + "loss": 3.9386, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.0719248959782174e-05, + "loss": 3.946, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.0710863012271654e-05, + "loss": 3.9644, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.0702477064761134e-05, + "loss": 3.9533, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.069409111725062e-05, + "loss": 3.9481, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.068572154854383e-05, + "loss": 3.9418, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.067735197983704e-05, + "loss": 3.9414, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.066896603232652e-05, + "loss": 3.9564, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.0660580084816e-05, + "loss": 3.9584, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.065219413730548e-05, + "loss": 3.9565, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.064380818979496e-05, + "loss": 3.9647, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.063542224228444e-05, + "loss": 3.9625, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.062703629477392e-05, + "loss": 3.9553, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.06186503472634e-05, + "loss": 3.9533, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.061028077855661e-05, + "loss": 3.9526, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.060189483104609e-05, + "loss": 3.9527, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.0593508883535574e-05, + "loss": 3.9557, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.0585122936025054e-05, + "loss": 3.9476, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.0576736988514534e-05, + "loss": 3.962, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.056838379861147e-05, + "loss": 3.9618, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.055999785110095e-05, + "loss": 3.9604, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.055161190359043e-05, + "loss": 3.9401, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.054324233488364e-05, + "loss": 3.9516, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.053485638737312e-05, + "loss": 3.966, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.05264704398626e-05, + "loss": 3.9577, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.051808449235208e-05, + "loss": 3.956, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.0509698544841565e-05, + "loss": 3.9659, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.0501312597331045e-05, + "loss": 3.9578, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0492926649820525e-05, + "loss": 3.9549, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.0484540702310004e-05, + "loss": 3.952, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.0476171133603214e-05, + "loss": 3.9618, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.0467801564896426e-05, + "loss": 3.9526, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.0459415617385906e-05, + "loss": 3.9706, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.0451029669875386e-05, + "loss": 3.9438, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.0442643722364866e-05, + "loss": 3.9536, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.0434257774854346e-05, + "loss": 3.9511, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.0425871827343826e-05, + "loss": 3.9621, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.0417485879833302e-05, + "loss": 3.9648, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.0409099932322782e-05, + "loss": 3.9445, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.0400730363615998e-05, + "loss": 3.9525, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.0392344416105478e-05, + "loss": 3.9445, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.038395846859495e-05, + "loss": 3.9545, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.0375572521084435e-05, + "loss": 3.9404, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.036720295237765e-05, + "loss": 3.951, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.035881700486713e-05, + "loss": 3.9547, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.0350431057356604e-05, + "loss": 3.9501, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.0342045109846084e-05, + "loss": 3.957, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.0333659162335564e-05, + "loss": 3.9529, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.0325273214825044e-05, + "loss": 3.9411, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.0316887267314527e-05, + "loss": 3.9586, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.0308501319804007e-05, + "loss": 3.956, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.0300131751097216e-05, + "loss": 3.953, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.0291762182390425e-05, + "loss": 3.9565, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.0283376234879905e-05, + "loss": 3.9601, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.027500666617312e-05, + "loss": 3.9535, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.0266620718662604e-05, + "loss": 3.9468, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.0258234771152077e-05, + "loss": 3.9552, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0249848823641557e-05, + "loss": 3.9507, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.0241462876131037e-05, + "loss": 3.9471, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.0233076928620517e-05, + "loss": 3.9494, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.0224690981109997e-05, + "loss": 3.9506, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.021630503359948e-05, + "loss": 3.953, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.020793546489269e-05, + "loss": 3.9452, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.019954951738217e-05, + "loss": 3.9507, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.019116356987165e-05, + "loss": 3.9461, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.018277762236113e-05, + "loss": 3.9521, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.017439167485061e-05, + "loss": 3.9525, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.016600572734009e-05, + "loss": 3.9584, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.0157636158633302e-05, + "loss": 3.9524, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.0149250211122782e-05, + "loss": 3.9473, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.0140864263612262e-05, + "loss": 3.9548, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.0132478316101742e-05, + "loss": 3.9584, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.012410874739495e-05, + "loss": 3.9621, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.0115722799884434e-05, + "loss": 3.9616, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.0107336852373914e-05, + "loss": 3.9527, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.0098967283667123e-05, + "loss": 3.9638, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.0090581336156603e-05, + "loss": 3.9578, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.0082195388646083e-05, + "loss": 3.9492, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.0073809441135563e-05, + "loss": 3.9532, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.0065423493625043e-05, + "loss": 3.9491, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.0057037546114526e-05, + "loss": 3.9505, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.0048651598604006e-05, + "loss": 3.9442, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.0040265651093486e-05, + "loss": 3.9563, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.0031879703582966e-05, + "loss": 3.9443, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.002349375607244e-05, + "loss": 3.956, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.001510780856192e-05, + "loss": 3.9519, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.0006721861051403e-05, + "loss": 3.9522, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 4.016125202178955, + "eval_runtime": 293.0281, + "eval_samples_per_second": 1302.233, + "eval_steps_per_second": 40.696, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.9998335913540883e-05, + "loss": 3.944, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.9989949966030363e-05, + "loss": 3.9422, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.9981564018519843e-05, + "loss": 3.955, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.9973178071009323e-05, + "loss": 3.9554, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.9964792123498803e-05, + "loss": 3.9533, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.9956406175988283e-05, + "loss": 3.9442, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.9948020228477763e-05, + "loss": 3.9443, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.9939634280967242e-05, + "loss": 3.9449, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.9931248333456722e-05, + "loss": 3.9568, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.9922862385946206e-05, + "loss": 3.9516, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.991447643843568e-05, + "loss": 3.957, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.990609049092516e-05, + "loss": 3.9622, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.9897720922218375e-05, + "loss": 3.9357, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.988933497470785e-05, + "loss": 3.9415, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.988094902719733e-05, + "loss": 3.9398, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.987256307968681e-05, + "loss": 3.9464, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.986417713217629e-05, + "loss": 3.9483, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.985579118466577e-05, + "loss": 3.9478, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.984740523715525e-05, + "loss": 3.945, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.983901928964473e-05, + "loss": 3.9708, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.983063334213421e-05, + "loss": 3.9528, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.982224739462369e-05, + "loss": 3.9524, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.9813861447113174e-05, + "loss": 3.9519, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.9805491878406383e-05, + "loss": 3.9652, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.9797105930895863e-05, + "loss": 3.9424, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.9788719983385343e-05, + "loss": 3.9461, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.9780334035874823e-05, + "loss": 3.9525, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.9771948088364303e-05, + "loss": 3.9428, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.9763562140853783e-05, + "loss": 3.9498, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.9755176193343267e-05, + "loss": 3.9508, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.974679024583274e-05, + "loss": 3.9591, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.9738420677125956e-05, + "loss": 3.9491, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.9730034729615436e-05, + "loss": 3.9534, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.9721648782104916e-05, + "loss": 3.9516, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.9713279213398128e-05, + "loss": 3.9552, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.9704893265887608e-05, + "loss": 3.952, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.9696507318377088e-05, + "loss": 3.9369, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.9688121370866568e-05, + "loss": 3.948, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.967973542335604e-05, + "loss": 3.9366, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.967134947584552e-05, + "loss": 3.9462, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.9662963528335004e-05, + "loss": 3.9473, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.9654593959628213e-05, + "loss": 3.9551, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.9646208012117693e-05, + "loss": 3.9427, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.9637822064607173e-05, + "loss": 3.9476, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.9629436117096653e-05, + "loss": 3.9542, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.9621050169586133e-05, + "loss": 3.9434, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.9612680600879346e-05, + "loss": 3.9576, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.9604294653368826e-05, + "loss": 3.9337, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.9595908705858306e-05, + "loss": 3.9419, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.9587522758347786e-05, + "loss": 3.9528, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.9579136810837266e-05, + "loss": 3.952, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.9570750863326746e-05, + "loss": 3.9484, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.9562381294619958e-05, + "loss": 3.9294, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.9553995347109438e-05, + "loss": 3.9499, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.9545609399598918e-05, + "loss": 3.9338, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.9537223452088398e-05, + "loss": 3.9629, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.9528837504577878e-05, + "loss": 3.9306, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.9520451557067358e-05, + "loss": 3.9551, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.9512065609556838e-05, + "loss": 3.9419, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.9503679662046318e-05, + "loss": 3.9298, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.949531009333953e-05, + "loss": 3.949, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.948692414582901e-05, + "loss": 3.9412, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.947853819831849e-05, + "loss": 3.9256, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.947015225080797e-05, + "loss": 3.9333, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.946176630329745e-05, + "loss": 3.9535, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.945339673459066e-05, + "loss": 3.9421, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.944501078708014e-05, + "loss": 3.9351, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.9436624839569622e-05, + "loss": 3.935, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.9428238892059102e-05, + "loss": 3.93, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.9419852944548576e-05, + "loss": 3.9444, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.9411466997038055e-05, + "loss": 3.9503, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.9403081049527535e-05, + "loss": 3.9456, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.9394695102017015e-05, + "loss": 3.9541, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.93863091545065e-05, + "loss": 3.9491, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.9377939585799708e-05, + "loss": 3.949, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.9369553638289188e-05, + "loss": 3.9385, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.9361167690778668e-05, + "loss": 3.945, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.9352798122071877e-05, + "loss": 3.9452, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.934441217456136e-05, + "loss": 3.9404, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.933602622705084e-05, + "loss": 3.9374, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.932764027954032e-05, + "loss": 3.9494, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.93192543320298e-05, + "loss": 3.9544, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.931086838451928e-05, + "loss": 3.9468, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.930248243700876e-05, + "loss": 3.9302, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.929411286830197e-05, + "loss": 3.9448, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.928574329959518e-05, + "loss": 3.9538, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.927735735208466e-05, + "loss": 3.9521, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.926897140457414e-05, + "loss": 3.9406, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.926058545706362e-05, + "loss": 3.9559, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.925221588835683e-05, + "loss": 3.9485, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.9243829940846314e-05, + "loss": 3.94, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.9235443993335794e-05, + "loss": 3.9429, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9227058045825274e-05, + "loss": 3.951, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.9218688477118483e-05, + "loss": 3.9422, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.9210302529607963e-05, + "loss": 3.9583, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.9201916582097443e-05, + "loss": 3.9376, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.9193530634586923e-05, + "loss": 3.9385, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.9185144687076406e-05, + "loss": 3.9419, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.9176758739565886e-05, + "loss": 3.9538, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.9168372792055366e-05, + "loss": 3.9499, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.9159986844544846e-05, + "loss": 3.9365, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.9151617275838055e-05, + "loss": 3.9397, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.9143231328327535e-05, + "loss": 3.9356, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.9134845380817015e-05, + "loss": 3.9494, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.9126459433306498e-05, + "loss": 3.9278, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9118073485795978e-05, + "loss": 3.9395, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9109687538285458e-05, + "loss": 3.9473, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9101301590774938e-05, + "loss": 3.941, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.909291564326441e-05, + "loss": 3.9429, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.9084546074557627e-05, + "loss": 3.9426, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.907617650585084e-05, + "loss": 3.9338, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.906780693714405e-05, + "loss": 3.9441, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.905942098963353e-05, + "loss": 3.9466, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.905103504212301e-05, + "loss": 3.9448, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.904264909461249e-05, + "loss": 3.9457, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.903426314710197e-05, + "loss": 3.9494, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.902587719959145e-05, + "loss": 3.9452, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.9017491252080932e-05, + "loss": 3.9385, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.9009105304570412e-05, + "loss": 3.9431, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.9000719357059885e-05, + "loss": 3.9416, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8992333409549365e-05, + "loss": 3.9337, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.898396384084258e-05, + "loss": 3.9394, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.897557789333206e-05, + "loss": 3.9372, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.8967191945821537e-05, + "loss": 3.949, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.8958805998311017e-05, + "loss": 3.935, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.8950420050800497e-05, + "loss": 3.939, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.8942050482093706e-05, + "loss": 3.9328, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.8933664534583186e-05, + "loss": 3.942, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.892527858707267e-05, + "loss": 3.9359, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.891689263956215e-05, + "loss": 3.9545, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.890850669205163e-05, + "loss": 3.9422, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.890012074454111e-05, + "loss": 3.941, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.889173479703059e-05, + "loss": 3.9425, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.88833652283238e-05, + "loss": 3.9452, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.887497928081328e-05, + "loss": 3.9503, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.8866593333302762e-05, + "loss": 3.9504, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.8858207385792242e-05, + "loss": 3.9457, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.8849821438281722e-05, + "loss": 3.9504, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.884145186957493e-05, + "loss": 3.9475, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.883306592206441e-05, + "loss": 3.9392, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.882467997455389e-05, + "loss": 3.9388, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.881629402704337e-05, + "loss": 3.9438, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8807924458336583e-05, + "loss": 3.9402, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.8799538510826063e-05, + "loss": 3.9316, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.8791152563315543e-05, + "loss": 3.9438, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.8782766615805023e-05, + "loss": 3.9361, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.8774380668294503e-05, + "loss": 3.9446, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.8765994720783983e-05, + "loss": 3.9412, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.8757608773273463e-05, + "loss": 3.9413, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 4.011011123657227, + "eval_runtime": 520.7016, + "eval_samples_per_second": 732.84, + "eval_steps_per_second": 22.902, + "step": 1297440 + }, + { + "epoch": 1.0, + "learning_rate": 2.8749222825762946e-05, + "loss": 3.9339, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.8740853257056155e-05, + "loss": 3.9361, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.8732467309545635e-05, + "loss": 3.9464, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.8724081362035115e-05, + "loss": 3.9413, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.8715695414524595e-05, + "loss": 3.9436, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.8707309467014072e-05, + "loss": 3.934, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.8698956277111017e-05, + "loss": 3.9318, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.8690570329600497e-05, + "loss": 3.9351, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.8682184382089977e-05, + "loss": 3.9457, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.8673798434579457e-05, + "loss": 3.9433, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.866542886587267e-05, + "loss": 3.9425, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.865705929716588e-05, + "loss": 3.9501, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.864867334965536e-05, + "loss": 3.926, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.8640287402144838e-05, + "loss": 3.9355, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.8631901454634318e-05, + "loss": 3.9357, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.8623515507123798e-05, + "loss": 3.9278, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.8615129559613278e-05, + "loss": 3.9409, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.860675999090649e-05, + "loss": 3.9343, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.859837404339597e-05, + "loss": 3.9333, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.858998809588545e-05, + "loss": 3.9647, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.858160214837493e-05, + "loss": 3.9406, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.857321620086441e-05, + "loss": 3.9437, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.856483025335389e-05, + "loss": 3.9418, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.8556444305843367e-05, + "loss": 3.9537, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.8548058358332847e-05, + "loss": 3.9359, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.8539672410822327e-05, + "loss": 3.9351, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.8531286463311807e-05, + "loss": 3.9382, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.8522900515801287e-05, + "loss": 3.9358, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.8514514568290767e-05, + "loss": 3.9374, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.8506161378387715e-05, + "loss": 3.9342, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.8497775430877195e-05, + "loss": 3.9551, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.8489405862170404e-05, + "loss": 3.9411, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.8481019914659884e-05, + "loss": 3.9403, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.8472633967149364e-05, + "loss": 3.9414, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.8464264398442577e-05, + "loss": 3.9458, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.8455878450932057e-05, + "loss": 3.9409, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.8447492503421537e-05, + "loss": 3.926, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.8439106555911016e-05, + "loss": 3.9376, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.843072060840049e-05, + "loss": 3.9256, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.842233466088997e-05, + "loss": 3.9411, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.8413948713379453e-05, + "loss": 3.9348, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.8405562765868933e-05, + "loss": 3.9431, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.8397176818358413e-05, + "loss": 3.9344, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.8388790870847893e-05, + "loss": 3.9369, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.8380404923337373e-05, + "loss": 3.9441, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.8372018975826853e-05, + "loss": 3.9356, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.8363633028316333e-05, + "loss": 3.9428, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.8355247080805813e-05, + "loss": 3.9285, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.8346861133295293e-05, + "loss": 3.9327, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.8338475185784773e-05, + "loss": 3.9391, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.8330105617077985e-05, + "loss": 3.9403, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.8321719669567465e-05, + "loss": 3.9411, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.8313350100860674e-05, + "loss": 3.9176, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.8304964153350154e-05, + "loss": 3.9415, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.8296578205839634e-05, + "loss": 3.9206, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.8288192258329117e-05, + "loss": 3.953, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.8279806310818597e-05, + "loss": 3.9228, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.8271420363308077e-05, + "loss": 3.944, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.8263034415797557e-05, + "loss": 3.9358, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.825464846828703e-05, + "loss": 3.9253, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.824626252077651e-05, + "loss": 3.9326, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.8237892952069726e-05, + "loss": 3.9324, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.822952338336294e-05, + "loss": 3.9166, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.822113743585242e-05, + "loss": 3.9252, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.82127514883419e-05, + "loss": 3.9392, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.820436554083138e-05, + "loss": 3.9327, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.8195979593320855e-05, + "loss": 3.9271, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.8187593645810335e-05, + "loss": 3.9255, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.8179207698299815e-05, + "loss": 3.9198, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.8170821750789295e-05, + "loss": 3.9356, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.8162452182082504e-05, + "loss": 3.9356, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.8154066234571984e-05, + "loss": 3.9369, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.8145680287061464e-05, + "loss": 3.9453, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.8137294339550947e-05, + "loss": 3.9383, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.8128924770844156e-05, + "loss": 3.9414, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.8120538823333636e-05, + "loss": 3.9235, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.8112152875823116e-05, + "loss": 3.9377, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.8103766928312596e-05, + "loss": 3.9334, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.809539735960581e-05, + "loss": 3.9284, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.808701141209529e-05, + "loss": 3.9295, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.807862546458477e-05, + "loss": 3.9358, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.807023951707425e-05, + "loss": 3.9464, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.806185356956373e-05, + "loss": 3.9392, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.8053484000856938e-05, + "loss": 3.9219, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.804511443215015e-05, + "loss": 3.9275, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.803672848463963e-05, + "loss": 3.9429, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.802834253712911e-05, + "loss": 3.9408, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.801995658961859e-05, + "loss": 3.9342, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.801157064210807e-05, + "loss": 3.9436, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.800318469459755e-05, + "loss": 3.9402, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.799479874708703e-05, + "loss": 3.9267, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.798641279957651e-05, + "loss": 3.9319, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.7978026852065993e-05, + "loss": 3.9421, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.7969657283359202e-05, + "loss": 3.9292, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.7961271335848682e-05, + "loss": 3.9503, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.7952885388338162e-05, + "loss": 3.929, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.7944499440827642e-05, + "loss": 3.9292, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.7936113493317122e-05, + "loss": 3.9325, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.7927743924610335e-05, + "loss": 3.9422, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.7919357977099815e-05, + "loss": 3.9417, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.7910972029589295e-05, + "loss": 3.9287, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.7902586082078774e-05, + "loss": 3.928, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.7894216513371984e-05, + "loss": 3.9259, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.7885830565861464e-05, + "loss": 3.9435, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.7877444618350947e-05, + "loss": 3.9179, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.7869075049644156e-05, + "loss": 3.9245, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.7860689102133636e-05, + "loss": 3.9402, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.7852303154623116e-05, + "loss": 3.9317, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.7843917207112596e-05, + "loss": 3.9296, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.7835531259602076e-05, + "loss": 3.9335, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.7827145312091556e-05, + "loss": 3.9252, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.7818759364581036e-05, + "loss": 3.9356, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.7810373417070512e-05, + "loss": 3.9319, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.7801987469559992e-05, + "loss": 3.9337, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.7793601522049472e-05, + "loss": 3.936, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.7785215574538952e-05, + "loss": 3.9425, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.7776829627028432e-05, + "loss": 3.9314, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.7768443679517912e-05, + "loss": 3.9266, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.776009048961486e-05, + "loss": 3.9351, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.7751704542104334e-05, + "loss": 3.9319, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.7743318594593814e-05, + "loss": 3.9215, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.7734932647083294e-05, + "loss": 3.9302, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.7726546699572774e-05, + "loss": 3.9271, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.7718160752062257e-05, + "loss": 3.9401, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.7709791183355466e-05, + "loss": 3.9247, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.7701405235844946e-05, + "loss": 3.9333, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.7693019288334426e-05, + "loss": 3.9166, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.7684633340823906e-05, + "loss": 3.9341, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.7676247393313386e-05, + "loss": 3.9266, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.7667861445802866e-05, + "loss": 3.9448, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.7659491877096078e-05, + "loss": 3.935, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.7651105929585558e-05, + "loss": 3.9346, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.7642719982075038e-05, + "loss": 3.9258, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.7634334034564518e-05, + "loss": 3.9315, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.7625948087053998e-05, + "loss": 3.9423, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.7617562139543478e-05, + "loss": 3.9439, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.7609176192032958e-05, + "loss": 3.9383, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.760080662332617e-05, + "loss": 3.9393, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.759242067581565e-05, + "loss": 3.9341, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.758403472830513e-05, + "loss": 3.932, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.757564878079461e-05, + "loss": 3.9301, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.756726283328409e-05, + "loss": 3.935, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.755887688577357e-05, + "loss": 3.9311, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.7550507317066783e-05, + "loss": 3.9213, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.7542121369556263e-05, + "loss": 3.9325, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.7533735422045743e-05, + "loss": 3.9272, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.7525349474535223e-05, + "loss": 3.9337, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.7516963527024696e-05, + "loss": 3.9307, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.750857757951418e-05, + "loss": 3.9311, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 4.006119251251221, + "eval_runtime": 527.9434, + "eval_samples_per_second": 722.788, + "eval_steps_per_second": 22.588, + "step": 1373760 + }, + { + "epoch": 0.0, + "learning_rate": 2.750019163200366e-05, + "loss": 3.921, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.749180568449314e-05, + "loss": 3.9271, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.748341973698262e-05, + "loss": 3.9341, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.74750337894721e-05, + "loss": 3.9325, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.746664784196158e-05, + "loss": 3.9374, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.745826189445106e-05, + "loss": 3.9196, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.744987594694054e-05, + "loss": 3.9265, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.744148999943002e-05, + "loss": 3.9218, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.7433104051919502e-05, + "loss": 3.9352, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.7424718104408982e-05, + "loss": 3.9342, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.7416332156898462e-05, + "loss": 3.9326, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.7407946209387935e-05, + "loss": 3.9357, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.7399560261877415e-05, + "loss": 3.9177, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.7391174314366895e-05, + "loss": 3.9227, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.7382788366856375e-05, + "loss": 3.9278, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.737440241934586e-05, + "loss": 3.9193, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.7366032850639067e-05, + "loss": 3.9288, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.7357646903128547e-05, + "loss": 3.9236, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.7349260955618027e-05, + "loss": 3.9225, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.7340875008107507e-05, + "loss": 3.9554, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.733250543940072e-05, + "loss": 3.9274, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.73241194918902e-05, + "loss": 3.9338, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.731573354437968e-05, + "loss": 3.9316, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.730734759686916e-05, + "loss": 3.9418, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.729896164935864e-05, + "loss": 3.923, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.729057570184812e-05, + "loss": 3.9243, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.728220613314133e-05, + "loss": 3.9294, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.7273820185630812e-05, + "loss": 3.9297, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.7265434238120292e-05, + "loss": 3.9231, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.7257048290609772e-05, + "loss": 3.9271, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.7248662343099252e-05, + "loss": 3.9419, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.7240276395588732e-05, + "loss": 3.9315, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.723190682688194e-05, + "loss": 3.9287, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.722352087937142e-05, + "loss": 3.9365, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.7215151310664633e-05, + "loss": 3.9327, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.7206765363154113e-05, + "loss": 3.9311, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.7198379415643593e-05, + "loss": 3.916, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.7189993468133073e-05, + "loss": 3.9313, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.7181607520622553e-05, + "loss": 3.9145, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.7173221573112033e-05, + "loss": 3.9259, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.7164835625601513e-05, + "loss": 3.9234, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.7156449678090996e-05, + "loss": 3.9342, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.7148063730580476e-05, + "loss": 3.9268, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.713967778306995e-05, + "loss": 3.9257, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.713129183555943e-05, + "loss": 3.9324, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.712290588804891e-05, + "loss": 3.9282, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.711451994053839e-05, + "loss": 3.9343, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.7106150371831602e-05, + "loss": 3.9184, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.7097764424321082e-05, + "loss": 3.9181, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.7089378476810562e-05, + "loss": 3.9308, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.7081025286907507e-05, + "loss": 3.9292, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.7072639339396987e-05, + "loss": 3.9276, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.7064253391886467e-05, + "loss": 3.912, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.705586744437595e-05, + "loss": 3.9322, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.7047481496865423e-05, + "loss": 3.9111, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.7039095549354903e-05, + "loss": 3.9407, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.7030709601844383e-05, + "loss": 3.9086, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.7022323654333863e-05, + "loss": 3.9349, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.7013954085627076e-05, + "loss": 3.9239, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.7005568138116556e-05, + "loss": 3.9215, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.6997182190606036e-05, + "loss": 3.9209, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.6988796243095516e-05, + "loss": 3.9247, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.6980410295584995e-05, + "loss": 3.9076, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.6972024348074475e-05, + "loss": 3.9173, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.6963638400563955e-05, + "loss": 3.9246, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.6955252453053435e-05, + "loss": 3.9273, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.6946882884346648e-05, + "loss": 3.9137, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.6938496936836128e-05, + "loss": 3.9174, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.6930110989325608e-05, + "loss": 3.915, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.6921725041815088e-05, + "loss": 3.9206, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.6913339094304568e-05, + "loss": 3.9239, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.6904953146794048e-05, + "loss": 3.9269, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.6896567199283528e-05, + "loss": 3.9356, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.688819763057674e-05, + "loss": 3.9328, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.687981168306622e-05, + "loss": 3.9324, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.68714257355557e-05, + "loss": 3.9135, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.686303978804518e-05, + "loss": 3.926, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.685467021933839e-05, + "loss": 3.9274, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.684628427182787e-05, + "loss": 3.9145, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.6837898324317352e-05, + "loss": 3.9252, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.682952875561056e-05, + "loss": 3.9252, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.682114280810004e-05, + "loss": 3.9358, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.681275686058952e-05, + "loss": 3.9274, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.6804370913079e-05, + "loss": 3.91, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.679598496556848e-05, + "loss": 3.9207, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.6787599018057958e-05, + "loss": 3.9295, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.6779213070547438e-05, + "loss": 3.9315, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.6770843501840654e-05, + "loss": 3.9257, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.6762457554330134e-05, + "loss": 3.9337, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6754071606819607e-05, + "loss": 3.9314, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.674568565930909e-05, + "loss": 3.9141, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.673729971179857e-05, + "loss": 3.9273, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.672891376428805e-05, + "loss": 3.9277, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.672052781677753e-05, + "loss": 3.9186, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.671214186926701e-05, + "loss": 3.9414, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.670375592175649e-05, + "loss": 3.922, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.669536997424597e-05, + "loss": 3.9148, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.668698402673545e-05, + "loss": 3.9244, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.667859807922493e-05, + "loss": 3.9341, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.6670228510518142e-05, + "loss": 3.9294, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.6661842563007622e-05, + "loss": 3.923, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.6653456615497102e-05, + "loss": 3.9158, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.6645070667986582e-05, + "loss": 3.9151, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.6636717478083524e-05, + "loss": 3.9338, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.6628331530573004e-05, + "loss": 3.9081, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.6619961961866213e-05, + "loss": 3.9181, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.6611576014355693e-05, + "loss": 3.9296, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.6603190066845173e-05, + "loss": 3.9207, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.6594804119334653e-05, + "loss": 3.9203, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.6586418171824136e-05, + "loss": 3.9257, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.6578032224313616e-05, + "loss": 3.9174, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.6569646276803096e-05, + "loss": 3.9253, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.6561260329292576e-05, + "loss": 3.9229, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.6552890760585785e-05, + "loss": 3.9228, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.6544504813075265e-05, + "loss": 3.9281, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.6536118865564745e-05, + "loss": 3.9322, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.6527732918054228e-05, + "loss": 3.9276, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.6519363349347437e-05, + "loss": 3.9152, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.6510977401836917e-05, + "loss": 3.9214, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.6502591454326397e-05, + "loss": 3.9211, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.6494205506815877e-05, + "loss": 3.9117, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.6485819559305357e-05, + "loss": 3.9266, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.6477433611794837e-05, + "loss": 3.913, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.646906404308805e-05, + "loss": 3.929, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.646067809557753e-05, + "loss": 3.9151, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.645229214806701e-05, + "loss": 3.9237, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.644390620055649e-05, + "loss": 3.9092, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.64355366318497e-05, + "loss": 3.9243, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.6427150684339182e-05, + "loss": 3.915, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.6418764736828662e-05, + "loss": 3.9363, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.6410378789318142e-05, + "loss": 3.9309, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.6401992841807622e-05, + "loss": 3.9245, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.639362327310083e-05, + "loss": 3.9147, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.638523732559031e-05, + "loss": 3.922, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.637685137807979e-05, + "loss": 3.933, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.6368465430569267e-05, + "loss": 3.9357, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.6360079483058747e-05, + "loss": 3.9252, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.6351709914351963e-05, + "loss": 3.9327, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.6343323966841443e-05, + "loss": 3.926, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.633493801933092e-05, + "loss": 3.9229, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.63265520718204e-05, + "loss": 3.9196, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.631816612430988e-05, + "loss": 3.9222, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.630979655560309e-05, + "loss": 3.9232, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.630141060809257e-05, + "loss": 3.9128, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.629302466058205e-05, + "loss": 3.92, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.628463871307153e-05, + "loss": 3.9225, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.6276252765561012e-05, + "loss": 3.9207, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.6267866818050492e-05, + "loss": 3.9214, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.6259480870539972e-05, + "loss": 3.9173, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 4.001740455627441, + "eval_runtime": 335.0378, + "eval_samples_per_second": 1138.949, + "eval_steps_per_second": 35.593, + "step": 1450080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6251094923029452e-05, + "loss": 3.9197, + "step": 1450496 + }, + { + "epoch": 1.0, + "learning_rate": 2.6242708975518932e-05, + "loss": 3.9157, + "step": 1451008 + }, + { + "epoch": 1.0, + "learning_rate": 2.623433940681214e-05, + "loss": 3.9263, + "step": 1451520 + }, + { + "epoch": 1.0, + "learning_rate": 2.6225969838105353e-05, + "loss": 3.9193, + "step": 1452032 + }, + { + "epoch": 1.0, + "learning_rate": 2.6217583890594833e-05, + "loss": 3.9301, + "step": 1452544 + }, + { + "epoch": 1.0, + "learning_rate": 2.6209197943084313e-05, + "loss": 3.9098, + "step": 1453056 + }, + { + "epoch": 1.0, + "learning_rate": 2.6200811995573793e-05, + "loss": 3.9203, + "step": 1453568 + }, + { + "epoch": 1.0, + "learning_rate": 2.6192426048063273e-05, + "loss": 3.9113, + "step": 1454080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6184040100552753e-05, + "loss": 3.928, + "step": 1454592 + }, + { + "epoch": 1.0, + "learning_rate": 2.6175654153042233e-05, + "loss": 3.925, + "step": 1455104 + }, + { + "epoch": 1.0, + "learning_rate": 2.6167268205531713e-05, + "loss": 3.9249, + "step": 1455616 + }, + { + "epoch": 1.0, + "learning_rate": 2.6158898636824925e-05, + "loss": 3.9267, + "step": 1456128 + }, + { + "epoch": 1.0, + "learning_rate": 2.6150512689314405e-05, + "loss": 3.9082, + "step": 1456640 + }, + { + "epoch": 1.0, + "learning_rate": 2.6142126741803885e-05, + "loss": 3.915, + "step": 1457152 + }, + { + "epoch": 1.0, + "learning_rate": 2.6133740794293365e-05, + "loss": 3.9179, + "step": 1457664 + }, + { + "epoch": 1.0, + "learning_rate": 2.6125371225586574e-05, + "loss": 3.913, + "step": 1458176 + }, + { + "epoch": 1.0, + "learning_rate": 2.6116985278076054e-05, + "loss": 3.919, + "step": 1458688 + }, + { + "epoch": 1.0, + "learning_rate": 2.6108615709369267e-05, + "loss": 3.9199, + "step": 1459200 + }, + { + "epoch": 1.0, + "learning_rate": 2.6100229761858747e-05, + "loss": 3.913, + "step": 1459712 + }, + { + "epoch": 1.0, + "learning_rate": 2.6091843814348227e-05, + "loss": 3.9492, + "step": 1460224 + }, + { + "epoch": 1.0, + "learning_rate": 2.6083457866837707e-05, + "loss": 3.9195, + "step": 1460736 + }, + { + "epoch": 1.0, + "learning_rate": 2.6075071919327187e-05, + "loss": 3.9242, + "step": 1461248 + }, + { + "epoch": 1.0, + "learning_rate": 2.60667023506204e-05, + "loss": 3.9251, + "step": 1461760 + }, + { + "epoch": 1.0, + "learning_rate": 2.605831640310988e-05, + "loss": 3.9308, + "step": 1462272 + }, + { + "epoch": 1.0, + "learning_rate": 2.604993045559936e-05, + "loss": 3.9151, + "step": 1462784 + }, + { + "epoch": 1.0, + "learning_rate": 2.604154450808884e-05, + "loss": 3.9225, + "step": 1463296 + }, + { + "epoch": 1.0, + "learning_rate": 2.603315856057832e-05, + "loss": 3.9173, + "step": 1463808 + }, + { + "epoch": 1.0, + "learning_rate": 2.60247726130678e-05, + "loss": 3.9209, + "step": 1464320 + }, + { + "epoch": 1.0, + "learning_rate": 2.6016403044361008e-05, + "loss": 3.9092, + "step": 1464832 + }, + { + "epoch": 1.01, + "learning_rate": 2.600801709685049e-05, + "loss": 3.9215, + "step": 1465344 + }, + { + "epoch": 1.01, + "learning_rate": 2.599963114933997e-05, + "loss": 3.9287, + "step": 1465856 + }, + { + "epoch": 1.01, + "learning_rate": 2.599124520182945e-05, + "loss": 3.9238, + "step": 1466368 + }, + { + "epoch": 1.01, + "learning_rate": 2.5982859254318925e-05, + "loss": 3.9237, + "step": 1466880 + }, + { + "epoch": 1.01, + "learning_rate": 2.5974473306808404e-05, + "loss": 3.926, + "step": 1467392 + }, + { + "epoch": 1.01, + "learning_rate": 2.596610373810162e-05, + "loss": 3.9215, + "step": 1467904 + }, + { + "epoch": 1.01, + "learning_rate": 2.59577177905911e-05, + "loss": 3.9277, + "step": 1468416 + }, + { + "epoch": 1.01, + "learning_rate": 2.5949348221884313e-05, + "loss": 3.905, + "step": 1468928 + }, + { + "epoch": 1.01, + "learning_rate": 2.5940962274373793e-05, + "loss": 3.9228, + "step": 1469440 + }, + { + "epoch": 1.01, + "learning_rate": 2.5932576326863273e-05, + "loss": 3.9059, + "step": 1469952 + }, + { + "epoch": 1.01, + "learning_rate": 2.5924190379352753e-05, + "loss": 3.9208, + "step": 1470464 + }, + { + "epoch": 1.01, + "learning_rate": 2.591580443184223e-05, + "loss": 3.9162, + "step": 1470976 + }, + { + "epoch": 1.01, + "learning_rate": 2.590741848433171e-05, + "loss": 3.9255, + "step": 1471488 + }, + { + "epoch": 1.01, + "learning_rate": 2.589903253682119e-05, + "loss": 3.9186, + "step": 1472000 + }, + { + "epoch": 1.01, + "learning_rate": 2.589064658931067e-05, + "loss": 3.9158, + "step": 1472512 + }, + { + "epoch": 1.01, + "learning_rate": 2.588226064180015e-05, + "loss": 3.9241, + "step": 1473024 + }, + { + "epoch": 1.01, + "learning_rate": 2.587387469428963e-05, + "loss": 3.92, + "step": 1473536 + }, + { + "epoch": 1.01, + "learning_rate": 2.586548874677911e-05, + "loss": 3.9235, + "step": 1474048 + }, + { + "epoch": 1.01, + "learning_rate": 2.585710279926859e-05, + "loss": 3.9148, + "step": 1474560 + }, + { + "epoch": 1.01, + "learning_rate": 2.58487332305618e-05, + "loss": 3.9053, + "step": 1475072 + }, + { + "epoch": 1.01, + "learning_rate": 2.584034728305128e-05, + "loss": 3.9223, + "step": 1475584 + }, + { + "epoch": 1.01, + "learning_rate": 2.583196133554076e-05, + "loss": 3.9202, + "step": 1476096 + }, + { + "epoch": 1.01, + "learning_rate": 2.58236081456377e-05, + "loss": 3.9198, + "step": 1476608 + }, + { + "epoch": 1.01, + "learning_rate": 2.5815222198127183e-05, + "loss": 3.9075, + "step": 1477120 + }, + { + "epoch": 1.01, + "learning_rate": 2.5806836250616663e-05, + "loss": 3.9271, + "step": 1477632 + }, + { + "epoch": 1.01, + "learning_rate": 2.5798450303106143e-05, + "loss": 3.8996, + "step": 1478144 + }, + { + "epoch": 1.01, + "learning_rate": 2.5790064355595623e-05, + "loss": 3.9323, + "step": 1478656 + }, + { + "epoch": 1.01, + "learning_rate": 2.5781678408085103e-05, + "loss": 3.9034, + "step": 1479168 + }, + { + "epoch": 1.01, + "learning_rate": 2.5773292460574583e-05, + "loss": 3.9216, + "step": 1479680 + }, + { + "epoch": 1.01, + "learning_rate": 2.5764906513064063e-05, + "loss": 3.9148, + "step": 1480192 + }, + { + "epoch": 1.01, + "learning_rate": 2.5756520565553543e-05, + "loss": 3.9151, + "step": 1480704 + }, + { + "epoch": 1.01, + "learning_rate": 2.5748134618043023e-05, + "loss": 3.9089, + "step": 1481216 + }, + { + "epoch": 1.01, + "learning_rate": 2.5739748670532502e-05, + "loss": 3.9216, + "step": 1481728 + }, + { + "epoch": 1.01, + "learning_rate": 2.5731362723021986e-05, + "loss": 3.8971, + "step": 1482240 + }, + { + "epoch": 1.01, + "learning_rate": 2.5722993154315195e-05, + "loss": 3.9063, + "step": 1482752 + }, + { + "epoch": 1.01, + "learning_rate": 2.5714607206804675e-05, + "loss": 3.9209, + "step": 1483264 + }, + { + "epoch": 1.01, + "learning_rate": 2.5706221259294155e-05, + "loss": 3.9165, + "step": 1483776 + }, + { + "epoch": 1.01, + "learning_rate": 2.5697851690587367e-05, + "loss": 3.9093, + "step": 1484288 + }, + { + "epoch": 1.01, + "learning_rate": 2.5689465743076847e-05, + "loss": 3.9103, + "step": 1484800 + }, + { + "epoch": 1.01, + "learning_rate": 2.5681079795566327e-05, + "loss": 3.9011, + "step": 1485312 + }, + { + "epoch": 1.01, + "learning_rate": 2.5672693848055807e-05, + "loss": 3.9107, + "step": 1485824 + }, + { + "epoch": 1.01, + "learning_rate": 2.5664307900545287e-05, + "loss": 3.9173, + "step": 1486336 + }, + { + "epoch": 1.01, + "learning_rate": 2.565592195303476e-05, + "loss": 3.9182, + "step": 1486848 + }, + { + "epoch": 1.01, + "learning_rate": 2.5647536005524244e-05, + "loss": 3.9276, + "step": 1487360 + }, + { + "epoch": 1.01, + "learning_rate": 2.5639150058013724e-05, + "loss": 3.9225, + "step": 1487872 + }, + { + "epoch": 1.01, + "learning_rate": 2.563078048930694e-05, + "loss": 3.925, + "step": 1488384 + }, + { + "epoch": 1.01, + "learning_rate": 2.5622394541796413e-05, + "loss": 3.9049, + "step": 1488896 + }, + { + "epoch": 1.01, + "learning_rate": 2.5614008594285893e-05, + "loss": 3.9156, + "step": 1489408 + }, + { + "epoch": 1.01, + "learning_rate": 2.5605622646775373e-05, + "loss": 3.9216, + "step": 1489920 + }, + { + "epoch": 1.01, + "learning_rate": 2.5597253078068585e-05, + "loss": 3.9066, + "step": 1490432 + }, + { + "epoch": 1.01, + "learning_rate": 2.55888835093618e-05, + "loss": 3.9181, + "step": 1490944 + }, + { + "epoch": 1.01, + "learning_rate": 2.558049756185128e-05, + "loss": 3.9158, + "step": 1491456 + }, + { + "epoch": 1.01, + "learning_rate": 2.557211161434076e-05, + "loss": 3.9258, + "step": 1491968 + }, + { + "epoch": 1.01, + "learning_rate": 2.5563725666830234e-05, + "loss": 3.9207, + "step": 1492480 + }, + { + "epoch": 1.01, + "learning_rate": 2.5555339719319714e-05, + "loss": 3.9041, + "step": 1492992 + }, + { + "epoch": 1.01, + "learning_rate": 2.5546953771809194e-05, + "loss": 3.9153, + "step": 1493504 + }, + { + "epoch": 1.01, + "learning_rate": 2.5538567824298677e-05, + "loss": 3.9187, + "step": 1494016 + }, + { + "epoch": 1.01, + "learning_rate": 2.5530181876788157e-05, + "loss": 3.9238, + "step": 1494528 + }, + { + "epoch": 1.01, + "learning_rate": 2.5521812308081366e-05, + "loss": 3.9188, + "step": 1495040 + }, + { + "epoch": 1.01, + "learning_rate": 2.5513426360570846e-05, + "loss": 3.9218, + "step": 1495552 + }, + { + "epoch": 1.02, + "learning_rate": 2.5505040413060326e-05, + "loss": 3.9262, + "step": 1496064 + }, + { + "epoch": 1.02, + "learning_rate": 2.5496654465549806e-05, + "loss": 3.9077, + "step": 1496576 + }, + { + "epoch": 1.02, + "learning_rate": 2.548828489684302e-05, + "loss": 3.9204, + "step": 1497088 + }, + { + "epoch": 1.02, + "learning_rate": 2.5479915328136235e-05, + "loss": 3.9154, + "step": 1497600 + }, + { + "epoch": 1.02, + "learning_rate": 2.5471529380625708e-05, + "loss": 3.9144, + "step": 1498112 + }, + { + "epoch": 1.02, + "learning_rate": 2.5463143433115188e-05, + "loss": 3.9311, + "step": 1498624 + }, + { + "epoch": 1.02, + "learning_rate": 2.5454757485604668e-05, + "loss": 3.9173, + "step": 1499136 + }, + { + "epoch": 1.02, + "learning_rate": 2.5446371538094148e-05, + "loss": 3.9042, + "step": 1499648 + }, + { + "epoch": 1.02, + "learning_rate": 2.543800196938736e-05, + "loss": 3.9159, + "step": 1500160 + }, + { + "epoch": 1.02, + "learning_rate": 2.542961602187684e-05, + "loss": 3.9246, + "step": 1500672 + }, + { + "epoch": 1.02, + "learning_rate": 2.542123007436632e-05, + "loss": 3.9238, + "step": 1501184 + }, + { + "epoch": 1.02, + "learning_rate": 2.54128441268558e-05, + "loss": 3.9153, + "step": 1501696 + }, + { + "epoch": 1.02, + "learning_rate": 2.540445817934528e-05, + "loss": 3.9071, + "step": 1502208 + }, + { + "epoch": 1.02, + "learning_rate": 2.539607223183476e-05, + "loss": 3.9087, + "step": 1502720 + }, + { + "epoch": 1.02, + "learning_rate": 2.538768628432424e-05, + "loss": 3.9254, + "step": 1503232 + }, + { + "epoch": 1.02, + "learning_rate": 2.5379300336813723e-05, + "loss": 3.8998, + "step": 1503744 + }, + { + "epoch": 1.02, + "learning_rate": 2.537094714691066e-05, + "loss": 3.9095, + "step": 1504256 + }, + { + "epoch": 1.02, + "learning_rate": 2.536256119940014e-05, + "loss": 3.9206, + "step": 1504768 + }, + { + "epoch": 1.02, + "learning_rate": 2.535417525188962e-05, + "loss": 3.9173, + "step": 1505280 + }, + { + "epoch": 1.02, + "learning_rate": 2.53457893043791e-05, + "loss": 3.9072, + "step": 1505792 + }, + { + "epoch": 1.02, + "learning_rate": 2.5337403356868585e-05, + "loss": 3.9197, + "step": 1506304 + }, + { + "epoch": 1.02, + "learning_rate": 2.5329017409358065e-05, + "loss": 3.9111, + "step": 1506816 + }, + { + "epoch": 1.02, + "learning_rate": 2.5320631461847545e-05, + "loss": 3.915, + "step": 1507328 + }, + { + "epoch": 1.02, + "learning_rate": 2.5312245514337024e-05, + "loss": 3.9163, + "step": 1507840 + }, + { + "epoch": 1.02, + "learning_rate": 2.5303875945630234e-05, + "loss": 3.9135, + "step": 1508352 + }, + { + "epoch": 1.02, + "learning_rate": 2.5295489998119714e-05, + "loss": 3.9251, + "step": 1508864 + }, + { + "epoch": 1.02, + "learning_rate": 2.5287104050609193e-05, + "loss": 3.9201, + "step": 1509376 + }, + { + "epoch": 1.02, + "learning_rate": 2.5278718103098677e-05, + "loss": 3.9216, + "step": 1509888 + }, + { + "epoch": 1.02, + "learning_rate": 2.5270348534391886e-05, + "loss": 3.9053, + "step": 1510400 + }, + { + "epoch": 1.02, + "learning_rate": 2.5261962586881366e-05, + "loss": 3.9145, + "step": 1510912 + }, + { + "epoch": 1.02, + "learning_rate": 2.5253576639370846e-05, + "loss": 3.9164, + "step": 1511424 + }, + { + "epoch": 1.02, + "learning_rate": 2.5245190691860326e-05, + "loss": 3.9032, + "step": 1511936 + }, + { + "epoch": 1.02, + "learning_rate": 2.5236804744349806e-05, + "loss": 3.9181, + "step": 1512448 + }, + { + "epoch": 1.02, + "learning_rate": 2.5228418796839286e-05, + "loss": 3.908, + "step": 1512960 + }, + { + "epoch": 1.02, + "learning_rate": 2.5220049228132498e-05, + "loss": 3.919, + "step": 1513472 + }, + { + "epoch": 1.02, + "learning_rate": 2.5211663280621978e-05, + "loss": 3.9083, + "step": 1513984 + }, + { + "epoch": 1.02, + "learning_rate": 2.5203277333111458e-05, + "loss": 3.9183, + "step": 1514496 + }, + { + "epoch": 1.02, + "learning_rate": 2.5194891385600938e-05, + "loss": 3.8958, + "step": 1515008 + }, + { + "epoch": 1.02, + "learning_rate": 2.5186521816894147e-05, + "loss": 3.9175, + "step": 1515520 + }, + { + "epoch": 1.02, + "learning_rate": 2.517813586938363e-05, + "loss": 3.9098, + "step": 1516032 + }, + { + "epoch": 1.02, + "learning_rate": 2.516974992187311e-05, + "loss": 3.9251, + "step": 1516544 + }, + { + "epoch": 1.02, + "learning_rate": 2.516136397436259e-05, + "loss": 3.9216, + "step": 1517056 + }, + { + "epoch": 1.02, + "learning_rate": 2.515297802685207e-05, + "loss": 3.9217, + "step": 1517568 + }, + { + "epoch": 1.02, + "learning_rate": 2.5144592079341544e-05, + "loss": 3.9048, + "step": 1518080 + }, + { + "epoch": 1.02, + "learning_rate": 2.513622251063476e-05, + "loss": 3.9191, + "step": 1518592 + }, + { + "epoch": 1.02, + "learning_rate": 2.512783656312424e-05, + "loss": 3.9214, + "step": 1519104 + }, + { + "epoch": 1.02, + "learning_rate": 2.5119450615613716e-05, + "loss": 3.9258, + "step": 1519616 + }, + { + "epoch": 1.02, + "learning_rate": 2.5111064668103196e-05, + "loss": 3.919, + "step": 1520128 + }, + { + "epoch": 1.02, + "learning_rate": 2.5102695099396412e-05, + "loss": 3.9205, + "step": 1520640 + }, + { + "epoch": 1.02, + "learning_rate": 2.5094309151885892e-05, + "loss": 3.9204, + "step": 1521152 + }, + { + "epoch": 1.02, + "learning_rate": 2.50859395831791e-05, + "loss": 3.9201, + "step": 1521664 + }, + { + "epoch": 1.02, + "learning_rate": 2.5077553635668584e-05, + "loss": 3.9085, + "step": 1522176 + }, + { + "epoch": 1.02, + "learning_rate": 2.5069167688158064e-05, + "loss": 3.9137, + "step": 1522688 + }, + { + "epoch": 1.02, + "learning_rate": 2.5060781740647544e-05, + "loss": 3.9142, + "step": 1523200 + }, + { + "epoch": 1.02, + "learning_rate": 2.5052395793137017e-05, + "loss": 3.9081, + "step": 1523712 + }, + { + "epoch": 1.02, + "learning_rate": 2.5044009845626497e-05, + "loss": 3.9113, + "step": 1524224 + }, + { + "epoch": 1.02, + "learning_rate": 2.5035623898115977e-05, + "loss": 3.9176, + "step": 1524736 + }, + { + "epoch": 1.02, + "learning_rate": 2.502723795060546e-05, + "loss": 3.9108, + "step": 1525248 + }, + { + "epoch": 1.02, + "learning_rate": 2.501885200309494e-05, + "loss": 3.9118, + "step": 1525760 + }, + { + "epoch": 1.02, + "learning_rate": 2.501048243438815e-05, + "loss": 3.9193, + "step": 1526272 + }, + { + "epoch": 1.03, + "eval_loss": 3.998426675796509, + "eval_runtime": 311.8076, + "eval_samples_per_second": 1223.803, + "eval_steps_per_second": 38.245, + "step": 1526400 + }, + { + "epoch": 0.0, + "learning_rate": 2.500209648687763e-05, + "loss": 3.9029, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.499371053936711e-05, + "loss": 3.9096, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.498532459185659e-05, + "loss": 3.9195, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.497693864434607e-05, + "loss": 3.9125, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.496855269683555e-05, + "loss": 3.9263, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.4960166749325033e-05, + "loss": 3.901, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.4951780801814513e-05, + "loss": 3.911, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.494339485430399e-05, + "loss": 3.9039, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.493500890679347e-05, + "loss": 3.9192, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.492662295928295e-05, + "loss": 3.9204, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.491823701177243e-05, + "loss": 3.911, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.490985106426191e-05, + "loss": 3.9242, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.4901465116751392e-05, + "loss": 3.8974, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.4893079169240872e-05, + "loss": 3.9084, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.488469322173035e-05, + "loss": 3.9128, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.487630727421983e-05, + "loss": 3.9049, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.486792132670931e-05, + "loss": 3.909, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.485953537919879e-05, + "loss": 3.9083, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.485114943168827e-05, + "loss": 3.91, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.484277986298148e-05, + "loss": 3.938, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.483439391547096e-05, + "loss": 3.9119, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.482600796796044e-05, + "loss": 3.9114, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.481762202044992e-05, + "loss": 3.9203, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.48092360729394e-05, + "loss": 3.9229, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.480086650423261e-05, + "loss": 3.907, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.4792480556722093e-05, + "loss": 3.9167, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.4784094609211573e-05, + "loss": 3.909, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.4775708661701053e-05, + "loss": 3.9142, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.476732271419053e-05, + "loss": 3.903, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.475893676668001e-05, + "loss": 3.9131, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.475055081916949e-05, + "loss": 3.9241, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.474216487165897e-05, + "loss": 3.9157, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.4733795302952182e-05, + "loss": 3.9137, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.4725409355441662e-05, + "loss": 3.9168, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.4717039786734875e-05, + "loss": 3.9159, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.470865383922435e-05, + "loss": 3.9174, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.470026789171383e-05, + "loss": 3.8985, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.469188194420331e-05, + "loss": 3.9123, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.4683495996692795e-05, + "loss": 3.9027, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.4675110049182275e-05, + "loss": 3.9068, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.4666740480475484e-05, + "loss": 3.9113, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.4658354532964964e-05, + "loss": 3.9171, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.4649968585454444e-05, + "loss": 3.9111, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.4641599016747656e-05, + "loss": 3.9101, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.4633213069237136e-05, + "loss": 3.9158, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.4624827121726616e-05, + "loss": 3.9114, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.4616441174216096e-05, + "loss": 3.916, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.4608055226705576e-05, + "loss": 3.9091, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.4599685657998785e-05, + "loss": 3.898, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.4591299710488265e-05, + "loss": 3.9179, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.4582913762977748e-05, + "loss": 3.9097, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.4574527815467228e-05, + "loss": 3.9136, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.4566141867956708e-05, + "loss": 3.9036, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.4557755920446185e-05, + "loss": 3.9137, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.4549369972935665e-05, + "loss": 3.8938, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.4540984025425145e-05, + "loss": 3.9232, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.4532598077914625e-05, + "loss": 3.8958, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.4524212130404105e-05, + "loss": 3.9087, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.4515826182893588e-05, + "loss": 3.9127, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.4507440235383064e-05, + "loss": 3.9047, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.4499070666676277e-05, + "loss": 3.9058, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.4490684719165757e-05, + "loss": 3.9094, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.4482298771655237e-05, + "loss": 3.8973, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.4473912824144717e-05, + "loss": 3.8954, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.446554325543793e-05, + "loss": 3.9102, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.445715730792741e-05, + "loss": 3.9105, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.444878773922062e-05, + "loss": 3.8986, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.4440401791710098e-05, + "loss": 3.907, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.4432015844199578e-05, + "loss": 3.8919, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.4423629896689058e-05, + "loss": 3.9046, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.4415243949178538e-05, + "loss": 3.9101, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.4406858001668018e-05, + "loss": 3.9094, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.439848843296123e-05, + "loss": 3.9181, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.439010248545071e-05, + "loss": 3.9149, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.4381716537940187e-05, + "loss": 3.9232, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.437333059042967e-05, + "loss": 3.897, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.436494464291915e-05, + "loss": 3.9097, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.4356575074212363e-05, + "loss": 3.9122, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.434818912670184e-05, + "loss": 3.8954, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.433980317919132e-05, + "loss": 3.9133, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.43314172316808e-05, + "loss": 3.9101, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.4323047662974012e-05, + "loss": 3.9172, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.4314661715463492e-05, + "loss": 3.9154, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.4306275767952972e-05, + "loss": 3.895, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.4297889820442452e-05, + "loss": 3.9117, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.428950387293193e-05, + "loss": 3.9077, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.428113430422514e-05, + "loss": 3.916, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.4272748356714624e-05, + "loss": 3.9099, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4264362409204104e-05, + "loss": 3.9157, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4255976461693584e-05, + "loss": 3.9166, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.4247606892986793e-05, + "loss": 3.9043, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.4239220945476273e-05, + "loss": 3.9114, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.4230834997965753e-05, + "loss": 3.9052, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.4222449050455233e-05, + "loss": 3.9131, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.4214063102944713e-05, + "loss": 3.9233, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.4205677155434193e-05, + "loss": 3.9078, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.4197291207923673e-05, + "loss": 3.9006, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.4188905260413153e-05, + "loss": 3.9065, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.4180535691706365e-05, + "loss": 3.9137, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.4172166122999574e-05, + "loss": 3.9207, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.4163780175489058e-05, + "loss": 3.905, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.4155394227978538e-05, + "loss": 3.9031, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.4147008280468018e-05, + "loss": 3.9003, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4138638711761227e-05, + "loss": 3.9164, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.4130252764250707e-05, + "loss": 3.8915, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.4121866816740187e-05, + "loss": 3.9051, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.4113480869229667e-05, + "loss": 3.9112, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.410511130052288e-05, + "loss": 3.9071, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.409672535301236e-05, + "loss": 3.9018, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.408833940550184e-05, + "loss": 3.9149, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.4079953457991316e-05, + "loss": 3.9034, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.4071567510480796e-05, + "loss": 3.9042, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.406318156297028e-05, + "loss": 3.9101, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.405479561545976e-05, + "loss": 3.9096, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.404640966794924e-05, + "loss": 3.9159, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.403802372043872e-05, + "loss": 3.9146, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.40296377729282e-05, + "loss": 3.9121, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.4021251825417675e-05, + "loss": 3.8974, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.4012865877907155e-05, + "loss": 3.9082, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.4004479930396635e-05, + "loss": 3.9081, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.3996110361689848e-05, + "loss": 3.8958, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.3987724414179328e-05, + "loss": 3.9122, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.3979338466668808e-05, + "loss": 3.8975, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.3970952519158288e-05, + "loss": 3.912, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.3962566571647767e-05, + "loss": 3.9056, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.395419700294098e-05, + "loss": 3.9087, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.394581105543046e-05, + "loss": 3.8924, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.393742510791994e-05, + "loss": 3.9072, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.392907191801688e-05, + "loss": 3.9063, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.392068597050636e-05, + "loss": 3.9115, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.391230002299584e-05, + "loss": 3.912, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.390391407548532e-05, + "loss": 3.9177, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.38955281279748e-05, + "loss": 3.8961, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.388714218046428e-05, + "loss": 3.9126, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.387875623295376e-05, + "loss": 3.9184, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.387037028544324e-05, + "loss": 3.9164, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.386198433793272e-05, + "loss": 3.9133, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.38535983904222e-05, + "loss": 3.9158, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.3845228821715414e-05, + "loss": 3.9108, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.3836842874204894e-05, + "loss": 3.9143, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.3828456926694374e-05, + "loss": 3.8972, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.382007097918385e-05, + "loss": 3.9108, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.381168503167333e-05, + "loss": 3.9035, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.3803315462966543e-05, + "loss": 3.9044, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.3794929515456026e-05, + "loss": 3.9063, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.3786543567945502e-05, + "loss": 3.906, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.3778173999238715e-05, + "loss": 3.9068, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.3769788051728195e-05, + "loss": 3.9011, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.3761402104217675e-05, + "loss": 3.915, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.9950153827667236, + "eval_runtime": 294.0522, + "eval_samples_per_second": 1297.698, + "eval_steps_per_second": 40.554, + "step": 1602720 + }, + { + "epoch": 0.0, + "learning_rate": 2.375301615670715e-05, + "loss": 3.8991, + "step": 1603072 + }, + { + "epoch": 0.0, + "learning_rate": 2.3744630209196635e-05, + "loss": 3.8988, + "step": 1603584 + }, + { + "epoch": 0.0, + "learning_rate": 2.3736244261686115e-05, + "loss": 3.9111, + "step": 1604096 + }, + { + "epoch": 0.0, + "learning_rate": 2.3727858314175595e-05, + "loss": 3.9103, + "step": 1604608 + }, + { + "epoch": 0.0, + "learning_rate": 2.3719472366665075e-05, + "loss": 3.9121, + "step": 1605120 + }, + { + "epoch": 0.0, + "learning_rate": 2.3711086419154555e-05, + "loss": 3.9016, + "step": 1605632 + }, + { + "epoch": 0.0, + "learning_rate": 2.370270047164403e-05, + "loss": 3.8995, + "step": 1606144 + }, + { + "epoch": 0.0, + "learning_rate": 2.369431452413351e-05, + "loss": 3.9003, + "step": 1606656 + }, + { + "epoch": 0.0, + "learning_rate": 2.368592857662299e-05, + "loss": 3.9071, + "step": 1607168 + }, + { + "epoch": 0.0, + "learning_rate": 2.3677542629112474e-05, + "loss": 3.9162, + "step": 1607680 + }, + { + "epoch": 0.0, + "learning_rate": 2.3669156681601954e-05, + "loss": 3.902, + "step": 1608192 + }, + { + "epoch": 0.0, + "learning_rate": 2.3660770734091434e-05, + "loss": 3.9137, + "step": 1608704 + }, + { + "epoch": 0.0, + "learning_rate": 2.3652384786580914e-05, + "loss": 3.8974, + "step": 1609216 + }, + { + "epoch": 0.0, + "learning_rate": 2.364399883907039e-05, + "loss": 3.8986, + "step": 1609728 + }, + { + "epoch": 0.0, + "learning_rate": 2.363561289155987e-05, + "loss": 3.9075, + "step": 1610240 + }, + { + "epoch": 0.0, + "learning_rate": 2.362722694404935e-05, + "loss": 3.8951, + "step": 1610752 + }, + { + "epoch": 0.0, + "learning_rate": 2.3618840996538834e-05, + "loss": 3.9017, + "step": 1611264 + }, + { + "epoch": 0.0, + "learning_rate": 2.3610471427832043e-05, + "loss": 3.9047, + "step": 1611776 + }, + { + "epoch": 0.0, + "learning_rate": 2.3602085480321523e-05, + "loss": 3.8999, + "step": 1612288 + }, + { + "epoch": 0.0, + "learning_rate": 2.3593699532811003e-05, + "loss": 3.9295, + "step": 1612800 + }, + { + "epoch": 0.0, + "learning_rate": 2.3585313585300483e-05, + "loss": 3.9115, + "step": 1613312 + }, + { + "epoch": 0.0, + "learning_rate": 2.3576927637789963e-05, + "loss": 3.9075, + "step": 1613824 + }, + { + "epoch": 0.0, + "learning_rate": 2.3568558069083175e-05, + "loss": 3.9109, + "step": 1614336 + }, + { + "epoch": 0.0, + "learning_rate": 2.3560172121572655e-05, + "loss": 3.9162, + "step": 1614848 + }, + { + "epoch": 0.0, + "learning_rate": 2.3551786174062135e-05, + "loss": 3.8976, + "step": 1615360 + }, + { + "epoch": 0.0, + "learning_rate": 2.3543416605355344e-05, + "loss": 3.9089, + "step": 1615872 + }, + { + "epoch": 0.0, + "learning_rate": 2.3535030657844824e-05, + "loss": 3.9061, + "step": 1616384 + }, + { + "epoch": 0.0, + "learning_rate": 2.3526644710334304e-05, + "loss": 3.8997, + "step": 1616896 + }, + { + "epoch": 0.0, + "learning_rate": 2.3518258762823788e-05, + "loss": 3.8942, + "step": 1617408 + }, + { + "epoch": 0.0, + "learning_rate": 2.3509872815313268e-05, + "loss": 3.9088, + "step": 1617920 + }, + { + "epoch": 0.01, + "learning_rate": 2.3501486867802748e-05, + "loss": 3.9192, + "step": 1618432 + }, + { + "epoch": 0.01, + "learning_rate": 2.3493100920292224e-05, + "loss": 3.9093, + "step": 1618944 + }, + { + "epoch": 0.01, + "learning_rate": 2.3484714972781704e-05, + "loss": 3.9123, + "step": 1619456 + }, + { + "epoch": 0.01, + "learning_rate": 2.3476329025271184e-05, + "loss": 3.9081, + "step": 1619968 + }, + { + "epoch": 0.01, + "learning_rate": 2.3467959456564397e-05, + "loss": 3.9067, + "step": 1620480 + }, + { + "epoch": 0.01, + "learning_rate": 2.3459573509053877e-05, + "loss": 3.9111, + "step": 1620992 + }, + { + "epoch": 0.01, + "learning_rate": 2.3451187561543357e-05, + "loss": 3.8983, + "step": 1621504 + }, + { + "epoch": 0.01, + "learning_rate": 2.3442801614032836e-05, + "loss": 3.9013, + "step": 1622016 + }, + { + "epoch": 0.01, + "learning_rate": 2.3434415666522316e-05, + "loss": 3.8935, + "step": 1622528 + }, + { + "epoch": 0.01, + "learning_rate": 2.3426029719011796e-05, + "loss": 3.8987, + "step": 1623040 + }, + { + "epoch": 0.01, + "learning_rate": 2.3417643771501276e-05, + "loss": 3.9052, + "step": 1623552 + }, + { + "epoch": 0.01, + "learning_rate": 2.340927420279449e-05, + "loss": 3.9113, + "step": 1624064 + }, + { + "epoch": 0.01, + "learning_rate": 2.340088825528397e-05, + "loss": 3.9018, + "step": 1624576 + }, + { + "epoch": 0.01, + "learning_rate": 2.339250230777345e-05, + "loss": 3.9032, + "step": 1625088 + }, + { + "epoch": 0.01, + "learning_rate": 2.3384116360262925e-05, + "loss": 3.9107, + "step": 1625600 + }, + { + "epoch": 0.01, + "learning_rate": 2.3375730412752405e-05, + "loss": 3.9043, + "step": 1626112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3367344465241885e-05, + "loss": 3.9093, + "step": 1626624 + }, + { + "epoch": 0.01, + "learning_rate": 2.3358958517731365e-05, + "loss": 3.9033, + "step": 1627136 + }, + { + "epoch": 0.01, + "learning_rate": 2.3350572570220845e-05, + "loss": 3.8886, + "step": 1627648 + }, + { + "epoch": 0.01, + "learning_rate": 2.334218662271033e-05, + "loss": 3.9129, + "step": 1628160 + }, + { + "epoch": 0.01, + "learning_rate": 2.333383343280727e-05, + "loss": 3.9014, + "step": 1628672 + }, + { + "epoch": 0.01, + "learning_rate": 2.332544748529675e-05, + "loss": 3.9078, + "step": 1629184 + }, + { + "epoch": 0.01, + "learning_rate": 2.3317061537786227e-05, + "loss": 3.8973, + "step": 1629696 + }, + { + "epoch": 0.01, + "learning_rate": 2.3308675590275707e-05, + "loss": 3.9043, + "step": 1630208 + }, + { + "epoch": 0.01, + "learning_rate": 2.330028964276519e-05, + "loss": 3.8879, + "step": 1630720 + }, + { + "epoch": 0.01, + "learning_rate": 2.32919200740584e-05, + "loss": 3.913, + "step": 1631232 + }, + { + "epoch": 0.01, + "learning_rate": 2.328353412654788e-05, + "loss": 3.8927, + "step": 1631744 + }, + { + "epoch": 0.01, + "learning_rate": 2.327514817903736e-05, + "loss": 3.9035, + "step": 1632256 + }, + { + "epoch": 0.01, + "learning_rate": 2.326676223152684e-05, + "loss": 3.9064, + "step": 1632768 + }, + { + "epoch": 0.01, + "learning_rate": 2.325837628401632e-05, + "loss": 3.8977, + "step": 1633280 + }, + { + "epoch": 0.01, + "learning_rate": 2.32499903365058e-05, + "loss": 3.8966, + "step": 1633792 + }, + { + "epoch": 0.01, + "learning_rate": 2.324162076779901e-05, + "loss": 3.9086, + "step": 1634304 + }, + { + "epoch": 0.01, + "learning_rate": 2.323323482028849e-05, + "loss": 3.8859, + "step": 1634816 + }, + { + "epoch": 0.01, + "learning_rate": 2.322484887277797e-05, + "loss": 3.8879, + "step": 1635328 + }, + { + "epoch": 0.01, + "learning_rate": 2.321646292526745e-05, + "loss": 3.903, + "step": 1635840 + }, + { + "epoch": 0.01, + "learning_rate": 2.320807697775693e-05, + "loss": 3.905, + "step": 1636352 + }, + { + "epoch": 0.01, + "learning_rate": 2.3199691030246408e-05, + "loss": 3.8903, + "step": 1636864 + }, + { + "epoch": 0.01, + "learning_rate": 2.319130508273589e-05, + "loss": 3.9004, + "step": 1637376 + }, + { + "epoch": 0.01, + "learning_rate": 2.318291913522537e-05, + "loss": 3.8835, + "step": 1637888 + }, + { + "epoch": 0.01, + "learning_rate": 2.317454956651858e-05, + "loss": 3.8949, + "step": 1638400 + }, + { + "epoch": 0.01, + "learning_rate": 2.3166179997811793e-05, + "loss": 3.9039, + "step": 1638912 + }, + { + "epoch": 0.01, + "learning_rate": 2.3157794050301272e-05, + "loss": 3.902, + "step": 1639424 + }, + { + "epoch": 0.01, + "learning_rate": 2.3149408102790752e-05, + "loss": 3.9078, + "step": 1639936 + }, + { + "epoch": 0.01, + "learning_rate": 2.3141038534083965e-05, + "loss": 3.9066, + "step": 1640448 + }, + { + "epoch": 0.01, + "learning_rate": 2.3132652586573445e-05, + "loss": 3.9184, + "step": 1640960 + }, + { + "epoch": 0.01, + "learning_rate": 2.3124266639062925e-05, + "loss": 3.8893, + "step": 1641472 + }, + { + "epoch": 0.01, + "learning_rate": 2.3115880691552405e-05, + "loss": 3.9053, + "step": 1641984 + }, + { + "epoch": 0.01, + "learning_rate": 2.310749474404188e-05, + "loss": 3.9075, + "step": 1642496 + }, + { + "epoch": 0.01, + "learning_rate": 2.309910879653136e-05, + "loss": 3.8859, + "step": 1643008 + }, + { + "epoch": 0.01, + "learning_rate": 2.3090722849020845e-05, + "loss": 3.9072, + "step": 1643520 + }, + { + "epoch": 0.01, + "learning_rate": 2.3082336901510325e-05, + "loss": 3.9031, + "step": 1644032 + }, + { + "epoch": 0.01, + "learning_rate": 2.3073967332803534e-05, + "loss": 3.9074, + "step": 1644544 + }, + { + "epoch": 0.01, + "learning_rate": 2.3065581385293014e-05, + "loss": 3.9092, + "step": 1645056 + }, + { + "epoch": 0.01, + "learning_rate": 2.3057195437782494e-05, + "loss": 3.8926, + "step": 1645568 + }, + { + "epoch": 0.01, + "learning_rate": 2.3048809490271974e-05, + "loss": 3.898, + "step": 1646080 + }, + { + "epoch": 0.01, + "learning_rate": 2.3040423542761454e-05, + "loss": 3.9008, + "step": 1646592 + }, + { + "epoch": 0.01, + "learning_rate": 2.3032037595250937e-05, + "loss": 3.9091, + "step": 1647104 + }, + { + "epoch": 0.01, + "learning_rate": 2.3023651647740413e-05, + "loss": 3.8991, + "step": 1647616 + }, + { + "epoch": 0.01, + "learning_rate": 2.3015282079033626e-05, + "loss": 3.9109, + "step": 1648128 + }, + { + "epoch": 0.02, + "learning_rate": 2.3006896131523106e-05, + "loss": 3.9134, + "step": 1648640 + }, + { + "epoch": 0.02, + "learning_rate": 2.2998526562816315e-05, + "loss": 3.898, + "step": 1649152 + }, + { + "epoch": 0.02, + "learning_rate": 2.29901406153058e-05, + "loss": 3.9046, + "step": 1649664 + }, + { + "epoch": 0.02, + "learning_rate": 2.2981754667795278e-05, + "loss": 3.8959, + "step": 1650176 + }, + { + "epoch": 0.02, + "learning_rate": 2.2973368720284758e-05, + "loss": 3.9081, + "step": 1650688 + }, + { + "epoch": 0.02, + "learning_rate": 2.2964982772774235e-05, + "loss": 3.9189, + "step": 1651200 + }, + { + "epoch": 0.02, + "learning_rate": 2.2956596825263715e-05, + "loss": 3.8974, + "step": 1651712 + }, + { + "epoch": 0.02, + "learning_rate": 2.2948210877753195e-05, + "loss": 3.8984, + "step": 1652224 + }, + { + "epoch": 0.02, + "learning_rate": 2.2939824930242675e-05, + "loss": 3.8945, + "step": 1652736 + }, + { + "epoch": 0.02, + "learning_rate": 2.2931438982732155e-05, + "loss": 3.9077, + "step": 1653248 + }, + { + "epoch": 0.02, + "learning_rate": 2.2923069414025367e-05, + "loss": 3.9154, + "step": 1653760 + }, + { + "epoch": 0.02, + "learning_rate": 2.2914683466514847e-05, + "loss": 3.8993, + "step": 1654272 + }, + { + "epoch": 0.02, + "learning_rate": 2.2906297519004327e-05, + "loss": 3.896, + "step": 1654784 + }, + { + "epoch": 0.02, + "learning_rate": 2.2897911571493807e-05, + "loss": 3.8884, + "step": 1655296 + }, + { + "epoch": 0.02, + "learning_rate": 2.2889542002787016e-05, + "loss": 3.9111, + "step": 1655808 + }, + { + "epoch": 0.02, + "learning_rate": 2.28811560552765e-05, + "loss": 3.8844, + "step": 1656320 + }, + { + "epoch": 0.02, + "learning_rate": 2.287277010776598e-05, + "loss": 3.8989, + "step": 1656832 + }, + { + "epoch": 0.02, + "learning_rate": 2.286438416025546e-05, + "loss": 3.898, + "step": 1657344 + }, + { + "epoch": 0.02, + "learning_rate": 2.285599821274494e-05, + "loss": 3.9024, + "step": 1657856 + }, + { + "epoch": 0.02, + "learning_rate": 2.2847612265234416e-05, + "loss": 3.8949, + "step": 1658368 + }, + { + "epoch": 0.02, + "learning_rate": 2.2839226317723896e-05, + "loss": 3.9045, + "step": 1658880 + }, + { + "epoch": 0.02, + "learning_rate": 2.2830840370213376e-05, + "loss": 3.9003, + "step": 1659392 + }, + { + "epoch": 0.02, + "learning_rate": 2.282245442270286e-05, + "loss": 3.8964, + "step": 1659904 + }, + { + "epoch": 0.02, + "learning_rate": 2.2814084853996068e-05, + "loss": 3.9019, + "step": 1660416 + }, + { + "epoch": 0.02, + "learning_rate": 2.280571528528928e-05, + "loss": 3.9023, + "step": 1660928 + }, + { + "epoch": 0.02, + "learning_rate": 2.279732933777876e-05, + "loss": 3.9066, + "step": 1661440 + }, + { + "epoch": 0.02, + "learning_rate": 2.2788943390268237e-05, + "loss": 3.9108, + "step": 1661952 + }, + { + "epoch": 0.02, + "learning_rate": 2.2780573821561453e-05, + "loss": 3.9003, + "step": 1662464 + }, + { + "epoch": 0.02, + "learning_rate": 2.2772187874050933e-05, + "loss": 3.8937, + "step": 1662976 + }, + { + "epoch": 0.02, + "learning_rate": 2.2763801926540413e-05, + "loss": 3.8993, + "step": 1663488 + }, + { + "epoch": 0.02, + "learning_rate": 2.275541597902989e-05, + "loss": 3.9037, + "step": 1664000 + }, + { + "epoch": 0.02, + "learning_rate": 2.274703003151937e-05, + "loss": 3.8908, + "step": 1664512 + }, + { + "epoch": 0.02, + "learning_rate": 2.273864408400885e-05, + "loss": 3.9019, + "step": 1665024 + }, + { + "epoch": 0.02, + "learning_rate": 2.273025813649833e-05, + "loss": 3.8892, + "step": 1665536 + }, + { + "epoch": 0.02, + "learning_rate": 2.2721872188987813e-05, + "loss": 3.9035, + "step": 1666048 + }, + { + "epoch": 0.02, + "learning_rate": 2.2713486241477293e-05, + "loss": 3.8989, + "step": 1666560 + }, + { + "epoch": 0.02, + "learning_rate": 2.2705116672770502e-05, + "loss": 3.9014, + "step": 1667072 + }, + { + "epoch": 0.02, + "learning_rate": 2.2696730725259982e-05, + "loss": 3.889, + "step": 1667584 + }, + { + "epoch": 0.02, + "learning_rate": 2.2688344777749462e-05, + "loss": 3.8961, + "step": 1668096 + }, + { + "epoch": 0.02, + "learning_rate": 2.2679975209042674e-05, + "loss": 3.9006, + "step": 1668608 + }, + { + "epoch": 0.02, + "learning_rate": 2.2671589261532154e-05, + "loss": 3.9084, + "step": 1669120 + }, + { + "epoch": 0.02, + "learning_rate": 2.2663203314021634e-05, + "loss": 3.9009, + "step": 1669632 + }, + { + "epoch": 0.02, + "learning_rate": 2.2654817366511114e-05, + "loss": 3.9087, + "step": 1670144 + }, + { + "epoch": 0.02, + "learning_rate": 2.2646431419000594e-05, + "loss": 3.8925, + "step": 1670656 + }, + { + "epoch": 0.02, + "learning_rate": 2.263804547149007e-05, + "loss": 3.9036, + "step": 1671168 + }, + { + "epoch": 0.02, + "learning_rate": 2.262965952397955e-05, + "loss": 3.9114, + "step": 1671680 + }, + { + "epoch": 0.02, + "learning_rate": 2.262127357646903e-05, + "loss": 3.908, + "step": 1672192 + }, + { + "epoch": 0.02, + "learning_rate": 2.2612904007762246e-05, + "loss": 3.9061, + "step": 1672704 + }, + { + "epoch": 0.02, + "learning_rate": 2.2604518060251723e-05, + "loss": 3.9127, + "step": 1673216 + }, + { + "epoch": 0.02, + "learning_rate": 2.2596132112741203e-05, + "loss": 3.9002, + "step": 1673728 + }, + { + "epoch": 0.02, + "learning_rate": 2.2587746165230683e-05, + "loss": 3.909, + "step": 1674240 + }, + { + "epoch": 0.02, + "learning_rate": 2.2579360217720163e-05, + "loss": 3.8904, + "step": 1674752 + }, + { + "epoch": 0.02, + "learning_rate": 2.2570974270209643e-05, + "loss": 3.9036, + "step": 1675264 + }, + { + "epoch": 0.02, + "learning_rate": 2.2562604701502855e-05, + "loss": 3.8974, + "step": 1675776 + }, + { + "epoch": 0.02, + "learning_rate": 2.2554218753992335e-05, + "loss": 3.8966, + "step": 1676288 + }, + { + "epoch": 0.02, + "learning_rate": 2.2545832806481815e-05, + "loss": 3.8996, + "step": 1676800 + }, + { + "epoch": 0.02, + "learning_rate": 2.2537446858971295e-05, + "loss": 3.8956, + "step": 1677312 + }, + { + "epoch": 0.02, + "learning_rate": 2.2529060911460775e-05, + "loss": 3.9086, + "step": 1677824 + }, + { + "epoch": 0.02, + "learning_rate": 2.252067496395025e-05, + "loss": 3.8873, + "step": 1678336 + }, + { + "epoch": 0.02, + "learning_rate": 2.2512305395243468e-05, + "loss": 3.9106, + "step": 1678848 + }, + { + "epoch": 0.03, + "eval_loss": 3.992438316345215, + "eval_runtime": 284.7379, + "eval_samples_per_second": 1340.148, + "eval_steps_per_second": 41.881, + "step": 1679040 + }, + { + "epoch": 1.0, + "learning_rate": 2.2503919447732948e-05, + "loss": 3.8956, + "step": 1679360 + }, + { + "epoch": 1.0, + "learning_rate": 2.2495533500222427e-05, + "loss": 3.8928, + "step": 1679872 + }, + { + "epoch": 1.0, + "learning_rate": 2.2487147552711904e-05, + "loss": 3.9049, + "step": 1680384 + }, + { + "epoch": 1.0, + "learning_rate": 2.2478761605201384e-05, + "loss": 3.9018, + "step": 1680896 + }, + { + "epoch": 1.0, + "learning_rate": 2.2470375657690864e-05, + "loss": 3.9058, + "step": 1681408 + }, + { + "epoch": 1.0, + "learning_rate": 2.2461989710180344e-05, + "loss": 3.8934, + "step": 1681920 + }, + { + "epoch": 1.0, + "learning_rate": 2.2453620141473556e-05, + "loss": 3.887, + "step": 1682432 + }, + { + "epoch": 1.0, + "learning_rate": 2.2445234193963036e-05, + "loss": 3.8958, + "step": 1682944 + }, + { + "epoch": 1.0, + "learning_rate": 2.2436848246452516e-05, + "loss": 3.8996, + "step": 1683456 + }, + { + "epoch": 1.0, + "learning_rate": 2.2428462298941996e-05, + "loss": 3.9065, + "step": 1683968 + }, + { + "epoch": 1.0, + "learning_rate": 2.2420076351431476e-05, + "loss": 3.9002, + "step": 1684480 + }, + { + "epoch": 1.0, + "learning_rate": 2.2411690403920956e-05, + "loss": 3.9065, + "step": 1684992 + }, + { + "epoch": 1.0, + "learning_rate": 2.2403304456410433e-05, + "loss": 3.8927, + "step": 1685504 + }, + { + "epoch": 1.0, + "learning_rate": 2.239493488770365e-05, + "loss": 3.8914, + "step": 1686016 + }, + { + "epoch": 1.0, + "learning_rate": 2.238654894019313e-05, + "loss": 3.9008, + "step": 1686528 + }, + { + "epoch": 1.0, + "learning_rate": 2.237816299268261e-05, + "loss": 3.8869, + "step": 1687040 + }, + { + "epoch": 1.0, + "learning_rate": 2.2369777045172085e-05, + "loss": 3.8949, + "step": 1687552 + }, + { + "epoch": 1.0, + "learning_rate": 2.2361391097661565e-05, + "loss": 3.8991, + "step": 1688064 + }, + { + "epoch": 1.0, + "learning_rate": 2.2353005150151045e-05, + "loss": 3.8917, + "step": 1688576 + }, + { + "epoch": 1.0, + "learning_rate": 2.234465196024799e-05, + "loss": 3.919, + "step": 1689088 + }, + { + "epoch": 1.0, + "learning_rate": 2.233626601273747e-05, + "loss": 3.9076, + "step": 1689600 + }, + { + "epoch": 1.0, + "learning_rate": 2.232788006522695e-05, + "loss": 3.8983, + "step": 1690112 + }, + { + "epoch": 1.0, + "learning_rate": 2.231949411771643e-05, + "loss": 3.9058, + "step": 1690624 + }, + { + "epoch": 1.0, + "learning_rate": 2.231112454900964e-05, + "loss": 3.9119, + "step": 1691136 + }, + { + "epoch": 1.0, + "learning_rate": 2.2302738601499122e-05, + "loss": 3.8918, + "step": 1691648 + }, + { + "epoch": 1.0, + "learning_rate": 2.2294352653988602e-05, + "loss": 3.9023, + "step": 1692160 + }, + { + "epoch": 1.0, + "learning_rate": 2.2285966706478082e-05, + "loss": 3.8957, + "step": 1692672 + }, + { + "epoch": 1.0, + "learning_rate": 2.227758075896756e-05, + "loss": 3.8945, + "step": 1693184 + }, + { + "epoch": 1.0, + "learning_rate": 2.226919481145704e-05, + "loss": 3.8924, + "step": 1693696 + }, + { + "epoch": 1.0, + "learning_rate": 2.226080886394652e-05, + "loss": 3.9009, + "step": 1694208 + }, + { + "epoch": 1.01, + "learning_rate": 2.2252422916436e-05, + "loss": 3.9092, + "step": 1694720 + }, + { + "epoch": 1.01, + "learning_rate": 2.224403696892548e-05, + "loss": 3.9007, + "step": 1695232 + }, + { + "epoch": 1.01, + "learning_rate": 2.2235651021414962e-05, + "loss": 3.9072, + "step": 1695744 + }, + { + "epoch": 1.01, + "learning_rate": 2.222726507390444e-05, + "loss": 3.9068, + "step": 1696256 + }, + { + "epoch": 1.01, + "learning_rate": 2.221889550519765e-05, + "loss": 3.8969, + "step": 1696768 + }, + { + "epoch": 1.01, + "learning_rate": 2.221050955768713e-05, + "loss": 3.903, + "step": 1697280 + }, + { + "epoch": 1.01, + "learning_rate": 2.220212361017661e-05, + "loss": 3.894, + "step": 1697792 + }, + { + "epoch": 1.01, + "learning_rate": 2.219373766266609e-05, + "loss": 3.8943, + "step": 1698304 + }, + { + "epoch": 1.01, + "learning_rate": 2.218535171515557e-05, + "loss": 3.8897, + "step": 1698816 + }, + { + "epoch": 1.01, + "learning_rate": 2.217696576764505e-05, + "loss": 3.89, + "step": 1699328 + }, + { + "epoch": 1.01, + "learning_rate": 2.216857982013453e-05, + "loss": 3.8993, + "step": 1699840 + }, + { + "epoch": 1.01, + "learning_rate": 2.216019387262401e-05, + "loss": 3.902, + "step": 1700352 + }, + { + "epoch": 1.01, + "learning_rate": 2.215180792511349e-05, + "loss": 3.8951, + "step": 1700864 + }, + { + "epoch": 1.01, + "learning_rate": 2.2143421977602967e-05, + "loss": 3.8954, + "step": 1701376 + }, + { + "epoch": 1.01, + "learning_rate": 2.2135036030092447e-05, + "loss": 3.9062, + "step": 1701888 + }, + { + "epoch": 1.01, + "learning_rate": 2.2126666461385663e-05, + "loss": 3.897, + "step": 1702400 + }, + { + "epoch": 1.01, + "learning_rate": 2.2118280513875143e-05, + "loss": 3.9023, + "step": 1702912 + }, + { + "epoch": 1.01, + "learning_rate": 2.210989456636462e-05, + "loss": 3.894, + "step": 1703424 + }, + { + "epoch": 1.01, + "learning_rate": 2.21015086188541e-05, + "loss": 3.8792, + "step": 1703936 + }, + { + "epoch": 1.01, + "learning_rate": 2.209312267134358e-05, + "loss": 3.9089, + "step": 1704448 + }, + { + "epoch": 1.01, + "learning_rate": 2.208473672383306e-05, + "loss": 3.8937, + "step": 1704960 + }, + { + "epoch": 1.01, + "learning_rate": 2.207635077632254e-05, + "loss": 3.902, + "step": 1705472 + }, + { + "epoch": 1.01, + "learning_rate": 2.2067964828812023e-05, + "loss": 3.8934, + "step": 1705984 + }, + { + "epoch": 1.01, + "learning_rate": 2.2059595260105232e-05, + "loss": 3.8913, + "step": 1706496 + }, + { + "epoch": 1.01, + "learning_rate": 2.2051209312594712e-05, + "loss": 3.8875, + "step": 1707008 + }, + { + "epoch": 1.01, + "learning_rate": 2.2042823365084192e-05, + "loss": 3.9002, + "step": 1707520 + }, + { + "epoch": 1.01, + "learning_rate": 2.20344537963774e-05, + "loss": 3.8875, + "step": 1708032 + }, + { + "epoch": 1.01, + "learning_rate": 2.2026067848866884e-05, + "loss": 3.8964, + "step": 1708544 + }, + { + "epoch": 1.01, + "learning_rate": 2.2017681901356364e-05, + "loss": 3.9046, + "step": 1709056 + }, + { + "epoch": 1.01, + "learning_rate": 2.2009295953845844e-05, + "loss": 3.8859, + "step": 1709568 + }, + { + "epoch": 1.01, + "learning_rate": 2.2000910006335324e-05, + "loss": 3.8881, + "step": 1710080 + }, + { + "epoch": 1.01, + "learning_rate": 2.19925240588248e-05, + "loss": 3.9067, + "step": 1710592 + }, + { + "epoch": 1.01, + "learning_rate": 2.1984154490118013e-05, + "loss": 3.876, + "step": 1711104 + }, + { + "epoch": 1.01, + "learning_rate": 2.1975768542607493e-05, + "loss": 3.8806, + "step": 1711616 + }, + { + "epoch": 1.01, + "learning_rate": 2.1967382595096976e-05, + "loss": 3.8971, + "step": 1712128 + }, + { + "epoch": 1.01, + "learning_rate": 2.1958996647586453e-05, + "loss": 3.8965, + "step": 1712640 + }, + { + "epoch": 1.01, + "learning_rate": 2.1950610700075933e-05, + "loss": 3.8863, + "step": 1713152 + }, + { + "epoch": 1.01, + "learning_rate": 2.1942224752565413e-05, + "loss": 3.8976, + "step": 1713664 + }, + { + "epoch": 1.01, + "learning_rate": 2.1933838805054893e-05, + "loss": 3.8764, + "step": 1714176 + }, + { + "epoch": 1.01, + "learning_rate": 2.1925452857544373e-05, + "loss": 3.8866, + "step": 1714688 + }, + { + "epoch": 1.01, + "learning_rate": 2.1917083288837585e-05, + "loss": 3.8978, + "step": 1715200 + }, + { + "epoch": 1.01, + "learning_rate": 2.1908697341327065e-05, + "loss": 3.8961, + "step": 1715712 + }, + { + "epoch": 1.01, + "learning_rate": 2.1900311393816545e-05, + "loss": 3.901, + "step": 1716224 + }, + { + "epoch": 1.01, + "learning_rate": 2.1891941825109754e-05, + "loss": 3.9018, + "step": 1716736 + }, + { + "epoch": 1.01, + "learning_rate": 2.1883555877599234e-05, + "loss": 3.9094, + "step": 1717248 + }, + { + "epoch": 1.01, + "learning_rate": 2.1875169930088714e-05, + "loss": 3.8837, + "step": 1717760 + }, + { + "epoch": 1.01, + "learning_rate": 2.1866800361381927e-05, + "loss": 3.8968, + "step": 1718272 + }, + { + "epoch": 1.01, + "learning_rate": 2.1858414413871407e-05, + "loss": 3.9001, + "step": 1718784 + }, + { + "epoch": 1.01, + "learning_rate": 2.1850028466360887e-05, + "loss": 3.8793, + "step": 1719296 + }, + { + "epoch": 1.01, + "learning_rate": 2.1841642518850367e-05, + "loss": 3.8994, + "step": 1719808 + }, + { + "epoch": 1.01, + "learning_rate": 2.1833256571339846e-05, + "loss": 3.8968, + "step": 1720320 + }, + { + "epoch": 1.01, + "learning_rate": 2.1824870623829326e-05, + "loss": 3.9017, + "step": 1720832 + }, + { + "epoch": 1.01, + "learning_rate": 2.1816484676318803e-05, + "loss": 3.9015, + "step": 1721344 + }, + { + "epoch": 1.01, + "learning_rate": 2.1808098728808286e-05, + "loss": 3.8879, + "step": 1721856 + }, + { + "epoch": 1.01, + "learning_rate": 2.1799712781297766e-05, + "loss": 3.8894, + "step": 1722368 + }, + { + "epoch": 1.01, + "learning_rate": 2.1791326833787246e-05, + "loss": 3.8951, + "step": 1722880 + }, + { + "epoch": 1.01, + "learning_rate": 2.1782940886276726e-05, + "loss": 3.8987, + "step": 1723392 + }, + { + "epoch": 1.01, + "learning_rate": 2.1774571317569935e-05, + "loss": 3.8967, + "step": 1723904 + }, + { + "epoch": 1.01, + "learning_rate": 2.1766185370059415e-05, + "loss": 3.9041, + "step": 1724416 + }, + { + "epoch": 1.02, + "learning_rate": 2.1757799422548895e-05, + "loss": 3.9043, + "step": 1724928 + }, + { + "epoch": 1.02, + "learning_rate": 2.174941347503838e-05, + "loss": 3.8936, + "step": 1725440 + }, + { + "epoch": 1.02, + "learning_rate": 2.174102752752786e-05, + "loss": 3.8938, + "step": 1725952 + }, + { + "epoch": 1.02, + "learning_rate": 2.1732657958821068e-05, + "loss": 3.8869, + "step": 1726464 + }, + { + "epoch": 1.02, + "learning_rate": 2.1724272011310548e-05, + "loss": 3.9083, + "step": 1726976 + }, + { + "epoch": 1.02, + "learning_rate": 2.1715886063800028e-05, + "loss": 3.9071, + "step": 1727488 + }, + { + "epoch": 1.02, + "learning_rate": 2.1707500116289507e-05, + "loss": 3.893, + "step": 1728000 + }, + { + "epoch": 1.02, + "learning_rate": 2.169913054758272e-05, + "loss": 3.8907, + "step": 1728512 + }, + { + "epoch": 1.02, + "learning_rate": 2.16907446000722e-05, + "loss": 3.8867, + "step": 1729024 + }, + { + "epoch": 1.02, + "learning_rate": 2.168235865256168e-05, + "loss": 3.9024, + "step": 1729536 + }, + { + "epoch": 1.02, + "learning_rate": 2.167397270505116e-05, + "loss": 3.9066, + "step": 1730048 + }, + { + "epoch": 1.02, + "learning_rate": 2.1665586757540636e-05, + "loss": 3.8929, + "step": 1730560 + }, + { + "epoch": 1.02, + "learning_rate": 2.1657200810030116e-05, + "loss": 3.8914, + "step": 1731072 + }, + { + "epoch": 1.02, + "learning_rate": 2.1648814862519596e-05, + "loss": 3.8857, + "step": 1731584 + }, + { + "epoch": 1.02, + "learning_rate": 2.164044529381281e-05, + "loss": 3.9001, + "step": 1732096 + }, + { + "epoch": 1.02, + "learning_rate": 2.163205934630229e-05, + "loss": 3.8814, + "step": 1732608 + }, + { + "epoch": 1.02, + "learning_rate": 2.162367339879177e-05, + "loss": 3.8929, + "step": 1733120 + }, + { + "epoch": 1.02, + "learning_rate": 2.161528745128125e-05, + "loss": 3.8856, + "step": 1733632 + }, + { + "epoch": 1.02, + "learning_rate": 2.160691788257446e-05, + "loss": 3.9006, + "step": 1734144 + }, + { + "epoch": 1.02, + "learning_rate": 2.159853193506394e-05, + "loss": 3.89, + "step": 1734656 + }, + { + "epoch": 1.02, + "learning_rate": 2.1590162366357154e-05, + "loss": 3.898, + "step": 1735168 + }, + { + "epoch": 1.02, + "learning_rate": 2.1581776418846634e-05, + "loss": 3.8947, + "step": 1735680 + }, + { + "epoch": 1.02, + "learning_rate": 2.157339047133611e-05, + "loss": 3.8872, + "step": 1736192 + }, + { + "epoch": 1.02, + "learning_rate": 2.156500452382559e-05, + "loss": 3.8975, + "step": 1736704 + }, + { + "epoch": 1.02, + "learning_rate": 2.155661857631507e-05, + "loss": 3.8948, + "step": 1737216 + }, + { + "epoch": 1.02, + "learning_rate": 2.154823262880455e-05, + "loss": 3.8987, + "step": 1737728 + }, + { + "epoch": 1.02, + "learning_rate": 2.1539846681294033e-05, + "loss": 3.9046, + "step": 1738240 + }, + { + "epoch": 1.02, + "learning_rate": 2.1531460733783513e-05, + "loss": 3.8909, + "step": 1738752 + }, + { + "epoch": 1.02, + "learning_rate": 2.152307478627299e-05, + "loss": 3.8942, + "step": 1739264 + }, + { + "epoch": 1.02, + "learning_rate": 2.151468883876247e-05, + "loss": 3.8886, + "step": 1739776 + }, + { + "epoch": 1.02, + "learning_rate": 2.150630289125195e-05, + "loss": 3.8981, + "step": 1740288 + }, + { + "epoch": 1.02, + "learning_rate": 2.149791694374143e-05, + "loss": 3.8918, + "step": 1740800 + }, + { + "epoch": 1.02, + "learning_rate": 2.148953099623091e-05, + "loss": 3.8925, + "step": 1741312 + }, + { + "epoch": 1.02, + "learning_rate": 2.1481145048720393e-05, + "loss": 3.8807, + "step": 1741824 + }, + { + "epoch": 1.02, + "learning_rate": 2.1472775480013602e-05, + "loss": 3.8964, + "step": 1742336 + }, + { + "epoch": 1.02, + "learning_rate": 2.1464389532503082e-05, + "loss": 3.8883, + "step": 1742848 + }, + { + "epoch": 1.02, + "learning_rate": 2.1456003584992562e-05, + "loss": 3.898, + "step": 1743360 + }, + { + "epoch": 1.02, + "learning_rate": 2.1447617637482042e-05, + "loss": 3.8805, + "step": 1743872 + }, + { + "epoch": 1.02, + "learning_rate": 2.1439248068775254e-05, + "loss": 3.8934, + "step": 1744384 + }, + { + "epoch": 1.02, + "learning_rate": 2.1430862121264734e-05, + "loss": 3.8905, + "step": 1744896 + }, + { + "epoch": 1.02, + "learning_rate": 2.1422476173754214e-05, + "loss": 3.9065, + "step": 1745408 + }, + { + "epoch": 1.02, + "learning_rate": 2.1414090226243694e-05, + "loss": 3.8939, + "step": 1745920 + }, + { + "epoch": 1.02, + "learning_rate": 2.140570427873317e-05, + "loss": 3.9023, + "step": 1746432 + }, + { + "epoch": 1.02, + "learning_rate": 2.1397334710026383e-05, + "loss": 3.8863, + "step": 1746944 + }, + { + "epoch": 1.02, + "learning_rate": 2.1388948762515863e-05, + "loss": 3.9009, + "step": 1747456 + }, + { + "epoch": 1.02, + "learning_rate": 2.1380562815005343e-05, + "loss": 3.903, + "step": 1747968 + }, + { + "epoch": 1.02, + "learning_rate": 2.1372176867494823e-05, + "loss": 3.9016, + "step": 1748480 + }, + { + "epoch": 1.02, + "learning_rate": 2.1363790919984303e-05, + "loss": 3.8989, + "step": 1748992 + }, + { + "epoch": 1.02, + "learning_rate": 2.1355404972473783e-05, + "loss": 3.9046, + "step": 1749504 + }, + { + "epoch": 1.02, + "learning_rate": 2.1347019024963263e-05, + "loss": 3.893, + "step": 1750016 + }, + { + "epoch": 1.02, + "learning_rate": 2.1338633077452743e-05, + "loss": 3.9046, + "step": 1750528 + }, + { + "epoch": 1.02, + "learning_rate": 2.1330247129942223e-05, + "loss": 3.8849, + "step": 1751040 + }, + { + "epoch": 1.02, + "learning_rate": 2.1321861182431703e-05, + "loss": 3.9003, + "step": 1751552 + }, + { + "epoch": 1.02, + "learning_rate": 2.1313475234921183e-05, + "loss": 3.8872, + "step": 1752064 + }, + { + "epoch": 1.02, + "learning_rate": 2.1305089287410663e-05, + "loss": 3.8939, + "step": 1752576 + }, + { + "epoch": 1.02, + "learning_rate": 2.1296719718703875e-05, + "loss": 3.8884, + "step": 1753088 + }, + { + "epoch": 1.02, + "learning_rate": 2.1288333771193352e-05, + "loss": 3.8862, + "step": 1753600 + }, + { + "epoch": 1.02, + "learning_rate": 2.1279947823682832e-05, + "loss": 3.9005, + "step": 1754112 + }, + { + "epoch": 1.02, + "learning_rate": 2.1271578254976048e-05, + "loss": 3.8836, + "step": 1754624 + }, + { + "epoch": 1.02, + "learning_rate": 2.1263192307465528e-05, + "loss": 3.9078, + "step": 1755136 + }, + { + "epoch": 1.03, + "eval_loss": 3.9898898601531982, + "eval_runtime": 287.0468, + "eval_samples_per_second": 1329.369, + "eval_steps_per_second": 41.544, + "step": 1755360 + }, + { + "epoch": 0.0, + "learning_rate": 2.1254806359955004e-05, + "loss": 3.888, + "step": 1755648 + }, + { + "epoch": 0.0, + "learning_rate": 2.1246420412444484e-05, + "loss": 3.8832, + "step": 1756160 + }, + { + "epoch": 0.0, + "learning_rate": 2.1238034464933964e-05, + "loss": 3.8943, + "step": 1756672 + }, + { + "epoch": 0.0, + "learning_rate": 2.1229648517423444e-05, + "loss": 3.8956, + "step": 1757184 + }, + { + "epoch": 0.0, + "learning_rate": 2.1221262569912924e-05, + "loss": 3.8954, + "step": 1757696 + }, + { + "epoch": 0.0, + "learning_rate": 2.1212876622402404e-05, + "loss": 3.8923, + "step": 1758208 + }, + { + "epoch": 0.0, + "learning_rate": 2.1204490674891887e-05, + "loss": 3.8867, + "step": 1758720 + }, + { + "epoch": 0.0, + "learning_rate": 2.1196104727381364e-05, + "loss": 3.8879, + "step": 1759232 + }, + { + "epoch": 0.0, + "learning_rate": 2.1187718779870844e-05, + "loss": 3.8941, + "step": 1759744 + }, + { + "epoch": 0.0, + "learning_rate": 2.1179332832360324e-05, + "loss": 3.9017, + "step": 1760256 + }, + { + "epoch": 0.0, + "learning_rate": 2.1170946884849804e-05, + "loss": 3.8948, + "step": 1760768 + }, + { + "epoch": 0.0, + "learning_rate": 2.1162577316143013e-05, + "loss": 3.8933, + "step": 1761280 + }, + { + "epoch": 0.0, + "learning_rate": 2.1154191368632496e-05, + "loss": 3.8905, + "step": 1761792 + }, + { + "epoch": 0.0, + "learning_rate": 2.1145805421121976e-05, + "loss": 3.8845, + "step": 1762304 + }, + { + "epoch": 0.0, + "learning_rate": 2.1137419473611456e-05, + "loss": 3.891, + "step": 1762816 + }, + { + "epoch": 0.0, + "learning_rate": 2.1129033526100936e-05, + "loss": 3.8807, + "step": 1763328 + }, + { + "epoch": 0.0, + "learning_rate": 2.1120647578590416e-05, + "loss": 3.8895, + "step": 1763840 + }, + { + "epoch": 0.0, + "learning_rate": 2.1112261631079893e-05, + "loss": 3.8907, + "step": 1764352 + }, + { + "epoch": 0.0, + "learning_rate": 2.1103875683569373e-05, + "loss": 3.8854, + "step": 1764864 + }, + { + "epoch": 0.0, + "learning_rate": 2.1095489736058856e-05, + "loss": 3.9095, + "step": 1765376 + }, + { + "epoch": 0.0, + "learning_rate": 2.1087103788548336e-05, + "loss": 3.9037, + "step": 1765888 + }, + { + "epoch": 0.0, + "learning_rate": 2.1078717841037816e-05, + "loss": 3.8917, + "step": 1766400 + }, + { + "epoch": 0.0, + "learning_rate": 2.1070331893527296e-05, + "loss": 3.8972, + "step": 1766912 + }, + { + "epoch": 0.0, + "learning_rate": 2.1061945946016772e-05, + "loss": 3.9021, + "step": 1767424 + }, + { + "epoch": 0.0, + "learning_rate": 2.1053559998506252e-05, + "loss": 3.8854, + "step": 1767936 + }, + { + "epoch": 0.0, + "learning_rate": 2.1045190429799465e-05, + "loss": 3.8981, + "step": 1768448 + }, + { + "epoch": 0.0, + "learning_rate": 2.1036804482288945e-05, + "loss": 3.8921, + "step": 1768960 + }, + { + "epoch": 0.0, + "learning_rate": 2.1028418534778425e-05, + "loss": 3.8871, + "step": 1769472 + }, + { + "epoch": 0.0, + "learning_rate": 2.1020032587267905e-05, + "loss": 3.8835, + "step": 1769984 + }, + { + "epoch": 0.0, + "learning_rate": 2.1011646639757385e-05, + "loss": 3.8975, + "step": 1770496 + }, + { + "epoch": 0.01, + "learning_rate": 2.1003260692246865e-05, + "loss": 3.8984, + "step": 1771008 + }, + { + "epoch": 0.01, + "learning_rate": 2.0994874744736345e-05, + "loss": 3.8975, + "step": 1771520 + }, + { + "epoch": 0.01, + "learning_rate": 2.0986488797225825e-05, + "loss": 3.9011, + "step": 1772032 + }, + { + "epoch": 0.01, + "learning_rate": 2.0978119228519037e-05, + "loss": 3.8938, + "step": 1772544 + }, + { + "epoch": 0.01, + "learning_rate": 2.0969749659812246e-05, + "loss": 3.8918, + "step": 1773056 + }, + { + "epoch": 0.01, + "learning_rate": 2.0961363712301726e-05, + "loss": 3.8986, + "step": 1773568 + }, + { + "epoch": 0.01, + "learning_rate": 2.095299414359494e-05, + "loss": 3.8892, + "step": 1774080 + }, + { + "epoch": 0.01, + "learning_rate": 2.094460819608442e-05, + "loss": 3.884, + "step": 1774592 + }, + { + "epoch": 0.01, + "learning_rate": 2.09362222485739e-05, + "loss": 3.8845, + "step": 1775104 + }, + { + "epoch": 0.01, + "learning_rate": 2.092783630106338e-05, + "loss": 3.8862, + "step": 1775616 + }, + { + "epoch": 0.01, + "learning_rate": 2.091945035355286e-05, + "loss": 3.8902, + "step": 1776128 + }, + { + "epoch": 0.01, + "learning_rate": 2.091106440604234e-05, + "loss": 3.897, + "step": 1776640 + }, + { + "epoch": 0.01, + "learning_rate": 2.090267845853182e-05, + "loss": 3.8904, + "step": 1777152 + }, + { + "epoch": 0.01, + "learning_rate": 2.0894292511021298e-05, + "loss": 3.8877, + "step": 1777664 + }, + { + "epoch": 0.01, + "learning_rate": 2.0885906563510778e-05, + "loss": 3.8963, + "step": 1778176 + }, + { + "epoch": 0.01, + "learning_rate": 2.0877520616000258e-05, + "loss": 3.8944, + "step": 1778688 + }, + { + "epoch": 0.01, + "learning_rate": 2.0869134668489738e-05, + "loss": 3.8951, + "step": 1779200 + }, + { + "epoch": 0.01, + "learning_rate": 2.0860748720979218e-05, + "loss": 3.8926, + "step": 1779712 + }, + { + "epoch": 0.01, + "learning_rate": 2.0852379152272427e-05, + "loss": 3.8663, + "step": 1780224 + }, + { + "epoch": 0.01, + "learning_rate": 2.0843993204761907e-05, + "loss": 3.9059, + "step": 1780736 + }, + { + "epoch": 0.01, + "learning_rate": 2.0835607257251387e-05, + "loss": 3.8866, + "step": 1781248 + }, + { + "epoch": 0.01, + "learning_rate": 2.0827237688544603e-05, + "loss": 3.8978, + "step": 1781760 + }, + { + "epoch": 0.01, + "learning_rate": 2.081885174103408e-05, + "loss": 3.8851, + "step": 1782272 + }, + { + "epoch": 0.01, + "learning_rate": 2.081046579352356e-05, + "loss": 3.887, + "step": 1782784 + }, + { + "epoch": 0.01, + "learning_rate": 2.080207984601304e-05, + "loss": 3.8817, + "step": 1783296 + }, + { + "epoch": 0.01, + "learning_rate": 2.0793710277306252e-05, + "loss": 3.8929, + "step": 1783808 + }, + { + "epoch": 0.01, + "learning_rate": 2.078532432979573e-05, + "loss": 3.8832, + "step": 1784320 + }, + { + "epoch": 0.01, + "learning_rate": 2.0776938382285212e-05, + "loss": 3.8887, + "step": 1784832 + }, + { + "epoch": 0.01, + "learning_rate": 2.0768552434774692e-05, + "loss": 3.9001, + "step": 1785344 + }, + { + "epoch": 0.01, + "learning_rate": 2.0760166487264172e-05, + "loss": 3.8821, + "step": 1785856 + }, + { + "epoch": 0.01, + "learning_rate": 2.0751780539753652e-05, + "loss": 3.8779, + "step": 1786368 + }, + { + "epoch": 0.01, + "learning_rate": 2.074339459224313e-05, + "loss": 3.8974, + "step": 1786880 + }, + { + "epoch": 0.01, + "learning_rate": 2.0735008644732608e-05, + "loss": 3.8728, + "step": 1787392 + }, + { + "epoch": 0.01, + "learning_rate": 2.072663907602582e-05, + "loss": 3.8732, + "step": 1787904 + }, + { + "epoch": 0.01, + "learning_rate": 2.0718253128515304e-05, + "loss": 3.8906, + "step": 1788416 + }, + { + "epoch": 0.01, + "learning_rate": 2.0709867181004784e-05, + "loss": 3.89, + "step": 1788928 + }, + { + "epoch": 0.01, + "learning_rate": 2.070148123349426e-05, + "loss": 3.8821, + "step": 1789440 + }, + { + "epoch": 0.01, + "learning_rate": 2.0693111664787473e-05, + "loss": 3.8896, + "step": 1789952 + }, + { + "epoch": 0.01, + "learning_rate": 2.0684725717276953e-05, + "loss": 3.8694, + "step": 1790464 + }, + { + "epoch": 0.01, + "learning_rate": 2.0676356148570166e-05, + "loss": 3.8806, + "step": 1790976 + }, + { + "epoch": 0.01, + "learning_rate": 2.0667970201059645e-05, + "loss": 3.8925, + "step": 1791488 + }, + { + "epoch": 0.01, + "learning_rate": 2.0659584253549125e-05, + "loss": 3.887, + "step": 1792000 + }, + { + "epoch": 0.01, + "learning_rate": 2.0651198306038605e-05, + "loss": 3.8978, + "step": 1792512 + }, + { + "epoch": 0.01, + "learning_rate": 2.0642812358528082e-05, + "loss": 3.8953, + "step": 1793024 + }, + { + "epoch": 0.01, + "learning_rate": 2.0634426411017562e-05, + "loss": 3.9006, + "step": 1793536 + }, + { + "epoch": 0.01, + "learning_rate": 2.0626040463507042e-05, + "loss": 3.8775, + "step": 1794048 + }, + { + "epoch": 0.01, + "learning_rate": 2.0617654515996522e-05, + "loss": 3.8923, + "step": 1794560 + }, + { + "epoch": 0.01, + "learning_rate": 2.0609284947289734e-05, + "loss": 3.8918, + "step": 1795072 + }, + { + "epoch": 0.01, + "learning_rate": 2.0600898999779214e-05, + "loss": 3.8778, + "step": 1795584 + }, + { + "epoch": 0.01, + "learning_rate": 2.0592513052268694e-05, + "loss": 3.8899, + "step": 1796096 + }, + { + "epoch": 0.01, + "learning_rate": 2.0584127104758174e-05, + "loss": 3.8906, + "step": 1796608 + }, + { + "epoch": 0.01, + "learning_rate": 2.0575741157247654e-05, + "loss": 3.8946, + "step": 1797120 + }, + { + "epoch": 0.01, + "learning_rate": 2.0567355209737134e-05, + "loss": 3.8999, + "step": 1797632 + }, + { + "epoch": 0.01, + "learning_rate": 2.0558985641030347e-05, + "loss": 3.8788, + "step": 1798144 + }, + { + "epoch": 0.01, + "learning_rate": 2.0550599693519827e-05, + "loss": 3.8838, + "step": 1798656 + }, + { + "epoch": 0.01, + "learning_rate": 2.0542213746009306e-05, + "loss": 3.8907, + "step": 1799168 + }, + { + "epoch": 0.01, + "learning_rate": 2.0533827798498786e-05, + "loss": 3.8938, + "step": 1799680 + }, + { + "epoch": 0.01, + "learning_rate": 2.0525441850988263e-05, + "loss": 3.891, + "step": 1800192 + }, + { + "epoch": 0.01, + "learning_rate": 2.0517055903477743e-05, + "loss": 3.8927, + "step": 1800704 + }, + { + "epoch": 0.02, + "learning_rate": 2.050868633477096e-05, + "loss": 3.8973, + "step": 1801216 + }, + { + "epoch": 0.02, + "learning_rate": 2.050030038726044e-05, + "loss": 3.8919, + "step": 1801728 + }, + { + "epoch": 0.02, + "learning_rate": 2.0491914439749915e-05, + "loss": 3.8866, + "step": 1802240 + }, + { + "epoch": 0.02, + "learning_rate": 2.0483528492239395e-05, + "loss": 3.8804, + "step": 1802752 + }, + { + "epoch": 0.02, + "learning_rate": 2.0475142544728875e-05, + "loss": 3.8978, + "step": 1803264 + }, + { + "epoch": 0.02, + "learning_rate": 2.0466756597218355e-05, + "loss": 3.898, + "step": 1803776 + }, + { + "epoch": 0.02, + "learning_rate": 2.0458370649707835e-05, + "loss": 3.8888, + "step": 1804288 + }, + { + "epoch": 0.02, + "learning_rate": 2.045001745980478e-05, + "loss": 3.8835, + "step": 1804800 + }, + { + "epoch": 0.02, + "learning_rate": 2.044163151229426e-05, + "loss": 3.883, + "step": 1805312 + }, + { + "epoch": 0.02, + "learning_rate": 2.0433245564783737e-05, + "loss": 3.8919, + "step": 1805824 + }, + { + "epoch": 0.02, + "learning_rate": 2.0424859617273217e-05, + "loss": 3.9049, + "step": 1806336 + }, + { + "epoch": 0.02, + "learning_rate": 2.0416473669762697e-05, + "loss": 3.8858, + "step": 1806848 + }, + { + "epoch": 0.02, + "learning_rate": 2.0408087722252177e-05, + "loss": 3.8874, + "step": 1807360 + }, + { + "epoch": 0.02, + "learning_rate": 2.039971815354539e-05, + "loss": 3.8814, + "step": 1807872 + }, + { + "epoch": 0.02, + "learning_rate": 2.039133220603487e-05, + "loss": 3.8894, + "step": 1808384 + }, + { + "epoch": 0.02, + "learning_rate": 2.038294625852435e-05, + "loss": 3.8768, + "step": 1808896 + }, + { + "epoch": 0.02, + "learning_rate": 2.037456031101383e-05, + "loss": 3.8903, + "step": 1809408 + }, + { + "epoch": 0.02, + "learning_rate": 2.036619074230704e-05, + "loss": 3.8763, + "step": 1809920 + }, + { + "epoch": 0.02, + "learning_rate": 2.035780479479652e-05, + "loss": 3.8932, + "step": 1810432 + }, + { + "epoch": 0.02, + "learning_rate": 2.0349418847286e-05, + "loss": 3.8869, + "step": 1810944 + }, + { + "epoch": 0.02, + "learning_rate": 2.034103289977548e-05, + "loss": 3.8891, + "step": 1811456 + }, + { + "epoch": 0.02, + "learning_rate": 2.033264695226496e-05, + "loss": 3.8857, + "step": 1811968 + }, + { + "epoch": 0.02, + "learning_rate": 2.032426100475444e-05, + "loss": 3.888, + "step": 1812480 + }, + { + "epoch": 0.02, + "learning_rate": 2.0315875057243918e-05, + "loss": 3.8897, + "step": 1812992 + }, + { + "epoch": 0.02, + "learning_rate": 2.0307489109733398e-05, + "loss": 3.8897, + "step": 1813504 + }, + { + "epoch": 0.02, + "learning_rate": 2.029910316222288e-05, + "loss": 3.8911, + "step": 1814016 + }, + { + "epoch": 0.02, + "learning_rate": 2.029071721471236e-05, + "loss": 3.8996, + "step": 1814528 + }, + { + "epoch": 0.02, + "learning_rate": 2.028234764600557e-05, + "loss": 3.883, + "step": 1815040 + }, + { + "epoch": 0.02, + "learning_rate": 2.027396169849505e-05, + "loss": 3.8888, + "step": 1815552 + }, + { + "epoch": 0.02, + "learning_rate": 2.026557575098453e-05, + "loss": 3.8821, + "step": 1816064 + }, + { + "epoch": 0.02, + "learning_rate": 2.025718980347401e-05, + "loss": 3.8886, + "step": 1816576 + }, + { + "epoch": 0.02, + "learning_rate": 2.024880385596349e-05, + "loss": 3.8854, + "step": 1817088 + }, + { + "epoch": 0.02, + "learning_rate": 2.0240434287256702e-05, + "loss": 3.8856, + "step": 1817600 + }, + { + "epoch": 0.02, + "learning_rate": 2.0232048339746182e-05, + "loss": 3.8772, + "step": 1818112 + }, + { + "epoch": 0.02, + "learning_rate": 2.0223662392235662e-05, + "loss": 3.8861, + "step": 1818624 + }, + { + "epoch": 0.02, + "learning_rate": 2.0215276444725142e-05, + "loss": 3.8861, + "step": 1819136 + }, + { + "epoch": 0.02, + "learning_rate": 2.0206890497214622e-05, + "loss": 3.8883, + "step": 1819648 + }, + { + "epoch": 0.02, + "learning_rate": 2.01985045497041e-05, + "loss": 3.8704, + "step": 1820160 + }, + { + "epoch": 0.02, + "learning_rate": 2.0190118602193582e-05, + "loss": 3.892, + "step": 1820672 + }, + { + "epoch": 0.02, + "learning_rate": 2.0181749033486795e-05, + "loss": 3.8828, + "step": 1821184 + }, + { + "epoch": 0.02, + "learning_rate": 2.0173363085976275e-05, + "loss": 3.8977, + "step": 1821696 + }, + { + "epoch": 0.02, + "learning_rate": 2.016497713846575e-05, + "loss": 3.8895, + "step": 1822208 + }, + { + "epoch": 0.02, + "learning_rate": 2.015659119095523e-05, + "loss": 3.8943, + "step": 1822720 + }, + { + "epoch": 0.02, + "learning_rate": 2.014820524344471e-05, + "loss": 3.8808, + "step": 1823232 + }, + { + "epoch": 0.02, + "learning_rate": 2.0139835674737924e-05, + "loss": 3.8957, + "step": 1823744 + }, + { + "epoch": 0.02, + "learning_rate": 2.0131449727227404e-05, + "loss": 3.8957, + "step": 1824256 + }, + { + "epoch": 0.02, + "learning_rate": 2.0123063779716883e-05, + "loss": 3.8945, + "step": 1824768 + }, + { + "epoch": 0.02, + "learning_rate": 2.0114694211010096e-05, + "loss": 3.8958, + "step": 1825280 + }, + { + "epoch": 0.02, + "learning_rate": 2.0106308263499573e-05, + "loss": 3.8952, + "step": 1825792 + }, + { + "epoch": 0.02, + "learning_rate": 2.0097938694792785e-05, + "loss": 3.8885, + "step": 1826304 + }, + { + "epoch": 0.02, + "learning_rate": 2.008955274728227e-05, + "loss": 3.8971, + "step": 1826816 + }, + { + "epoch": 0.02, + "learning_rate": 2.0081166799771748e-05, + "loss": 3.8783, + "step": 1827328 + }, + { + "epoch": 0.02, + "learning_rate": 2.0072780852261225e-05, + "loss": 3.8941, + "step": 1827840 + }, + { + "epoch": 0.02, + "learning_rate": 2.0064394904750705e-05, + "loss": 3.8823, + "step": 1828352 + }, + { + "epoch": 0.02, + "learning_rate": 2.0056008957240185e-05, + "loss": 3.8902, + "step": 1828864 + }, + { + "epoch": 0.02, + "learning_rate": 2.0047623009729665e-05, + "loss": 3.8786, + "step": 1829376 + }, + { + "epoch": 0.02, + "learning_rate": 2.0039237062219145e-05, + "loss": 3.8827, + "step": 1829888 + }, + { + "epoch": 0.02, + "learning_rate": 2.0030851114708628e-05, + "loss": 3.8885, + "step": 1830400 + }, + { + "epoch": 0.02, + "learning_rate": 2.0022465167198105e-05, + "loss": 3.8804, + "step": 1830912 + }, + { + "epoch": 0.02, + "learning_rate": 2.0014079219687585e-05, + "loss": 3.9025, + "step": 1831424 + }, + { + "epoch": 0.03, + "eval_loss": 3.9875099658966064, + "eval_runtime": 309.8709, + "eval_samples_per_second": 1231.452, + "eval_steps_per_second": 38.484, + "step": 1831680 + }, + { + "epoch": 1.0, + "learning_rate": 2.0005693272177065e-05, + "loss": 3.8786, + "step": 1831936 + }, + { + "epoch": 1.0, + "learning_rate": 1.9997307324666544e-05, + "loss": 3.8819, + "step": 1832448 + }, + { + "epoch": 1.0, + "learning_rate": 1.9988937755959754e-05, + "loss": 3.8826, + "step": 1832960 + }, + { + "epoch": 1.0, + "learning_rate": 1.9980551808449237e-05, + "loss": 3.8905, + "step": 1833472 + }, + { + "epoch": 1.0, + "learning_rate": 1.9972165860938717e-05, + "loss": 3.8939, + "step": 1833984 + }, + { + "epoch": 1.0, + "learning_rate": 1.9963779913428197e-05, + "loss": 3.8812, + "step": 1834496 + }, + { + "epoch": 1.0, + "learning_rate": 1.9955393965917677e-05, + "loss": 3.8877, + "step": 1835008 + }, + { + "epoch": 1.0, + "learning_rate": 1.9947024397210886e-05, + "loss": 3.8812, + "step": 1835520 + }, + { + "epoch": 1.0, + "learning_rate": 1.9938638449700366e-05, + "loss": 3.8846, + "step": 1836032 + }, + { + "epoch": 1.0, + "learning_rate": 1.9930252502189846e-05, + "loss": 3.8988, + "step": 1836544 + }, + { + "epoch": 1.0, + "learning_rate": 1.992186655467933e-05, + "loss": 3.8858, + "step": 1837056 + }, + { + "epoch": 1.0, + "learning_rate": 1.991348060716881e-05, + "loss": 3.887, + "step": 1837568 + }, + { + "epoch": 1.0, + "learning_rate": 1.9905094659658286e-05, + "loss": 3.8854, + "step": 1838080 + }, + { + "epoch": 1.0, + "learning_rate": 1.9896725090951498e-05, + "loss": 3.8756, + "step": 1838592 + }, + { + "epoch": 1.0, + "learning_rate": 1.9888339143440978e-05, + "loss": 3.888, + "step": 1839104 + }, + { + "epoch": 1.0, + "learning_rate": 1.9879953195930458e-05, + "loss": 3.8744, + "step": 1839616 + }, + { + "epoch": 1.0, + "learning_rate": 1.9871567248419938e-05, + "loss": 3.8825, + "step": 1840128 + }, + { + "epoch": 1.0, + "learning_rate": 1.986319767971315e-05, + "loss": 3.8869, + "step": 1840640 + }, + { + "epoch": 1.0, + "learning_rate": 1.985481173220263e-05, + "loss": 3.8781, + "step": 1841152 + }, + { + "epoch": 1.0, + "learning_rate": 1.9846425784692107e-05, + "loss": 3.9003, + "step": 1841664 + }, + { + "epoch": 1.0, + "learning_rate": 1.9838039837181587e-05, + "loss": 3.9003, + "step": 1842176 + }, + { + "epoch": 1.0, + "learning_rate": 1.9829653889671067e-05, + "loss": 3.8881, + "step": 1842688 + }, + { + "epoch": 1.0, + "learning_rate": 1.9821267942160547e-05, + "loss": 3.8868, + "step": 1843200 + }, + { + "epoch": 1.0, + "learning_rate": 1.981289837345376e-05, + "loss": 3.8958, + "step": 1843712 + }, + { + "epoch": 1.0, + "learning_rate": 1.980451242594324e-05, + "loss": 3.8852, + "step": 1844224 + }, + { + "epoch": 1.0, + "learning_rate": 1.979612647843272e-05, + "loss": 3.886, + "step": 1844736 + }, + { + "epoch": 1.0, + "learning_rate": 1.97877405309222e-05, + "loss": 3.8865, + "step": 1845248 + }, + { + "epoch": 1.0, + "learning_rate": 1.977935458341168e-05, + "loss": 3.8826, + "step": 1845760 + }, + { + "epoch": 1.0, + "learning_rate": 1.977096863590116e-05, + "loss": 3.8843, + "step": 1846272 + }, + { + "epoch": 1.0, + "learning_rate": 1.976258268839064e-05, + "loss": 3.8854, + "step": 1846784 + }, + { + "epoch": 1.01, + "learning_rate": 1.975421311968385e-05, + "loss": 3.8898, + "step": 1847296 + }, + { + "epoch": 1.01, + "learning_rate": 1.974582717217333e-05, + "loss": 3.893, + "step": 1847808 + }, + { + "epoch": 1.01, + "learning_rate": 1.973744122466281e-05, + "loss": 3.8933, + "step": 1848320 + }, + { + "epoch": 1.01, + "learning_rate": 1.972907165595602e-05, + "loss": 3.8879, + "step": 1848832 + }, + { + "epoch": 1.01, + "learning_rate": 1.97206857084455e-05, + "loss": 3.8819, + "step": 1849344 + }, + { + "epoch": 1.01, + "learning_rate": 1.9712316139738713e-05, + "loss": 3.8972, + "step": 1849856 + }, + { + "epoch": 1.01, + "learning_rate": 1.9703930192228193e-05, + "loss": 3.8843, + "step": 1850368 + }, + { + "epoch": 1.01, + "learning_rate": 1.9695544244717673e-05, + "loss": 3.8775, + "step": 1850880 + }, + { + "epoch": 1.01, + "learning_rate": 1.9687158297207153e-05, + "loss": 3.878, + "step": 1851392 + }, + { + "epoch": 1.01, + "learning_rate": 1.9678772349696633e-05, + "loss": 3.8782, + "step": 1851904 + }, + { + "epoch": 1.01, + "learning_rate": 1.9670386402186113e-05, + "loss": 3.8839, + "step": 1852416 + }, + { + "epoch": 1.01, + "learning_rate": 1.9662000454675593e-05, + "loss": 3.8897, + "step": 1852928 + }, + { + "epoch": 1.01, + "learning_rate": 1.9653614507165073e-05, + "loss": 3.8887, + "step": 1853440 + }, + { + "epoch": 1.01, + "learning_rate": 1.9645228559654553e-05, + "loss": 3.8862, + "step": 1853952 + }, + { + "epoch": 1.01, + "learning_rate": 1.9636842612144033e-05, + "loss": 3.884, + "step": 1854464 + }, + { + "epoch": 1.01, + "learning_rate": 1.9628456664633513e-05, + "loss": 3.8904, + "step": 1854976 + }, + { + "epoch": 1.01, + "learning_rate": 1.9620070717122993e-05, + "loss": 3.8872, + "step": 1855488 + }, + { + "epoch": 1.01, + "learning_rate": 1.961168476961247e-05, + "loss": 3.8875, + "step": 1856000 + }, + { + "epoch": 1.01, + "learning_rate": 1.9603298822101952e-05, + "loss": 3.8612, + "step": 1856512 + }, + { + "epoch": 1.01, + "learning_rate": 1.9594929253395165e-05, + "loss": 3.8982, + "step": 1857024 + }, + { + "epoch": 1.01, + "learning_rate": 1.9586559684688374e-05, + "loss": 3.8801, + "step": 1857536 + }, + { + "epoch": 1.01, + "learning_rate": 1.9578173737177854e-05, + "loss": 3.8936, + "step": 1858048 + }, + { + "epoch": 1.01, + "learning_rate": 1.9569787789667334e-05, + "loss": 3.8781, + "step": 1858560 + }, + { + "epoch": 1.01, + "learning_rate": 1.9561401842156814e-05, + "loss": 3.8803, + "step": 1859072 + }, + { + "epoch": 1.01, + "learning_rate": 1.9553032273450026e-05, + "loss": 3.8765, + "step": 1859584 + }, + { + "epoch": 1.01, + "learning_rate": 1.9544646325939506e-05, + "loss": 3.8852, + "step": 1860096 + }, + { + "epoch": 1.01, + "learning_rate": 1.9536260378428986e-05, + "loss": 3.8791, + "step": 1860608 + }, + { + "epoch": 1.01, + "learning_rate": 1.9527874430918466e-05, + "loss": 3.8811, + "step": 1861120 + }, + { + "epoch": 1.01, + "learning_rate": 1.9519488483407943e-05, + "loss": 3.8923, + "step": 1861632 + }, + { + "epoch": 1.01, + "learning_rate": 1.9511102535897423e-05, + "loss": 3.8793, + "step": 1862144 + }, + { + "epoch": 1.01, + "learning_rate": 1.9502716588386906e-05, + "loss": 3.8702, + "step": 1862656 + }, + { + "epoch": 1.01, + "learning_rate": 1.9494330640876386e-05, + "loss": 3.8949, + "step": 1863168 + }, + { + "epoch": 1.01, + "learning_rate": 1.9485961072169595e-05, + "loss": 3.8684, + "step": 1863680 + }, + { + "epoch": 1.01, + "learning_rate": 1.9477575124659075e-05, + "loss": 3.8655, + "step": 1864192 + }, + { + "epoch": 1.01, + "learning_rate": 1.9469189177148555e-05, + "loss": 3.8873, + "step": 1864704 + }, + { + "epoch": 1.01, + "learning_rate": 1.9460803229638035e-05, + "loss": 3.8847, + "step": 1865216 + }, + { + "epoch": 1.01, + "learning_rate": 1.9452417282127515e-05, + "loss": 3.8784, + "step": 1865728 + }, + { + "epoch": 1.01, + "learning_rate": 1.9444047713420727e-05, + "loss": 3.8804, + "step": 1866240 + }, + { + "epoch": 1.01, + "learning_rate": 1.943567814471394e-05, + "loss": 3.8652, + "step": 1866752 + }, + { + "epoch": 1.01, + "learning_rate": 1.9427292197203417e-05, + "loss": 3.8748, + "step": 1867264 + }, + { + "epoch": 1.01, + "learning_rate": 1.9418906249692896e-05, + "loss": 3.8855, + "step": 1867776 + }, + { + "epoch": 1.01, + "learning_rate": 1.9410520302182376e-05, + "loss": 3.8815, + "step": 1868288 + }, + { + "epoch": 1.01, + "learning_rate": 1.940213435467186e-05, + "loss": 3.8929, + "step": 1868800 + }, + { + "epoch": 1.01, + "learning_rate": 1.939374840716134e-05, + "loss": 3.8852, + "step": 1869312 + }, + { + "epoch": 1.01, + "learning_rate": 1.938536245965082e-05, + "loss": 3.8958, + "step": 1869824 + }, + { + "epoch": 1.01, + "learning_rate": 1.93769765121403e-05, + "loss": 3.8713, + "step": 1870336 + }, + { + "epoch": 1.01, + "learning_rate": 1.936860694343351e-05, + "loss": 3.8882, + "step": 1870848 + }, + { + "epoch": 1.01, + "learning_rate": 1.936022099592299e-05, + "loss": 3.8805, + "step": 1871360 + }, + { + "epoch": 1.01, + "learning_rate": 1.935183504841247e-05, + "loss": 3.8755, + "step": 1871872 + }, + { + "epoch": 1.01, + "learning_rate": 1.934344910090195e-05, + "loss": 3.8817, + "step": 1872384 + }, + { + "epoch": 1.01, + "learning_rate": 1.933506315339143e-05, + "loss": 3.8883, + "step": 1872896 + }, + { + "epoch": 1.01, + "learning_rate": 1.932667720588091e-05, + "loss": 3.8847, + "step": 1873408 + }, + { + "epoch": 1.01, + "learning_rate": 1.931829125837039e-05, + "loss": 3.8968, + "step": 1873920 + }, + { + "epoch": 1.01, + "learning_rate": 1.930990531085987e-05, + "loss": 3.8692, + "step": 1874432 + }, + { + "epoch": 1.01, + "learning_rate": 1.930151936334935e-05, + "loss": 3.8772, + "step": 1874944 + }, + { + "epoch": 1.01, + "learning_rate": 1.9293166173446293e-05, + "loss": 3.8876, + "step": 1875456 + }, + { + "epoch": 1.01, + "learning_rate": 1.9284780225935773e-05, + "loss": 3.8868, + "step": 1875968 + }, + { + "epoch": 1.01, + "learning_rate": 1.927639427842525e-05, + "loss": 3.885, + "step": 1876480 + }, + { + "epoch": 1.01, + "learning_rate": 1.926800833091473e-05, + "loss": 3.8902, + "step": 1876992 + }, + { + "epoch": 1.02, + "learning_rate": 1.9259638762207942e-05, + "loss": 3.8876, + "step": 1877504 + }, + { + "epoch": 1.02, + "learning_rate": 1.9251252814697422e-05, + "loss": 3.8876, + "step": 1878016 + }, + { + "epoch": 1.02, + "learning_rate": 1.9242866867186902e-05, + "loss": 3.8811, + "step": 1878528 + }, + { + "epoch": 1.02, + "learning_rate": 1.9234497298480115e-05, + "loss": 3.8753, + "step": 1879040 + }, + { + "epoch": 1.02, + "learning_rate": 1.9226111350969595e-05, + "loss": 3.8952, + "step": 1879552 + }, + { + "epoch": 1.02, + "learning_rate": 1.921772540345907e-05, + "loss": 3.8868, + "step": 1880064 + }, + { + "epoch": 1.02, + "learning_rate": 1.920933945594855e-05, + "loss": 3.8867, + "step": 1880576 + }, + { + "epoch": 1.02, + "learning_rate": 1.920095350843803e-05, + "loss": 3.8787, + "step": 1881088 + }, + { + "epoch": 1.02, + "learning_rate": 1.9192583939731247e-05, + "loss": 3.8728, + "step": 1881600 + }, + { + "epoch": 1.02, + "learning_rate": 1.9184197992220724e-05, + "loss": 3.8844, + "step": 1882112 + }, + { + "epoch": 1.02, + "learning_rate": 1.9175812044710204e-05, + "loss": 3.8956, + "step": 1882624 + }, + { + "epoch": 1.02, + "learning_rate": 1.9167426097199684e-05, + "loss": 3.8831, + "step": 1883136 + }, + { + "epoch": 1.02, + "learning_rate": 1.9159040149689164e-05, + "loss": 3.8814, + "step": 1883648 + }, + { + "epoch": 1.02, + "learning_rate": 1.9150654202178643e-05, + "loss": 3.8768, + "step": 1884160 + }, + { + "epoch": 1.02, + "learning_rate": 1.9142284633471856e-05, + "loss": 3.8796, + "step": 1884672 + }, + { + "epoch": 1.02, + "learning_rate": 1.9133898685961336e-05, + "loss": 3.8769, + "step": 1885184 + }, + { + "epoch": 1.02, + "learning_rate": 1.9125512738450816e-05, + "loss": 3.8767, + "step": 1885696 + }, + { + "epoch": 1.02, + "learning_rate": 1.9117126790940296e-05, + "loss": 3.8717, + "step": 1886208 + }, + { + "epoch": 1.02, + "learning_rate": 1.9108740843429776e-05, + "loss": 3.8886, + "step": 1886720 + }, + { + "epoch": 1.02, + "learning_rate": 1.9100354895919252e-05, + "loss": 3.8823, + "step": 1887232 + }, + { + "epoch": 1.02, + "learning_rate": 1.9091968948408732e-05, + "loss": 3.8803, + "step": 1887744 + }, + { + "epoch": 1.02, + "learning_rate": 1.9083599379701948e-05, + "loss": 3.8745, + "step": 1888256 + }, + { + "epoch": 1.02, + "learning_rate": 1.9075213432191428e-05, + "loss": 3.8857, + "step": 1888768 + }, + { + "epoch": 1.02, + "learning_rate": 1.9066843863484637e-05, + "loss": 3.8847, + "step": 1889280 + }, + { + "epoch": 1.02, + "learning_rate": 1.9058457915974117e-05, + "loss": 3.8838, + "step": 1889792 + }, + { + "epoch": 1.02, + "learning_rate": 1.9050071968463597e-05, + "loss": 3.8875, + "step": 1890304 + }, + { + "epoch": 1.02, + "learning_rate": 1.9041686020953077e-05, + "loss": 3.8935, + "step": 1890816 + }, + { + "epoch": 1.02, + "learning_rate": 1.9033300073442557e-05, + "loss": 3.8767, + "step": 1891328 + }, + { + "epoch": 1.02, + "learning_rate": 1.9024914125932037e-05, + "loss": 3.8861, + "step": 1891840 + }, + { + "epoch": 1.02, + "learning_rate": 1.9016528178421517e-05, + "loss": 3.8732, + "step": 1892352 + }, + { + "epoch": 1.02, + "learning_rate": 1.9008142230910997e-05, + "loss": 3.8833, + "step": 1892864 + }, + { + "epoch": 1.02, + "learning_rate": 1.8999756283400477e-05, + "loss": 3.8812, + "step": 1893376 + }, + { + "epoch": 1.02, + "learning_rate": 1.8991370335889957e-05, + "loss": 3.8781, + "step": 1893888 + }, + { + "epoch": 1.02, + "learning_rate": 1.8982984388379433e-05, + "loss": 3.8746, + "step": 1894400 + }, + { + "epoch": 1.02, + "learning_rate": 1.8974598440868917e-05, + "loss": 3.8817, + "step": 1894912 + }, + { + "epoch": 1.02, + "learning_rate": 1.8966212493358397e-05, + "loss": 3.8815, + "step": 1895424 + }, + { + "epoch": 1.02, + "learning_rate": 1.895784292465161e-05, + "loss": 3.8834, + "step": 1895936 + }, + { + "epoch": 1.02, + "learning_rate": 1.8949456977141086e-05, + "loss": 3.867, + "step": 1896448 + }, + { + "epoch": 1.02, + "learning_rate": 1.8941071029630566e-05, + "loss": 3.8823, + "step": 1896960 + }, + { + "epoch": 1.02, + "learning_rate": 1.8932685082120046e-05, + "loss": 3.878, + "step": 1897472 + }, + { + "epoch": 1.02, + "learning_rate": 1.8924299134609526e-05, + "loss": 3.8924, + "step": 1897984 + }, + { + "epoch": 1.02, + "learning_rate": 1.891591318709901e-05, + "loss": 3.8844, + "step": 1898496 + }, + { + "epoch": 1.02, + "learning_rate": 1.8907543618392218e-05, + "loss": 3.8841, + "step": 1899008 + }, + { + "epoch": 1.02, + "learning_rate": 1.8899157670881698e-05, + "loss": 3.8757, + "step": 1899520 + }, + { + "epoch": 1.02, + "learning_rate": 1.8890771723371178e-05, + "loss": 3.8899, + "step": 1900032 + }, + { + "epoch": 1.02, + "learning_rate": 1.8882385775860658e-05, + "loss": 3.8896, + "step": 1900544 + }, + { + "epoch": 1.02, + "learning_rate": 1.8873999828350138e-05, + "loss": 3.8891, + "step": 1901056 + }, + { + "epoch": 1.02, + "learning_rate": 1.8865613880839618e-05, + "loss": 3.888, + "step": 1901568 + }, + { + "epoch": 1.02, + "learning_rate": 1.8857227933329098e-05, + "loss": 3.8898, + "step": 1902080 + }, + { + "epoch": 1.02, + "learning_rate": 1.8848841985818578e-05, + "loss": 3.8846, + "step": 1902592 + }, + { + "epoch": 1.02, + "learning_rate": 1.884047241711179e-05, + "loss": 3.891, + "step": 1903104 + }, + { + "epoch": 1.02, + "learning_rate": 1.8832086469601267e-05, + "loss": 3.873, + "step": 1903616 + }, + { + "epoch": 1.02, + "learning_rate": 1.8823700522090747e-05, + "loss": 3.8899, + "step": 1904128 + }, + { + "epoch": 1.02, + "learning_rate": 1.881531457458023e-05, + "loss": 3.8804, + "step": 1904640 + }, + { + "epoch": 1.02, + "learning_rate": 1.880694500587344e-05, + "loss": 3.8822, + "step": 1905152 + }, + { + "epoch": 1.02, + "learning_rate": 1.879855905836292e-05, + "loss": 3.8729, + "step": 1905664 + }, + { + "epoch": 1.02, + "learning_rate": 1.87901731108524e-05, + "loss": 3.8771, + "step": 1906176 + }, + { + "epoch": 1.02, + "learning_rate": 1.878178716334188e-05, + "loss": 3.8839, + "step": 1906688 + }, + { + "epoch": 1.02, + "learning_rate": 1.877341759463509e-05, + "loss": 3.882, + "step": 1907200 + }, + { + "epoch": 1.02, + "learning_rate": 1.876503164712457e-05, + "loss": 3.8921, + "step": 1907712 + }, + { + "epoch": 1.03, + "eval_loss": 3.985269784927368, + "eval_runtime": 311.6074, + "eval_samples_per_second": 1224.589, + "eval_steps_per_second": 38.269, + "step": 1908000 + }, + { + "epoch": 0.0, + "learning_rate": 1.875664569961405e-05, + "loss": 3.8733, + "step": 1908224 + }, + { + "epoch": 0.0, + "learning_rate": 1.874825975210353e-05, + "loss": 3.8752, + "step": 1908736 + }, + { + "epoch": 0.0, + "learning_rate": 1.873987380459301e-05, + "loss": 3.8756, + "step": 1909248 + }, + { + "epoch": 0.0, + "learning_rate": 1.873148785708249e-05, + "loss": 3.8878, + "step": 1909760 + }, + { + "epoch": 0.0, + "learning_rate": 1.8723101909571968e-05, + "loss": 3.8859, + "step": 1910272 + }, + { + "epoch": 0.0, + "learning_rate": 1.8714715962061448e-05, + "loss": 3.8732, + "step": 1910784 + }, + { + "epoch": 0.0, + "learning_rate": 1.870633001455093e-05, + "loss": 3.8831, + "step": 1911296 + }, + { + "epoch": 0.0, + "learning_rate": 1.869794406704041e-05, + "loss": 3.8745, + "step": 1911808 + }, + { + "epoch": 0.0, + "learning_rate": 1.868955811952989e-05, + "loss": 3.8766, + "step": 1912320 + }, + { + "epoch": 0.0, + "learning_rate": 1.868117217201937e-05, + "loss": 3.8941, + "step": 1912832 + }, + { + "epoch": 0.0, + "learning_rate": 1.867278622450885e-05, + "loss": 3.8793, + "step": 1913344 + }, + { + "epoch": 0.0, + "learning_rate": 1.8664400276998328e-05, + "loss": 3.877, + "step": 1913856 + }, + { + "epoch": 0.0, + "learning_rate": 1.8656014329487808e-05, + "loss": 3.8894, + "step": 1914368 + }, + { + "epoch": 0.0, + "learning_rate": 1.8647628381977287e-05, + "loss": 3.8628, + "step": 1914880 + }, + { + "epoch": 0.0, + "learning_rate": 1.863924243446677e-05, + "loss": 3.8806, + "step": 1915392 + }, + { + "epoch": 0.0, + "learning_rate": 1.863085648695625e-05, + "loss": 3.8697, + "step": 1915904 + }, + { + "epoch": 0.0, + "learning_rate": 1.862247053944573e-05, + "loss": 3.8813, + "step": 1916416 + }, + { + "epoch": 0.0, + "learning_rate": 1.861408459193521e-05, + "loss": 3.8798, + "step": 1916928 + }, + { + "epoch": 0.0, + "learning_rate": 1.860571502322842e-05, + "loss": 3.871, + "step": 1917440 + }, + { + "epoch": 0.0, + "learning_rate": 1.85973290757179e-05, + "loss": 3.8933, + "step": 1917952 + }, + { + "epoch": 0.0, + "learning_rate": 1.858894312820738e-05, + "loss": 3.8956, + "step": 1918464 + }, + { + "epoch": 0.0, + "learning_rate": 1.858055718069686e-05, + "loss": 3.8844, + "step": 1918976 + }, + { + "epoch": 0.0, + "learning_rate": 1.857217123318634e-05, + "loss": 3.8848, + "step": 1919488 + }, + { + "epoch": 0.0, + "learning_rate": 1.856378528567582e-05, + "loss": 3.8832, + "step": 1920000 + }, + { + "epoch": 0.0, + "learning_rate": 1.85553993381653e-05, + "loss": 3.884, + "step": 1920512 + }, + { + "epoch": 0.0, + "learning_rate": 1.854702976945851e-05, + "loss": 3.8778, + "step": 1921024 + }, + { + "epoch": 0.0, + "learning_rate": 1.8538660200751724e-05, + "loss": 3.8845, + "step": 1921536 + }, + { + "epoch": 0.0, + "learning_rate": 1.8530274253241204e-05, + "loss": 3.8809, + "step": 1922048 + }, + { + "epoch": 0.0, + "learning_rate": 1.8521888305730684e-05, + "loss": 3.8757, + "step": 1922560 + }, + { + "epoch": 0.0, + "learning_rate": 1.851350235822016e-05, + "loss": 3.8799, + "step": 1923072 + }, + { + "epoch": 0.01, + "learning_rate": 1.850511641070964e-05, + "loss": 3.8843, + "step": 1923584 + }, + { + "epoch": 0.01, + "learning_rate": 1.8496746842002853e-05, + "loss": 3.8914, + "step": 1924096 + }, + { + "epoch": 0.01, + "learning_rate": 1.8488360894492333e-05, + "loss": 3.8865, + "step": 1924608 + }, + { + "epoch": 0.01, + "learning_rate": 1.8479974946981813e-05, + "loss": 3.885, + "step": 1925120 + }, + { + "epoch": 0.01, + "learning_rate": 1.8471588999471293e-05, + "loss": 3.8777, + "step": 1925632 + }, + { + "epoch": 0.01, + "learning_rate": 1.8463219430764506e-05, + "loss": 3.8837, + "step": 1926144 + }, + { + "epoch": 0.01, + "learning_rate": 1.8454833483253982e-05, + "loss": 3.8839, + "step": 1926656 + }, + { + "epoch": 0.01, + "learning_rate": 1.8446447535743462e-05, + "loss": 3.8733, + "step": 1927168 + }, + { + "epoch": 0.01, + "learning_rate": 1.8438061588232942e-05, + "loss": 3.8713, + "step": 1927680 + }, + { + "epoch": 0.01, + "learning_rate": 1.8429675640722426e-05, + "loss": 3.8708, + "step": 1928192 + }, + { + "epoch": 0.01, + "learning_rate": 1.8421289693211906e-05, + "loss": 3.8802, + "step": 1928704 + }, + { + "epoch": 0.01, + "learning_rate": 1.8412903745701385e-05, + "loss": 3.8809, + "step": 1929216 + }, + { + "epoch": 0.01, + "learning_rate": 1.8404517798190865e-05, + "loss": 3.8814, + "step": 1929728 + }, + { + "epoch": 0.01, + "learning_rate": 1.8396131850680342e-05, + "loss": 3.8801, + "step": 1930240 + }, + { + "epoch": 0.01, + "learning_rate": 1.8387745903169822e-05, + "loss": 3.8809, + "step": 1930752 + }, + { + "epoch": 0.01, + "learning_rate": 1.8379359955659302e-05, + "loss": 3.8808, + "step": 1931264 + }, + { + "epoch": 0.01, + "learning_rate": 1.8370974008148782e-05, + "loss": 3.8816, + "step": 1931776 + }, + { + "epoch": 0.01, + "learning_rate": 1.8362588060638265e-05, + "loss": 3.8876, + "step": 1932288 + }, + { + "epoch": 0.01, + "learning_rate": 1.8354202113127745e-05, + "loss": 3.8528, + "step": 1932800 + }, + { + "epoch": 0.01, + "learning_rate": 1.8345816165617222e-05, + "loss": 3.8878, + "step": 1933312 + }, + { + "epoch": 0.01, + "learning_rate": 1.8337446596910434e-05, + "loss": 3.8777, + "step": 1933824 + }, + { + "epoch": 0.01, + "learning_rate": 1.8329077028203647e-05, + "loss": 3.8893, + "step": 1934336 + }, + { + "epoch": 0.01, + "learning_rate": 1.8320691080693127e-05, + "loss": 3.875, + "step": 1934848 + }, + { + "epoch": 0.01, + "learning_rate": 1.831232151198634e-05, + "loss": 3.8735, + "step": 1935360 + }, + { + "epoch": 0.01, + "learning_rate": 1.8303935564475816e-05, + "loss": 3.8671, + "step": 1935872 + }, + { + "epoch": 0.01, + "learning_rate": 1.8295549616965296e-05, + "loss": 3.8782, + "step": 1936384 + }, + { + "epoch": 0.01, + "learning_rate": 1.8287163669454776e-05, + "loss": 3.8791, + "step": 1936896 + }, + { + "epoch": 0.01, + "learning_rate": 1.8278777721944256e-05, + "loss": 3.8706, + "step": 1937408 + }, + { + "epoch": 0.01, + "learning_rate": 1.8270391774433736e-05, + "loss": 3.8871, + "step": 1937920 + }, + { + "epoch": 0.01, + "learning_rate": 1.826200582692322e-05, + "loss": 3.8791, + "step": 1938432 + }, + { + "epoch": 0.01, + "learning_rate": 1.8253619879412695e-05, + "loss": 3.8591, + "step": 1938944 + }, + { + "epoch": 0.01, + "learning_rate": 1.8245233931902175e-05, + "loss": 3.8886, + "step": 1939456 + }, + { + "epoch": 0.01, + "learning_rate": 1.8236847984391655e-05, + "loss": 3.865, + "step": 1939968 + }, + { + "epoch": 0.01, + "learning_rate": 1.8228462036881135e-05, + "loss": 3.86, + "step": 1940480 + }, + { + "epoch": 0.01, + "learning_rate": 1.8220076089370615e-05, + "loss": 3.8787, + "step": 1940992 + }, + { + "epoch": 0.01, + "learning_rate": 1.8211706520663828e-05, + "loss": 3.8781, + "step": 1941504 + }, + { + "epoch": 0.01, + "learning_rate": 1.8203320573153308e-05, + "loss": 3.8667, + "step": 1942016 + }, + { + "epoch": 0.01, + "learning_rate": 1.8194934625642788e-05, + "loss": 3.8818, + "step": 1942528 + }, + { + "epoch": 0.01, + "learning_rate": 1.8186565056935997e-05, + "loss": 3.8605, + "step": 1943040 + }, + { + "epoch": 0.01, + "learning_rate": 1.8178179109425477e-05, + "loss": 3.8662, + "step": 1943552 + }, + { + "epoch": 0.01, + "learning_rate": 1.8169793161914957e-05, + "loss": 3.8813, + "step": 1944064 + }, + { + "epoch": 0.01, + "learning_rate": 1.816140721440444e-05, + "loss": 3.8735, + "step": 1944576 + }, + { + "epoch": 0.01, + "learning_rate": 1.815302126689392e-05, + "loss": 3.889, + "step": 1945088 + }, + { + "epoch": 0.01, + "learning_rate": 1.81446353193834e-05, + "loss": 3.876, + "step": 1945600 + }, + { + "epoch": 0.01, + "learning_rate": 1.813626575067661e-05, + "loss": 3.8897, + "step": 1946112 + }, + { + "epoch": 0.01, + "learning_rate": 1.812787980316609e-05, + "loss": 3.8684, + "step": 1946624 + }, + { + "epoch": 0.01, + "learning_rate": 1.811949385565557e-05, + "loss": 3.8854, + "step": 1947136 + }, + { + "epoch": 0.01, + "learning_rate": 1.811110790814505e-05, + "loss": 3.8719, + "step": 1947648 + }, + { + "epoch": 0.01, + "learning_rate": 1.810272196063453e-05, + "loss": 3.8731, + "step": 1948160 + }, + { + "epoch": 0.01, + "learning_rate": 1.809433601312401e-05, + "loss": 3.8766, + "step": 1948672 + }, + { + "epoch": 0.01, + "learning_rate": 1.808595006561349e-05, + "loss": 3.8796, + "step": 1949184 + }, + { + "epoch": 0.01, + "learning_rate": 1.8077580496906698e-05, + "loss": 3.8793, + "step": 1949696 + }, + { + "epoch": 0.01, + "learning_rate": 1.8069194549396178e-05, + "loss": 3.8918, + "step": 1950208 + }, + { + "epoch": 0.01, + "learning_rate": 1.8060808601885658e-05, + "loss": 3.8633, + "step": 1950720 + }, + { + "epoch": 0.01, + "learning_rate": 1.805242265437514e-05, + "loss": 3.8707, + "step": 1951232 + }, + { + "epoch": 0.01, + "learning_rate": 1.804403670686462e-05, + "loss": 3.8819, + "step": 1951744 + }, + { + "epoch": 0.01, + "learning_rate": 1.80356507593541e-05, + "loss": 3.8825, + "step": 1952256 + }, + { + "epoch": 0.01, + "learning_rate": 1.802728119064731e-05, + "loss": 3.8772, + "step": 1952768 + }, + { + "epoch": 0.01, + "learning_rate": 1.801889524313679e-05, + "loss": 3.8869, + "step": 1953280 + }, + { + "epoch": 0.02, + "learning_rate": 1.801050929562627e-05, + "loss": 3.8823, + "step": 1953792 + }, + { + "epoch": 0.02, + "learning_rate": 1.8002139726919483e-05, + "loss": 3.8834, + "step": 1954304 + }, + { + "epoch": 0.02, + "learning_rate": 1.7993753779408962e-05, + "loss": 3.8796, + "step": 1954816 + }, + { + "epoch": 0.02, + "learning_rate": 1.7985367831898442e-05, + "loss": 3.8706, + "step": 1955328 + }, + { + "epoch": 0.02, + "learning_rate": 1.7976981884387922e-05, + "loss": 3.886, + "step": 1955840 + }, + { + "epoch": 0.02, + "learning_rate": 1.7968595936877402e-05, + "loss": 3.884, + "step": 1956352 + }, + { + "epoch": 0.02, + "learning_rate": 1.796020998936688e-05, + "loss": 3.8797, + "step": 1956864 + }, + { + "epoch": 0.02, + "learning_rate": 1.795182404185636e-05, + "loss": 3.8762, + "step": 1957376 + }, + { + "epoch": 0.02, + "learning_rate": 1.7943438094345842e-05, + "loss": 3.865, + "step": 1957888 + }, + { + "epoch": 0.02, + "learning_rate": 1.7935052146835322e-05, + "loss": 3.8792, + "step": 1958400 + }, + { + "epoch": 0.02, + "learning_rate": 1.7926666199324802e-05, + "loss": 3.8898, + "step": 1958912 + }, + { + "epoch": 0.02, + "learning_rate": 1.7918280251814282e-05, + "loss": 3.8781, + "step": 1959424 + }, + { + "epoch": 0.02, + "learning_rate": 1.7909894304303762e-05, + "loss": 3.8776, + "step": 1959936 + }, + { + "epoch": 0.02, + "learning_rate": 1.790152473559697e-05, + "loss": 3.8704, + "step": 1960448 + }, + { + "epoch": 0.02, + "learning_rate": 1.789313878808645e-05, + "loss": 3.8699, + "step": 1960960 + }, + { + "epoch": 0.02, + "learning_rate": 1.7884752840575934e-05, + "loss": 3.8757, + "step": 1961472 + }, + { + "epoch": 0.02, + "learning_rate": 1.7876383271869144e-05, + "loss": 3.8696, + "step": 1961984 + }, + { + "epoch": 0.02, + "learning_rate": 1.7867997324358623e-05, + "loss": 3.8685, + "step": 1962496 + }, + { + "epoch": 0.02, + "learning_rate": 1.7859611376848103e-05, + "loss": 3.8833, + "step": 1963008 + }, + { + "epoch": 0.02, + "learning_rate": 1.7851225429337583e-05, + "loss": 3.879, + "step": 1963520 + }, + { + "epoch": 0.02, + "learning_rate": 1.7842855860630796e-05, + "loss": 3.8722, + "step": 1964032 + }, + { + "epoch": 0.02, + "learning_rate": 1.7834469913120276e-05, + "loss": 3.8734, + "step": 1964544 + }, + { + "epoch": 0.02, + "learning_rate": 1.7826083965609756e-05, + "loss": 3.8755, + "step": 1965056 + }, + { + "epoch": 0.02, + "learning_rate": 1.7817698018099236e-05, + "loss": 3.8828, + "step": 1965568 + }, + { + "epoch": 0.02, + "learning_rate": 1.7809312070588712e-05, + "loss": 3.875, + "step": 1966080 + }, + { + "epoch": 0.02, + "learning_rate": 1.7800926123078192e-05, + "loss": 3.8849, + "step": 1966592 + }, + { + "epoch": 0.02, + "learning_rate": 1.7792556554371405e-05, + "loss": 3.886, + "step": 1967104 + }, + { + "epoch": 0.02, + "learning_rate": 1.7784170606860888e-05, + "loss": 3.8704, + "step": 1967616 + }, + { + "epoch": 0.02, + "learning_rate": 1.7775784659350365e-05, + "loss": 3.8793, + "step": 1968128 + }, + { + "epoch": 0.02, + "learning_rate": 1.7767398711839845e-05, + "loss": 3.8699, + "step": 1968640 + }, + { + "epoch": 0.02, + "learning_rate": 1.7759012764329325e-05, + "loss": 3.8794, + "step": 1969152 + }, + { + "epoch": 0.02, + "learning_rate": 1.7750626816818805e-05, + "loss": 3.8796, + "step": 1969664 + }, + { + "epoch": 0.02, + "learning_rate": 1.7742240869308284e-05, + "loss": 3.8679, + "step": 1970176 + }, + { + "epoch": 0.02, + "learning_rate": 1.7733854921797764e-05, + "loss": 3.8665, + "step": 1970688 + }, + { + "epoch": 0.02, + "learning_rate": 1.7725485353090977e-05, + "loss": 3.8779, + "step": 1971200 + }, + { + "epoch": 0.02, + "learning_rate": 1.7717099405580457e-05, + "loss": 3.8775, + "step": 1971712 + }, + { + "epoch": 0.02, + "learning_rate": 1.7708713458069937e-05, + "loss": 3.8796, + "step": 1972224 + }, + { + "epoch": 0.02, + "learning_rate": 1.7700327510559417e-05, + "loss": 3.8615, + "step": 1972736 + }, + { + "epoch": 0.02, + "learning_rate": 1.7691957941852626e-05, + "loss": 3.8741, + "step": 1973248 + }, + { + "epoch": 0.02, + "learning_rate": 1.768358837314584e-05, + "loss": 3.8704, + "step": 1973760 + }, + { + "epoch": 0.02, + "learning_rate": 1.767520242563532e-05, + "loss": 3.8885, + "step": 1974272 + }, + { + "epoch": 0.02, + "learning_rate": 1.7666816478124798e-05, + "loss": 3.8816, + "step": 1974784 + }, + { + "epoch": 0.02, + "learning_rate": 1.7658430530614278e-05, + "loss": 3.8795, + "step": 1975296 + }, + { + "epoch": 0.02, + "learning_rate": 1.7650044583103758e-05, + "loss": 3.8669, + "step": 1975808 + }, + { + "epoch": 0.02, + "learning_rate": 1.7641658635593238e-05, + "loss": 3.8901, + "step": 1976320 + }, + { + "epoch": 0.02, + "learning_rate": 1.763328906688645e-05, + "loss": 3.8806, + "step": 1976832 + }, + { + "epoch": 0.02, + "learning_rate": 1.762490311937593e-05, + "loss": 3.8874, + "step": 1977344 + }, + { + "epoch": 0.02, + "learning_rate": 1.761651717186541e-05, + "loss": 3.8806, + "step": 1977856 + }, + { + "epoch": 0.02, + "learning_rate": 1.760813122435489e-05, + "loss": 3.884, + "step": 1978368 + }, + { + "epoch": 0.02, + "learning_rate": 1.7599745276844367e-05, + "loss": 3.877, + "step": 1978880 + }, + { + "epoch": 0.02, + "learning_rate": 1.7591359329333847e-05, + "loss": 3.89, + "step": 1979392 + }, + { + "epoch": 0.02, + "learning_rate": 1.7582973381823327e-05, + "loss": 3.8633, + "step": 1979904 + }, + { + "epoch": 0.02, + "learning_rate": 1.757458743431281e-05, + "loss": 3.8847, + "step": 1980416 + }, + { + "epoch": 0.02, + "learning_rate": 1.7566234244409752e-05, + "loss": 3.8722, + "step": 1980928 + }, + { + "epoch": 0.02, + "learning_rate": 1.7557848296899232e-05, + "loss": 3.8756, + "step": 1981440 + }, + { + "epoch": 0.02, + "learning_rate": 1.7549462349388712e-05, + "loss": 3.8689, + "step": 1981952 + }, + { + "epoch": 0.02, + "learning_rate": 1.754107640187819e-05, + "loss": 3.8722, + "step": 1982464 + }, + { + "epoch": 0.02, + "learning_rate": 1.7532690454367672e-05, + "loss": 3.877, + "step": 1982976 + }, + { + "epoch": 0.02, + "learning_rate": 1.7524320885660884e-05, + "loss": 3.8763, + "step": 1983488 + }, + { + "epoch": 0.02, + "learning_rate": 1.7515934938150364e-05, + "loss": 3.8835, + "step": 1984000 + }, + { + "epoch": 0.03, + "eval_loss": 3.9829511642456055, + "eval_runtime": 294.1363, + "eval_samples_per_second": 1297.327, + "eval_steps_per_second": 40.542, + "step": 1984320 + }, + { + "epoch": 1.0, + "learning_rate": 1.750754899063984e-05, + "loss": 3.8672, + "step": 1984512 + }, + { + "epoch": 1.0, + "learning_rate": 1.749916304312932e-05, + "loss": 3.8702, + "step": 1985024 + }, + { + "epoch": 1.0, + "learning_rate": 1.74907770956188e-05, + "loss": 3.8692, + "step": 1985536 + }, + { + "epoch": 1.0, + "learning_rate": 1.748239114810828e-05, + "loss": 3.8835, + "step": 1986048 + }, + { + "epoch": 1.0, + "learning_rate": 1.7474021579401493e-05, + "loss": 3.8837, + "step": 1986560 + }, + { + "epoch": 1.0, + "learning_rate": 1.7465635631890973e-05, + "loss": 3.8696, + "step": 1987072 + }, + { + "epoch": 1.0, + "learning_rate": 1.7457249684380453e-05, + "loss": 3.8752, + "step": 1987584 + }, + { + "epoch": 1.0, + "learning_rate": 1.7448863736869933e-05, + "loss": 3.8694, + "step": 1988096 + }, + { + "epoch": 1.0, + "learning_rate": 1.7440477789359413e-05, + "loss": 3.8738, + "step": 1988608 + }, + { + "epoch": 1.0, + "learning_rate": 1.7432108220652622e-05, + "loss": 3.8843, + "step": 1989120 + }, + { + "epoch": 1.0, + "learning_rate": 1.7423722273142105e-05, + "loss": 3.8744, + "step": 1989632 + }, + { + "epoch": 1.0, + "learning_rate": 1.7415336325631585e-05, + "loss": 3.8768, + "step": 1990144 + }, + { + "epoch": 1.0, + "learning_rate": 1.7406950378121065e-05, + "loss": 3.8839, + "step": 1990656 + }, + { + "epoch": 1.0, + "learning_rate": 1.7398564430610545e-05, + "loss": 3.8608, + "step": 1991168 + }, + { + "epoch": 1.0, + "learning_rate": 1.7390194861903754e-05, + "loss": 3.8726, + "step": 1991680 + }, + { + "epoch": 1.0, + "learning_rate": 1.7381808914393234e-05, + "loss": 3.8632, + "step": 1992192 + }, + { + "epoch": 1.0, + "learning_rate": 1.7373422966882714e-05, + "loss": 3.8738, + "step": 1992704 + }, + { + "epoch": 1.0, + "learning_rate": 1.7365037019372194e-05, + "loss": 3.8788, + "step": 1993216 + }, + { + "epoch": 1.0, + "learning_rate": 1.7356667450665407e-05, + "loss": 3.8648, + "step": 1993728 + }, + { + "epoch": 1.0, + "learning_rate": 1.7348281503154887e-05, + "loss": 3.8854, + "step": 1994240 + }, + { + "epoch": 1.0, + "learning_rate": 1.7339895555644367e-05, + "loss": 3.8879, + "step": 1994752 + }, + { + "epoch": 1.0, + "learning_rate": 1.7331509608133843e-05, + "loss": 3.8787, + "step": 1995264 + }, + { + "epoch": 1.0, + "learning_rate": 1.7323123660623327e-05, + "loss": 3.8816, + "step": 1995776 + }, + { + "epoch": 1.0, + "learning_rate": 1.731475409191654e-05, + "loss": 3.8781, + "step": 1996288 + }, + { + "epoch": 1.0, + "learning_rate": 1.730636814440602e-05, + "loss": 3.8814, + "step": 1996800 + }, + { + "epoch": 1.0, + "learning_rate": 1.7297982196895496e-05, + "loss": 3.8724, + "step": 1997312 + }, + { + "epoch": 1.0, + "learning_rate": 1.7289596249384975e-05, + "loss": 3.8731, + "step": 1997824 + }, + { + "epoch": 1.0, + "learning_rate": 1.7281210301874455e-05, + "loss": 3.8774, + "step": 1998336 + }, + { + "epoch": 1.0, + "learning_rate": 1.7272824354363935e-05, + "loss": 3.871, + "step": 1998848 + }, + { + "epoch": 1.0, + "learning_rate": 1.726443840685342e-05, + "loss": 3.873, + "step": 1999360 + }, + { + "epoch": 1.01, + "learning_rate": 1.72560524593429e-05, + "loss": 3.8785, + "step": 1999872 + }, + { + "epoch": 1.01, + "learning_rate": 1.7247682890636108e-05, + "loss": 3.8785, + "step": 2000384 + }, + { + "epoch": 1.01, + "learning_rate": 1.7239296943125588e-05, + "loss": 3.887, + "step": 2000896 + }, + { + "epoch": 1.01, + "learning_rate": 1.7230910995615068e-05, + "loss": 3.8785, + "step": 2001408 + }, + { + "epoch": 1.01, + "learning_rate": 1.7222525048104548e-05, + "loss": 3.872, + "step": 2001920 + }, + { + "epoch": 1.01, + "learning_rate": 1.721415547939776e-05, + "loss": 3.8788, + "step": 2002432 + }, + { + "epoch": 1.01, + "learning_rate": 1.720576953188724e-05, + "loss": 3.8785, + "step": 2002944 + }, + { + "epoch": 1.01, + "learning_rate": 1.719738358437672e-05, + "loss": 3.8664, + "step": 2003456 + }, + { + "epoch": 1.01, + "learning_rate": 1.71889976368662e-05, + "loss": 3.8656, + "step": 2003968 + }, + { + "epoch": 1.01, + "learning_rate": 1.7180611689355677e-05, + "loss": 3.8694, + "step": 2004480 + }, + { + "epoch": 1.01, + "learning_rate": 1.7172225741845157e-05, + "loss": 3.8687, + "step": 2004992 + }, + { + "epoch": 1.01, + "learning_rate": 1.7163839794334636e-05, + "loss": 3.8785, + "step": 2005504 + }, + { + "epoch": 1.01, + "learning_rate": 1.715545384682412e-05, + "loss": 3.8746, + "step": 2006016 + }, + { + "epoch": 1.01, + "learning_rate": 1.71470678993136e-05, + "loss": 3.8781, + "step": 2006528 + }, + { + "epoch": 1.01, + "learning_rate": 1.713868195180308e-05, + "loss": 3.8716, + "step": 2007040 + }, + { + "epoch": 1.01, + "learning_rate": 1.7130296004292556e-05, + "loss": 3.8798, + "step": 2007552 + }, + { + "epoch": 1.01, + "learning_rate": 1.7121910056782036e-05, + "loss": 3.8739, + "step": 2008064 + }, + { + "epoch": 1.01, + "learning_rate": 1.711355686687898e-05, + "loss": 3.8829, + "step": 2008576 + }, + { + "epoch": 1.01, + "learning_rate": 1.710517091936846e-05, + "loss": 3.8492, + "step": 2009088 + }, + { + "epoch": 1.01, + "learning_rate": 1.709678497185794e-05, + "loss": 3.8786, + "step": 2009600 + }, + { + "epoch": 1.01, + "learning_rate": 1.708839902434742e-05, + "loss": 3.8728, + "step": 2010112 + }, + { + "epoch": 1.01, + "learning_rate": 1.708002945564063e-05, + "loss": 3.8838, + "step": 2010624 + }, + { + "epoch": 1.01, + "learning_rate": 1.707164350813011e-05, + "loss": 3.8681, + "step": 2011136 + }, + { + "epoch": 1.01, + "learning_rate": 1.706325756061959e-05, + "loss": 3.8683, + "step": 2011648 + }, + { + "epoch": 1.01, + "learning_rate": 1.7054871613109074e-05, + "loss": 3.8678, + "step": 2012160 + }, + { + "epoch": 1.01, + "learning_rate": 1.7046485665598553e-05, + "loss": 3.8717, + "step": 2012672 + }, + { + "epoch": 1.01, + "learning_rate": 1.7038116096891763e-05, + "loss": 3.8796, + "step": 2013184 + }, + { + "epoch": 1.01, + "learning_rate": 1.7029730149381243e-05, + "loss": 3.8603, + "step": 2013696 + }, + { + "epoch": 1.01, + "learning_rate": 1.7021344201870722e-05, + "loss": 3.887, + "step": 2014208 + }, + { + "epoch": 1.01, + "learning_rate": 1.7012958254360202e-05, + "loss": 3.8722, + "step": 2014720 + }, + { + "epoch": 1.01, + "learning_rate": 1.7004572306849682e-05, + "loss": 3.8513, + "step": 2015232 + }, + { + "epoch": 1.01, + "learning_rate": 1.6996186359339162e-05, + "loss": 3.884, + "step": 2015744 + }, + { + "epoch": 1.01, + "learning_rate": 1.6987800411828642e-05, + "loss": 3.8614, + "step": 2016256 + }, + { + "epoch": 1.01, + "learning_rate": 1.6979414464318122e-05, + "loss": 3.8526, + "step": 2016768 + }, + { + "epoch": 1.01, + "learning_rate": 1.697104489561133e-05, + "loss": 3.8763, + "step": 2017280 + }, + { + "epoch": 1.01, + "learning_rate": 1.6962675326904544e-05, + "loss": 3.8715, + "step": 2017792 + }, + { + "epoch": 1.01, + "learning_rate": 1.6954289379394027e-05, + "loss": 3.8595, + "step": 2018304 + }, + { + "epoch": 1.01, + "learning_rate": 1.6945903431883504e-05, + "loss": 3.8787, + "step": 2018816 + }, + { + "epoch": 1.01, + "learning_rate": 1.6937517484372984e-05, + "loss": 3.8551, + "step": 2019328 + }, + { + "epoch": 1.01, + "learning_rate": 1.6929131536862464e-05, + "loss": 3.8616, + "step": 2019840 + }, + { + "epoch": 1.01, + "learning_rate": 1.6920761968155676e-05, + "loss": 3.8751, + "step": 2020352 + }, + { + "epoch": 1.01, + "learning_rate": 1.6912376020645153e-05, + "loss": 3.8722, + "step": 2020864 + }, + { + "epoch": 1.01, + "learning_rate": 1.6903990073134636e-05, + "loss": 3.8793, + "step": 2021376 + }, + { + "epoch": 1.01, + "learning_rate": 1.689562050442785e-05, + "loss": 3.8718, + "step": 2021888 + }, + { + "epoch": 1.01, + "learning_rate": 1.6887234556917325e-05, + "loss": 3.884, + "step": 2022400 + }, + { + "epoch": 1.01, + "learning_rate": 1.6878848609406805e-05, + "loss": 3.8645, + "step": 2022912 + }, + { + "epoch": 1.01, + "learning_rate": 1.6870462661896285e-05, + "loss": 3.8797, + "step": 2023424 + }, + { + "epoch": 1.01, + "learning_rate": 1.6862093093189497e-05, + "loss": 3.8619, + "step": 2023936 + }, + { + "epoch": 1.01, + "learning_rate": 1.6853707145678977e-05, + "loss": 3.8694, + "step": 2024448 + }, + { + "epoch": 1.01, + "learning_rate": 1.6845321198168457e-05, + "loss": 3.8717, + "step": 2024960 + }, + { + "epoch": 1.01, + "learning_rate": 1.6836935250657937e-05, + "loss": 3.8704, + "step": 2025472 + }, + { + "epoch": 1.01, + "learning_rate": 1.6828549303147417e-05, + "loss": 3.8791, + "step": 2025984 + }, + { + "epoch": 1.01, + "learning_rate": 1.6820163355636897e-05, + "loss": 3.8856, + "step": 2026496 + }, + { + "epoch": 1.01, + "learning_rate": 1.6811777408126377e-05, + "loss": 3.8667, + "step": 2027008 + }, + { + "epoch": 1.01, + "learning_rate": 1.6803391460615857e-05, + "loss": 3.8633, + "step": 2027520 + }, + { + "epoch": 1.01, + "learning_rate": 1.6795005513105337e-05, + "loss": 3.8728, + "step": 2028032 + }, + { + "epoch": 1.01, + "learning_rate": 1.6786619565594817e-05, + "loss": 3.879, + "step": 2028544 + }, + { + "epoch": 1.01, + "learning_rate": 1.6778233618084297e-05, + "loss": 3.8695, + "step": 2029056 + }, + { + "epoch": 1.01, + "learning_rate": 1.6769847670573777e-05, + "loss": 3.8807, + "step": 2029568 + }, + { + "epoch": 1.01, + "learning_rate": 1.6761461723063257e-05, + "loss": 3.8781, + "step": 2030080 + }, + { + "epoch": 1.02, + "learning_rate": 1.6753075775552737e-05, + "loss": 3.8775, + "step": 2030592 + }, + { + "epoch": 1.02, + "learning_rate": 1.6744706206845946e-05, + "loss": 3.8741, + "step": 2031104 + }, + { + "epoch": 1.02, + "learning_rate": 1.673632025933543e-05, + "loss": 3.8654, + "step": 2031616 + }, + { + "epoch": 1.02, + "learning_rate": 1.672793431182491e-05, + "loss": 3.8807, + "step": 2032128 + }, + { + "epoch": 1.02, + "learning_rate": 1.671954836431439e-05, + "loss": 3.8757, + "step": 2032640 + }, + { + "epoch": 1.02, + "learning_rate": 1.6711162416803866e-05, + "loss": 3.8782, + "step": 2033152 + }, + { + "epoch": 1.02, + "learning_rate": 1.6702776469293346e-05, + "loss": 3.8698, + "step": 2033664 + }, + { + "epoch": 1.02, + "learning_rate": 1.6694390521782826e-05, + "loss": 3.8596, + "step": 2034176 + }, + { + "epoch": 1.02, + "learning_rate": 1.6686020953076038e-05, + "loss": 3.8741, + "step": 2034688 + }, + { + "epoch": 1.02, + "learning_rate": 1.6677635005565518e-05, + "loss": 3.8842, + "step": 2035200 + }, + { + "epoch": 1.02, + "learning_rate": 1.6669249058054998e-05, + "loss": 3.8753, + "step": 2035712 + }, + { + "epoch": 1.02, + "learning_rate": 1.6660863110544478e-05, + "loss": 3.8711, + "step": 2036224 + }, + { + "epoch": 1.02, + "learning_rate": 1.6652477163033958e-05, + "loss": 3.8687, + "step": 2036736 + }, + { + "epoch": 1.02, + "learning_rate": 1.6644091215523438e-05, + "loss": 3.8649, + "step": 2037248 + }, + { + "epoch": 1.02, + "learning_rate": 1.6635721646816647e-05, + "loss": 3.8734, + "step": 2037760 + }, + { + "epoch": 1.02, + "learning_rate": 1.662733569930613e-05, + "loss": 3.8609, + "step": 2038272 + }, + { + "epoch": 1.02, + "learning_rate": 1.661894975179561e-05, + "loss": 3.8664, + "step": 2038784 + }, + { + "epoch": 1.02, + "learning_rate": 1.661056380428509e-05, + "loss": 3.8755, + "step": 2039296 + }, + { + "epoch": 1.02, + "learning_rate": 1.660217785677457e-05, + "loss": 3.8757, + "step": 2039808 + }, + { + "epoch": 1.02, + "learning_rate": 1.659380828806778e-05, + "loss": 3.8702, + "step": 2040320 + }, + { + "epoch": 1.02, + "learning_rate": 1.658542234055726e-05, + "loss": 3.8657, + "step": 2040832 + }, + { + "epoch": 1.02, + "learning_rate": 1.6577052771850472e-05, + "loss": 3.8684, + "step": 2041344 + }, + { + "epoch": 1.02, + "learning_rate": 1.6568666824339952e-05, + "loss": 3.8772, + "step": 2041856 + }, + { + "epoch": 1.02, + "learning_rate": 1.6560280876829432e-05, + "loss": 3.8704, + "step": 2042368 + }, + { + "epoch": 1.02, + "learning_rate": 1.6551894929318912e-05, + "loss": 3.8826, + "step": 2042880 + }, + { + "epoch": 1.02, + "learning_rate": 1.654350898180839e-05, + "loss": 3.8751, + "step": 2043392 + }, + { + "epoch": 1.02, + "learning_rate": 1.6535123034297868e-05, + "loss": 3.8704, + "step": 2043904 + }, + { + "epoch": 1.02, + "learning_rate": 1.652673708678735e-05, + "loss": 3.8717, + "step": 2044416 + }, + { + "epoch": 1.02, + "learning_rate": 1.651835113927683e-05, + "loss": 3.869, + "step": 2044928 + }, + { + "epoch": 1.02, + "learning_rate": 1.650996519176631e-05, + "loss": 3.8727, + "step": 2045440 + }, + { + "epoch": 1.02, + "learning_rate": 1.650157924425579e-05, + "loss": 3.8776, + "step": 2045952 + }, + { + "epoch": 1.02, + "learning_rate": 1.649319329674527e-05, + "loss": 3.8623, + "step": 2046464 + }, + { + "epoch": 1.02, + "learning_rate": 1.648480734923475e-05, + "loss": 3.8622, + "step": 2046976 + }, + { + "epoch": 1.02, + "learning_rate": 1.6476421401724228e-05, + "loss": 3.8714, + "step": 2047488 + }, + { + "epoch": 1.02, + "learning_rate": 1.6468051833017444e-05, + "loss": 3.8733, + "step": 2048000 + }, + { + "epoch": 1.02, + "learning_rate": 1.6459665885506924e-05, + "loss": 3.8665, + "step": 2048512 + }, + { + "epoch": 1.02, + "learning_rate": 1.6451279937996404e-05, + "loss": 3.8603, + "step": 2049024 + }, + { + "epoch": 1.02, + "learning_rate": 1.6442910369289613e-05, + "loss": 3.8698, + "step": 2049536 + }, + { + "epoch": 1.02, + "learning_rate": 1.6434524421779093e-05, + "loss": 3.865, + "step": 2050048 + }, + { + "epoch": 1.02, + "learning_rate": 1.6426138474268573e-05, + "loss": 3.8859, + "step": 2050560 + }, + { + "epoch": 1.02, + "learning_rate": 1.6417752526758053e-05, + "loss": 3.8729, + "step": 2051072 + }, + { + "epoch": 1.02, + "learning_rate": 1.6409366579247533e-05, + "loss": 3.877, + "step": 2051584 + }, + { + "epoch": 1.02, + "learning_rate": 1.6400997010540745e-05, + "loss": 3.8632, + "step": 2052096 + }, + { + "epoch": 1.02, + "learning_rate": 1.6392627441833954e-05, + "loss": 3.8841, + "step": 2052608 + }, + { + "epoch": 1.02, + "learning_rate": 1.6384241494323434e-05, + "loss": 3.8723, + "step": 2053120 + }, + { + "epoch": 1.02, + "learning_rate": 1.6375855546812914e-05, + "loss": 3.8817, + "step": 2053632 + }, + { + "epoch": 1.02, + "learning_rate": 1.6367469599302394e-05, + "loss": 3.8797, + "step": 2054144 + }, + { + "epoch": 1.02, + "learning_rate": 1.6359083651791874e-05, + "loss": 3.8762, + "step": 2054656 + }, + { + "epoch": 1.02, + "learning_rate": 1.6350697704281354e-05, + "loss": 3.8719, + "step": 2055168 + }, + { + "epoch": 1.02, + "learning_rate": 1.6342311756770834e-05, + "loss": 3.8876, + "step": 2055680 + }, + { + "epoch": 1.02, + "learning_rate": 1.6333925809260314e-05, + "loss": 3.86, + "step": 2056192 + }, + { + "epoch": 1.02, + "learning_rate": 1.6325539861749794e-05, + "loss": 3.8778, + "step": 2056704 + }, + { + "epoch": 1.02, + "learning_rate": 1.6317153914239274e-05, + "loss": 3.87, + "step": 2057216 + }, + { + "epoch": 1.02, + "learning_rate": 1.6308767966728754e-05, + "loss": 3.8715, + "step": 2057728 + }, + { + "epoch": 1.02, + "learning_rate": 1.6300382019218234e-05, + "loss": 3.8647, + "step": 2058240 + }, + { + "epoch": 1.02, + "learning_rate": 1.6292012450511446e-05, + "loss": 3.8661, + "step": 2058752 + }, + { + "epoch": 1.02, + "learning_rate": 1.6283642881804655e-05, + "loss": 3.8689, + "step": 2059264 + }, + { + "epoch": 1.02, + "learning_rate": 1.6275256934294135e-05, + "loss": 3.8765, + "step": 2059776 + }, + { + "epoch": 1.02, + "learning_rate": 1.6266870986783615e-05, + "loss": 3.8781, + "step": 2060288 + }, + { + "epoch": 1.03, + "eval_loss": 3.980713367462158, + "eval_runtime": 298.0036, + "eval_samples_per_second": 1280.491, + "eval_steps_per_second": 40.016, + "step": 2060640 + }, + { + "epoch": 0.0, + "learning_rate": 1.62584850392731e-05, + "loss": 3.8649, + "step": 2060800 + }, + { + "epoch": 0.0, + "learning_rate": 1.625009909176258e-05, + "loss": 3.8634, + "step": 2061312 + }, + { + "epoch": 0.0, + "learning_rate": 1.6241713144252055e-05, + "loss": 3.8629, + "step": 2061824 + }, + { + "epoch": 0.0, + "learning_rate": 1.6233327196741535e-05, + "loss": 3.8779, + "step": 2062336 + }, + { + "epoch": 0.0, + "learning_rate": 1.6224941249231015e-05, + "loss": 3.8778, + "step": 2062848 + }, + { + "epoch": 0.0, + "learning_rate": 1.6216555301720495e-05, + "loss": 3.8642, + "step": 2063360 + }, + { + "epoch": 0.0, + "learning_rate": 1.6208169354209975e-05, + "loss": 3.8687, + "step": 2063872 + }, + { + "epoch": 0.0, + "learning_rate": 1.6199783406699455e-05, + "loss": 3.8666, + "step": 2064384 + }, + { + "epoch": 0.0, + "learning_rate": 1.6191397459188938e-05, + "loss": 3.8687, + "step": 2064896 + }, + { + "epoch": 0.0, + "learning_rate": 1.6183011511678415e-05, + "loss": 3.8752, + "step": 2065408 + }, + { + "epoch": 0.0, + "learning_rate": 1.6174625564167895e-05, + "loss": 3.8746, + "step": 2065920 + }, + { + "epoch": 0.0, + "learning_rate": 1.6166239616657375e-05, + "loss": 3.8702, + "step": 2066432 + }, + { + "epoch": 0.0, + "learning_rate": 1.6157853669146855e-05, + "loss": 3.8788, + "step": 2066944 + }, + { + "epoch": 0.0, + "learning_rate": 1.6149467721636335e-05, + "loss": 3.8562, + "step": 2067456 + }, + { + "epoch": 0.0, + "learning_rate": 1.6141081774125815e-05, + "loss": 3.8692, + "step": 2067968 + }, + { + "epoch": 0.0, + "learning_rate": 1.6132695826615295e-05, + "loss": 3.8556, + "step": 2068480 + }, + { + "epoch": 0.0, + "learning_rate": 1.6124326257908507e-05, + "loss": 3.8729, + "step": 2068992 + }, + { + "epoch": 0.0, + "learning_rate": 1.6115940310397987e-05, + "loss": 3.8763, + "step": 2069504 + }, + { + "epoch": 0.0, + "learning_rate": 1.6107570741691196e-05, + "loss": 3.8534, + "step": 2070016 + }, + { + "epoch": 0.0, + "learning_rate": 1.6099184794180676e-05, + "loss": 3.878, + "step": 2070528 + }, + { + "epoch": 0.0, + "learning_rate": 1.6090798846670156e-05, + "loss": 3.8849, + "step": 2071040 + }, + { + "epoch": 0.0, + "learning_rate": 1.608241289915964e-05, + "loss": 3.8741, + "step": 2071552 + }, + { + "epoch": 0.0, + "learning_rate": 1.607402695164912e-05, + "loss": 3.8788, + "step": 2072064 + }, + { + "epoch": 0.0, + "learning_rate": 1.6065641004138596e-05, + "loss": 3.8744, + "step": 2072576 + }, + { + "epoch": 0.0, + "learning_rate": 1.6057255056628076e-05, + "loss": 3.8763, + "step": 2073088 + }, + { + "epoch": 0.0, + "learning_rate": 1.6048869109117556e-05, + "loss": 3.8674, + "step": 2073600 + }, + { + "epoch": 0.0, + "learning_rate": 1.6040483161607036e-05, + "loss": 3.8666, + "step": 2074112 + }, + { + "epoch": 0.0, + "learning_rate": 1.6032097214096516e-05, + "loss": 3.871, + "step": 2074624 + }, + { + "epoch": 0.0, + "learning_rate": 1.6023711266586e-05, + "loss": 3.8671, + "step": 2075136 + }, + { + "epoch": 0.0, + "learning_rate": 1.601532531907548e-05, + "loss": 3.8708, + "step": 2075648 + }, + { + "epoch": 0.01, + "learning_rate": 1.6006955750368688e-05, + "loss": 3.8748, + "step": 2076160 + }, + { + "epoch": 0.01, + "learning_rate": 1.5998586181661897e-05, + "loss": 3.8785, + "step": 2076672 + }, + { + "epoch": 0.01, + "learning_rate": 1.5990200234151377e-05, + "loss": 3.8739, + "step": 2077184 + }, + { + "epoch": 0.01, + "learning_rate": 1.598181428664086e-05, + "loss": 3.8788, + "step": 2077696 + }, + { + "epoch": 0.01, + "learning_rate": 1.597342833913034e-05, + "loss": 3.8642, + "step": 2078208 + }, + { + "epoch": 0.01, + "learning_rate": 1.596505877042355e-05, + "loss": 3.8764, + "step": 2078720 + }, + { + "epoch": 0.01, + "learning_rate": 1.595667282291303e-05, + "loss": 3.8773, + "step": 2079232 + }, + { + "epoch": 0.01, + "learning_rate": 1.594828687540251e-05, + "loss": 3.8548, + "step": 2079744 + }, + { + "epoch": 0.01, + "learning_rate": 1.593990092789199e-05, + "loss": 3.8642, + "step": 2080256 + }, + { + "epoch": 0.01, + "learning_rate": 1.593151498038147e-05, + "loss": 3.8658, + "step": 2080768 + }, + { + "epoch": 0.01, + "learning_rate": 1.592312903287095e-05, + "loss": 3.8644, + "step": 2081280 + }, + { + "epoch": 0.01, + "learning_rate": 1.591474308536043e-05, + "loss": 3.8718, + "step": 2081792 + }, + { + "epoch": 0.01, + "learning_rate": 1.590635713784991e-05, + "loss": 3.8716, + "step": 2082304 + }, + { + "epoch": 0.01, + "learning_rate": 1.589798756914312e-05, + "loss": 3.8703, + "step": 2082816 + }, + { + "epoch": 0.01, + "learning_rate": 1.5889601621632598e-05, + "loss": 3.871, + "step": 2083328 + }, + { + "epoch": 0.01, + "learning_rate": 1.5881215674122078e-05, + "loss": 3.8736, + "step": 2083840 + }, + { + "epoch": 0.01, + "learning_rate": 1.587282972661156e-05, + "loss": 3.8683, + "step": 2084352 + }, + { + "epoch": 0.01, + "learning_rate": 1.5864460157904774e-05, + "loss": 3.8776, + "step": 2084864 + }, + { + "epoch": 0.01, + "learning_rate": 1.585607421039425e-05, + "loss": 3.8511, + "step": 2085376 + }, + { + "epoch": 0.01, + "learning_rate": 1.584768826288373e-05, + "loss": 3.8736, + "step": 2085888 + }, + { + "epoch": 0.01, + "learning_rate": 1.583930231537321e-05, + "loss": 3.8655, + "step": 2086400 + }, + { + "epoch": 0.01, + "learning_rate": 1.583091636786269e-05, + "loss": 3.8798, + "step": 2086912 + }, + { + "epoch": 0.01, + "learning_rate": 1.582253042035217e-05, + "loss": 3.8657, + "step": 2087424 + }, + { + "epoch": 0.01, + "learning_rate": 1.5814144472841654e-05, + "loss": 3.859, + "step": 2087936 + }, + { + "epoch": 0.01, + "learning_rate": 1.580575852533113e-05, + "loss": 3.8632, + "step": 2088448 + }, + { + "epoch": 0.01, + "learning_rate": 1.5797388956624343e-05, + "loss": 3.8694, + "step": 2088960 + }, + { + "epoch": 0.01, + "learning_rate": 1.5789003009113823e-05, + "loss": 3.8754, + "step": 2089472 + }, + { + "epoch": 0.01, + "learning_rate": 1.5780617061603303e-05, + "loss": 3.8551, + "step": 2089984 + }, + { + "epoch": 0.01, + "learning_rate": 1.5772247492896515e-05, + "loss": 3.8802, + "step": 2090496 + }, + { + "epoch": 0.01, + "learning_rate": 1.5763861545385995e-05, + "loss": 3.8714, + "step": 2091008 + }, + { + "epoch": 0.01, + "learning_rate": 1.5755475597875475e-05, + "loss": 3.8438, + "step": 2091520 + }, + { + "epoch": 0.01, + "learning_rate": 1.5747089650364955e-05, + "loss": 3.8774, + "step": 2092032 + }, + { + "epoch": 0.01, + "learning_rate": 1.573870370285443e-05, + "loss": 3.8582, + "step": 2092544 + }, + { + "epoch": 0.01, + "learning_rate": 1.5730334134147644e-05, + "loss": 3.8511, + "step": 2093056 + }, + { + "epoch": 0.01, + "learning_rate": 1.5721948186637124e-05, + "loss": 3.8676, + "step": 2093568 + }, + { + "epoch": 0.01, + "learning_rate": 1.5713562239126604e-05, + "loss": 3.8684, + "step": 2094080 + }, + { + "epoch": 0.01, + "learning_rate": 1.5705176291616084e-05, + "loss": 3.8584, + "step": 2094592 + }, + { + "epoch": 0.01, + "learning_rate": 1.5696790344105564e-05, + "loss": 3.8748, + "step": 2095104 + }, + { + "epoch": 0.01, + "learning_rate": 1.5688404396595044e-05, + "loss": 3.8478, + "step": 2095616 + }, + { + "epoch": 0.01, + "learning_rate": 1.5680018449084524e-05, + "loss": 3.8559, + "step": 2096128 + }, + { + "epoch": 0.01, + "learning_rate": 1.5671648880377733e-05, + "loss": 3.8715, + "step": 2096640 + }, + { + "epoch": 0.01, + "learning_rate": 1.5663262932867216e-05, + "loss": 3.8707, + "step": 2097152 + }, + { + "epoch": 0.01, + "learning_rate": 1.5654876985356696e-05, + "loss": 3.8715, + "step": 2097664 + }, + { + "epoch": 0.01, + "learning_rate": 1.5646491037846176e-05, + "loss": 3.8703, + "step": 2098176 + }, + { + "epoch": 0.01, + "learning_rate": 1.5638121469139385e-05, + "loss": 3.8765, + "step": 2098688 + }, + { + "epoch": 0.01, + "learning_rate": 1.5629735521628865e-05, + "loss": 3.8632, + "step": 2099200 + }, + { + "epoch": 0.01, + "learning_rate": 1.5621349574118345e-05, + "loss": 3.8779, + "step": 2099712 + }, + { + "epoch": 0.01, + "learning_rate": 1.5612963626607825e-05, + "loss": 3.8601, + "step": 2100224 + }, + { + "epoch": 0.01, + "learning_rate": 1.560457767909731e-05, + "loss": 3.8625, + "step": 2100736 + }, + { + "epoch": 0.01, + "learning_rate": 1.5596191731586785e-05, + "loss": 3.8628, + "step": 2101248 + }, + { + "epoch": 0.01, + "learning_rate": 1.5587805784076265e-05, + "loss": 3.8677, + "step": 2101760 + }, + { + "epoch": 0.01, + "learning_rate": 1.5579419836565745e-05, + "loss": 3.8741, + "step": 2102272 + }, + { + "epoch": 0.01, + "learning_rate": 1.5571033889055225e-05, + "loss": 3.8795, + "step": 2102784 + }, + { + "epoch": 0.01, + "learning_rate": 1.556268069915217e-05, + "loss": 3.8642, + "step": 2103296 + }, + { + "epoch": 0.01, + "learning_rate": 1.555429475164165e-05, + "loss": 3.8563, + "step": 2103808 + }, + { + "epoch": 0.01, + "learning_rate": 1.554590880413113e-05, + "loss": 3.8691, + "step": 2104320 + }, + { + "epoch": 0.01, + "learning_rate": 1.553752285662061e-05, + "loss": 3.8755, + "step": 2104832 + }, + { + "epoch": 0.01, + "learning_rate": 1.552915328791382e-05, + "loss": 3.8642, + "step": 2105344 + }, + { + "epoch": 0.01, + "learning_rate": 1.55207673404033e-05, + "loss": 3.8751, + "step": 2105856 + }, + { + "epoch": 0.01, + "learning_rate": 1.551238139289278e-05, + "loss": 3.8755, + "step": 2106368 + }, + { + "epoch": 0.02, + "learning_rate": 1.550399544538226e-05, + "loss": 3.8726, + "step": 2106880 + }, + { + "epoch": 0.02, + "learning_rate": 1.549560949787174e-05, + "loss": 3.867, + "step": 2107392 + }, + { + "epoch": 0.02, + "learning_rate": 1.548722355036122e-05, + "loss": 3.8612, + "step": 2107904 + }, + { + "epoch": 0.02, + "learning_rate": 1.54788376028507e-05, + "loss": 3.8781, + "step": 2108416 + }, + { + "epoch": 0.02, + "learning_rate": 1.547045165534018e-05, + "loss": 3.875, + "step": 2108928 + }, + { + "epoch": 0.02, + "learning_rate": 1.5462082086633388e-05, + "loss": 3.8712, + "step": 2109440 + }, + { + "epoch": 0.02, + "learning_rate": 1.545369613912287e-05, + "loss": 3.867, + "step": 2109952 + }, + { + "epoch": 0.02, + "learning_rate": 1.544531019161235e-05, + "loss": 3.8542, + "step": 2110464 + }, + { + "epoch": 0.02, + "learning_rate": 1.543692424410183e-05, + "loss": 3.8684, + "step": 2110976 + }, + { + "epoch": 0.02, + "learning_rate": 1.542853829659131e-05, + "loss": 3.8802, + "step": 2111488 + }, + { + "epoch": 0.02, + "learning_rate": 1.542016872788452e-05, + "loss": 3.8688, + "step": 2112000 + }, + { + "epoch": 0.02, + "learning_rate": 1.5411782780374e-05, + "loss": 3.8654, + "step": 2112512 + }, + { + "epoch": 0.02, + "learning_rate": 1.540339683286348e-05, + "loss": 3.8652, + "step": 2113024 + }, + { + "epoch": 0.02, + "learning_rate": 1.5395010885352963e-05, + "loss": 3.8618, + "step": 2113536 + }, + { + "epoch": 0.02, + "learning_rate": 1.538662493784244e-05, + "loss": 3.8674, + "step": 2114048 + }, + { + "epoch": 0.02, + "learning_rate": 1.537823899033192e-05, + "loss": 3.8619, + "step": 2114560 + }, + { + "epoch": 0.02, + "learning_rate": 1.5369869421625132e-05, + "loss": 3.8577, + "step": 2115072 + }, + { + "epoch": 0.02, + "learning_rate": 1.5361483474114612e-05, + "loss": 3.8689, + "step": 2115584 + }, + { + "epoch": 0.02, + "learning_rate": 1.5353097526604092e-05, + "loss": 3.8689, + "step": 2116096 + }, + { + "epoch": 0.02, + "learning_rate": 1.5344711579093572e-05, + "loss": 3.8646, + "step": 2116608 + }, + { + "epoch": 0.02, + "learning_rate": 1.5336342010386785e-05, + "loss": 3.8644, + "step": 2117120 + }, + { + "epoch": 0.02, + "learning_rate": 1.5327956062876265e-05, + "loss": 3.8613, + "step": 2117632 + }, + { + "epoch": 0.02, + "learning_rate": 1.531957011536574e-05, + "loss": 3.8743, + "step": 2118144 + }, + { + "epoch": 0.02, + "learning_rate": 1.531118416785522e-05, + "loss": 3.8659, + "step": 2118656 + }, + { + "epoch": 0.02, + "learning_rate": 1.53027982203447e-05, + "loss": 3.8755, + "step": 2119168 + }, + { + "epoch": 0.02, + "learning_rate": 1.529441227283418e-05, + "loss": 3.8701, + "step": 2119680 + }, + { + "epoch": 0.02, + "learning_rate": 1.5286026325323664e-05, + "loss": 3.8658, + "step": 2120192 + }, + { + "epoch": 0.02, + "learning_rate": 1.5277640377813144e-05, + "loss": 3.8692, + "step": 2120704 + }, + { + "epoch": 0.02, + "learning_rate": 1.5269287187910086e-05, + "loss": 3.8648, + "step": 2121216 + }, + { + "epoch": 0.02, + "learning_rate": 1.5260901240399563e-05, + "loss": 3.8675, + "step": 2121728 + }, + { + "epoch": 0.02, + "learning_rate": 1.5252515292889044e-05, + "loss": 3.8722, + "step": 2122240 + }, + { + "epoch": 0.02, + "learning_rate": 1.5244129345378524e-05, + "loss": 3.8597, + "step": 2122752 + }, + { + "epoch": 0.02, + "learning_rate": 1.5235743397868004e-05, + "loss": 3.859, + "step": 2123264 + }, + { + "epoch": 0.02, + "learning_rate": 1.5227357450357486e-05, + "loss": 3.8675, + "step": 2123776 + }, + { + "epoch": 0.02, + "learning_rate": 1.5218971502846966e-05, + "loss": 3.8679, + "step": 2124288 + }, + { + "epoch": 0.02, + "learning_rate": 1.5210585555336442e-05, + "loss": 3.8649, + "step": 2124800 + }, + { + "epoch": 0.02, + "learning_rate": 1.5202232365433386e-05, + "loss": 3.8583, + "step": 2125312 + }, + { + "epoch": 0.02, + "learning_rate": 1.5193846417922866e-05, + "loss": 3.8615, + "step": 2125824 + }, + { + "epoch": 0.02, + "learning_rate": 1.5185460470412347e-05, + "loss": 3.8626, + "step": 2126336 + }, + { + "epoch": 0.02, + "learning_rate": 1.5177074522901827e-05, + "loss": 3.8813, + "step": 2126848 + }, + { + "epoch": 0.02, + "learning_rate": 1.5168704954195038e-05, + "loss": 3.8649, + "step": 2127360 + }, + { + "epoch": 0.02, + "learning_rate": 1.5160319006684518e-05, + "loss": 3.8738, + "step": 2127872 + }, + { + "epoch": 0.02, + "learning_rate": 1.5151933059173998e-05, + "loss": 3.8596, + "step": 2128384 + }, + { + "epoch": 0.02, + "learning_rate": 1.5143547111663478e-05, + "loss": 3.8749, + "step": 2128896 + }, + { + "epoch": 0.02, + "learning_rate": 1.5135161164152958e-05, + "loss": 3.8688, + "step": 2129408 + }, + { + "epoch": 0.02, + "learning_rate": 1.512677521664244e-05, + "loss": 3.8767, + "step": 2129920 + }, + { + "epoch": 0.02, + "learning_rate": 1.5118389269131916e-05, + "loss": 3.8774, + "step": 2130432 + }, + { + "epoch": 0.02, + "learning_rate": 1.5110003321621396e-05, + "loss": 3.8713, + "step": 2130944 + }, + { + "epoch": 0.02, + "learning_rate": 1.5101617374110878e-05, + "loss": 3.8704, + "step": 2131456 + }, + { + "epoch": 0.02, + "learning_rate": 1.5093231426600358e-05, + "loss": 3.8771, + "step": 2131968 + }, + { + "epoch": 0.02, + "learning_rate": 1.5084845479089837e-05, + "loss": 3.859, + "step": 2132480 + }, + { + "epoch": 0.02, + "learning_rate": 1.5076459531579317e-05, + "loss": 3.8735, + "step": 2132992 + }, + { + "epoch": 0.02, + "learning_rate": 1.5068089962872528e-05, + "loss": 3.8658, + "step": 2133504 + }, + { + "epoch": 0.02, + "learning_rate": 1.505972039416574e-05, + "loss": 3.8679, + "step": 2134016 + }, + { + "epoch": 0.02, + "learning_rate": 1.5051334446655219e-05, + "loss": 3.8578, + "step": 2134528 + }, + { + "epoch": 0.02, + "learning_rate": 1.5042948499144699e-05, + "loss": 3.8668, + "step": 2135040 + }, + { + "epoch": 0.02, + "learning_rate": 1.5034562551634179e-05, + "loss": 3.8626, + "step": 2135552 + }, + { + "epoch": 0.02, + "learning_rate": 1.5026176604123659e-05, + "loss": 3.8654, + "step": 2136064 + }, + { + "epoch": 0.02, + "learning_rate": 1.501779065661314e-05, + "loss": 3.8727, + "step": 2136576 + }, + { + "epoch": 0.03, + "eval_loss": 3.979320764541626, + "eval_runtime": 292.1184, + "eval_samples_per_second": 1306.289, + "eval_steps_per_second": 40.822, + "step": 2136960 + }, + { + "epoch": 1.0, + "learning_rate": 1.500940470910262e-05, + "loss": 3.8674, + "step": 2137088 + }, + { + "epoch": 1.0, + "learning_rate": 1.5001018761592097e-05, + "loss": 3.8552, + "step": 2137600 + }, + { + "epoch": 1.0, + "learning_rate": 1.4992649192885311e-05, + "loss": 3.8606, + "step": 2138112 + }, + { + "epoch": 1.0, + "learning_rate": 1.498427962417852e-05, + "loss": 3.8716, + "step": 2138624 + }, + { + "epoch": 1.0, + "learning_rate": 1.4975893676668002e-05, + "loss": 3.8692, + "step": 2139136 + }, + { + "epoch": 1.0, + "learning_rate": 1.4967507729157482e-05, + "loss": 3.8621, + "step": 2139648 + }, + { + "epoch": 1.0, + "learning_rate": 1.4959121781646962e-05, + "loss": 3.8692, + "step": 2140160 + }, + { + "epoch": 1.0, + "learning_rate": 1.4950735834136442e-05, + "loss": 3.8613, + "step": 2140672 + }, + { + "epoch": 1.0, + "learning_rate": 1.4942366265429653e-05, + "loss": 3.862, + "step": 2141184 + }, + { + "epoch": 1.0, + "learning_rate": 1.4933980317919133e-05, + "loss": 3.8681, + "step": 2141696 + }, + { + "epoch": 1.0, + "learning_rate": 1.4925594370408612e-05, + "loss": 3.8758, + "step": 2142208 + }, + { + "epoch": 1.0, + "learning_rate": 1.4917208422898094e-05, + "loss": 3.864, + "step": 2142720 + }, + { + "epoch": 1.0, + "learning_rate": 1.490882247538757e-05, + "loss": 3.8758, + "step": 2143232 + }, + { + "epoch": 1.0, + "learning_rate": 1.490043652787705e-05, + "loss": 3.847, + "step": 2143744 + }, + { + "epoch": 1.0, + "learning_rate": 1.4892050580366532e-05, + "loss": 3.866, + "step": 2144256 + }, + { + "epoch": 1.0, + "learning_rate": 1.4883664632856012e-05, + "loss": 3.8539, + "step": 2144768 + }, + { + "epoch": 1.0, + "learning_rate": 1.4875311442952956e-05, + "loss": 3.8679, + "step": 2145280 + }, + { + "epoch": 1.0, + "learning_rate": 1.4866941874246165e-05, + "loss": 3.8724, + "step": 2145792 + }, + { + "epoch": 1.0, + "learning_rate": 1.4858555926735646e-05, + "loss": 3.8527, + "step": 2146304 + }, + { + "epoch": 1.0, + "learning_rate": 1.4850169979225126e-05, + "loss": 3.8717, + "step": 2146816 + }, + { + "epoch": 1.0, + "learning_rate": 1.4841784031714606e-05, + "loss": 3.8818, + "step": 2147328 + }, + { + "epoch": 1.0, + "learning_rate": 1.4833398084204086e-05, + "loss": 3.8674, + "step": 2147840 + }, + { + "epoch": 1.0, + "learning_rate": 1.4825012136693566e-05, + "loss": 3.8743, + "step": 2148352 + }, + { + "epoch": 1.0, + "learning_rate": 1.4816626189183044e-05, + "loss": 3.8714, + "step": 2148864 + }, + { + "epoch": 1.0, + "learning_rate": 1.4808240241672524e-05, + "loss": 3.8725, + "step": 2149376 + }, + { + "epoch": 1.0, + "learning_rate": 1.4799854294162004e-05, + "loss": 3.8651, + "step": 2149888 + }, + { + "epoch": 1.0, + "learning_rate": 1.4791468346651486e-05, + "loss": 3.8607, + "step": 2150400 + }, + { + "epoch": 1.0, + "learning_rate": 1.4783082399140966e-05, + "loss": 3.8664, + "step": 2150912 + }, + { + "epoch": 1.0, + "learning_rate": 1.4774696451630446e-05, + "loss": 3.8631, + "step": 2151424 + }, + { + "epoch": 1.0, + "learning_rate": 1.4766326882923657e-05, + "loss": 3.8633, + "step": 2151936 + }, + { + "epoch": 1.01, + "learning_rate": 1.4757940935413137e-05, + "loss": 3.8748, + "step": 2152448 + }, + { + "epoch": 1.01, + "learning_rate": 1.4749571366706347e-05, + "loss": 3.8719, + "step": 2152960 + }, + { + "epoch": 1.01, + "learning_rate": 1.4741185419195827e-05, + "loss": 3.8662, + "step": 2153472 + }, + { + "epoch": 1.01, + "learning_rate": 1.4732799471685307e-05, + "loss": 3.8776, + "step": 2153984 + }, + { + "epoch": 1.01, + "learning_rate": 1.4724413524174787e-05, + "loss": 3.8635, + "step": 2154496 + }, + { + "epoch": 1.01, + "learning_rate": 1.4716043955467998e-05, + "loss": 3.8734, + "step": 2155008 + }, + { + "epoch": 1.01, + "learning_rate": 1.4707658007957478e-05, + "loss": 3.8683, + "step": 2155520 + }, + { + "epoch": 1.01, + "learning_rate": 1.4699272060446958e-05, + "loss": 3.8534, + "step": 2156032 + }, + { + "epoch": 1.01, + "learning_rate": 1.469088611293644e-05, + "loss": 3.8618, + "step": 2156544 + }, + { + "epoch": 1.01, + "learning_rate": 1.4682516544229649e-05, + "loss": 3.861, + "step": 2157056 + }, + { + "epoch": 1.01, + "learning_rate": 1.4674130596719129e-05, + "loss": 3.8571, + "step": 2157568 + }, + { + "epoch": 1.01, + "learning_rate": 1.466574464920861e-05, + "loss": 3.8668, + "step": 2158080 + }, + { + "epoch": 1.01, + "learning_rate": 1.465735870169809e-05, + "loss": 3.8692, + "step": 2158592 + }, + { + "epoch": 1.01, + "learning_rate": 1.464897275418757e-05, + "loss": 3.8672, + "step": 2159104 + }, + { + "epoch": 1.01, + "learning_rate": 1.4640586806677049e-05, + "loss": 3.8654, + "step": 2159616 + }, + { + "epoch": 1.01, + "learning_rate": 1.4632217237970261e-05, + "loss": 3.872, + "step": 2160128 + }, + { + "epoch": 1.01, + "learning_rate": 1.4623831290459741e-05, + "loss": 3.8601, + "step": 2160640 + }, + { + "epoch": 1.01, + "learning_rate": 1.4615445342949221e-05, + "loss": 3.8722, + "step": 2161152 + }, + { + "epoch": 1.01, + "learning_rate": 1.46070593954387e-05, + "loss": 3.8505, + "step": 2161664 + }, + { + "epoch": 1.01, + "learning_rate": 1.4598673447928179e-05, + "loss": 3.8669, + "step": 2162176 + }, + { + "epoch": 1.01, + "learning_rate": 1.4590287500417659e-05, + "loss": 3.8627, + "step": 2162688 + }, + { + "epoch": 1.01, + "learning_rate": 1.458190155290714e-05, + "loss": 3.8775, + "step": 2163200 + }, + { + "epoch": 1.01, + "learning_rate": 1.457351560539662e-05, + "loss": 3.8618, + "step": 2163712 + }, + { + "epoch": 1.01, + "learning_rate": 1.45651296578861e-05, + "loss": 3.8543, + "step": 2164224 + }, + { + "epoch": 1.01, + "learning_rate": 1.4556760089179311e-05, + "loss": 3.8594, + "step": 2164736 + }, + { + "epoch": 1.01, + "learning_rate": 1.4548374141668791e-05, + "loss": 3.8615, + "step": 2165248 + }, + { + "epoch": 1.01, + "learning_rate": 1.4539988194158271e-05, + "loss": 3.873, + "step": 2165760 + }, + { + "epoch": 1.01, + "learning_rate": 1.4531602246647751e-05, + "loss": 3.8483, + "step": 2166272 + }, + { + "epoch": 1.01, + "learning_rate": 1.4523232677940962e-05, + "loss": 3.8777, + "step": 2166784 + }, + { + "epoch": 1.01, + "learning_rate": 1.4514846730430442e-05, + "loss": 3.8665, + "step": 2167296 + }, + { + "epoch": 1.01, + "learning_rate": 1.4506460782919922e-05, + "loss": 3.8424, + "step": 2167808 + }, + { + "epoch": 1.01, + "learning_rate": 1.4498074835409404e-05, + "loss": 3.8732, + "step": 2168320 + }, + { + "epoch": 1.01, + "learning_rate": 1.4489705266702613e-05, + "loss": 3.8525, + "step": 2168832 + }, + { + "epoch": 1.01, + "learning_rate": 1.4481319319192094e-05, + "loss": 3.8478, + "step": 2169344 + }, + { + "epoch": 1.01, + "learning_rate": 1.4472933371681574e-05, + "loss": 3.8611, + "step": 2169856 + }, + { + "epoch": 1.01, + "learning_rate": 1.4464547424171054e-05, + "loss": 3.8661, + "step": 2170368 + }, + { + "epoch": 1.01, + "learning_rate": 1.4456161476660533e-05, + "loss": 3.8603, + "step": 2170880 + }, + { + "epoch": 1.01, + "learning_rate": 1.4447791907953745e-05, + "loss": 3.8641, + "step": 2171392 + }, + { + "epoch": 1.01, + "learning_rate": 1.4439405960443225e-05, + "loss": 3.8464, + "step": 2171904 + }, + { + "epoch": 1.01, + "learning_rate": 1.4431020012932703e-05, + "loss": 3.8521, + "step": 2172416 + }, + { + "epoch": 1.01, + "learning_rate": 1.4422634065422183e-05, + "loss": 3.8649, + "step": 2172928 + }, + { + "epoch": 1.01, + "learning_rate": 1.4414248117911663e-05, + "loss": 3.8722, + "step": 2173440 + }, + { + "epoch": 1.01, + "learning_rate": 1.4405878549204876e-05, + "loss": 3.8678, + "step": 2173952 + }, + { + "epoch": 1.01, + "learning_rate": 1.4397492601694354e-05, + "loss": 3.8642, + "step": 2174464 + }, + { + "epoch": 1.01, + "learning_rate": 1.4389123032987566e-05, + "loss": 3.873, + "step": 2174976 + }, + { + "epoch": 1.01, + "learning_rate": 1.4380737085477048e-05, + "loss": 3.8605, + "step": 2175488 + }, + { + "epoch": 1.01, + "learning_rate": 1.4372351137966528e-05, + "loss": 3.8678, + "step": 2176000 + }, + { + "epoch": 1.01, + "learning_rate": 1.4363965190456005e-05, + "loss": 3.8609, + "step": 2176512 + }, + { + "epoch": 1.01, + "learning_rate": 1.4355579242945486e-05, + "loss": 3.8576, + "step": 2177024 + }, + { + "epoch": 1.01, + "learning_rate": 1.4347193295434966e-05, + "loss": 3.8624, + "step": 2177536 + }, + { + "epoch": 1.01, + "learning_rate": 1.4338807347924446e-05, + "loss": 3.8569, + "step": 2178048 + }, + { + "epoch": 1.01, + "learning_rate": 1.4330421400413926e-05, + "loss": 3.8733, + "step": 2178560 + }, + { + "epoch": 1.01, + "learning_rate": 1.4322035452903406e-05, + "loss": 3.8758, + "step": 2179072 + }, + { + "epoch": 1.01, + "learning_rate": 1.4313649505392884e-05, + "loss": 3.8672, + "step": 2179584 + }, + { + "epoch": 1.01, + "learning_rate": 1.4305263557882364e-05, + "loss": 3.8487, + "step": 2180096 + }, + { + "epoch": 1.01, + "learning_rate": 1.4296893989175578e-05, + "loss": 3.8657, + "step": 2180608 + }, + { + "epoch": 1.01, + "learning_rate": 1.4288508041665058e-05, + "loss": 3.8708, + "step": 2181120 + }, + { + "epoch": 1.01, + "learning_rate": 1.4280138472958268e-05, + "loss": 3.8628, + "step": 2181632 + }, + { + "epoch": 1.01, + "learning_rate": 1.427175252544775e-05, + "loss": 3.8684, + "step": 2182144 + }, + { + "epoch": 1.01, + "learning_rate": 1.4263366577937229e-05, + "loss": 3.8758, + "step": 2182656 + }, + { + "epoch": 1.02, + "learning_rate": 1.4254980630426709e-05, + "loss": 3.8666, + "step": 2183168 + }, + { + "epoch": 1.02, + "learning_rate": 1.4246594682916187e-05, + "loss": 3.8655, + "step": 2183680 + }, + { + "epoch": 1.02, + "learning_rate": 1.4238208735405667e-05, + "loss": 3.8584, + "step": 2184192 + }, + { + "epoch": 1.02, + "learning_rate": 1.4229822787895147e-05, + "loss": 3.8733, + "step": 2184704 + }, + { + "epoch": 1.02, + "learning_rate": 1.4221436840384627e-05, + "loss": 3.8681, + "step": 2185216 + }, + { + "epoch": 1.02, + "learning_rate": 1.4213050892874107e-05, + "loss": 3.8694, + "step": 2185728 + }, + { + "epoch": 1.02, + "learning_rate": 1.4204681324167318e-05, + "loss": 3.8627, + "step": 2186240 + }, + { + "epoch": 1.02, + "learning_rate": 1.4196295376656798e-05, + "loss": 3.8522, + "step": 2186752 + }, + { + "epoch": 1.02, + "learning_rate": 1.418790942914628e-05, + "loss": 3.8628, + "step": 2187264 + }, + { + "epoch": 1.02, + "learning_rate": 1.417952348163576e-05, + "loss": 3.8781, + "step": 2187776 + }, + { + "epoch": 1.02, + "learning_rate": 1.417113753412524e-05, + "loss": 3.8687, + "step": 2188288 + }, + { + "epoch": 1.02, + "learning_rate": 1.4162751586614718e-05, + "loss": 3.8559, + "step": 2188800 + }, + { + "epoch": 1.02, + "learning_rate": 1.4154365639104198e-05, + "loss": 3.8657, + "step": 2189312 + }, + { + "epoch": 1.02, + "learning_rate": 1.4145979691593678e-05, + "loss": 3.8588, + "step": 2189824 + }, + { + "epoch": 1.02, + "learning_rate": 1.413761012288689e-05, + "loss": 3.8627, + "step": 2190336 + }, + { + "epoch": 1.02, + "learning_rate": 1.4129224175376368e-05, + "loss": 3.8599, + "step": 2190848 + }, + { + "epoch": 1.02, + "learning_rate": 1.4120838227865848e-05, + "loss": 3.8557, + "step": 2191360 + }, + { + "epoch": 1.02, + "learning_rate": 1.4112452280355328e-05, + "loss": 3.8625, + "step": 2191872 + }, + { + "epoch": 1.02, + "learning_rate": 1.410406633284481e-05, + "loss": 3.865, + "step": 2192384 + }, + { + "epoch": 1.02, + "learning_rate": 1.4095696764138019e-05, + "loss": 3.8629, + "step": 2192896 + }, + { + "epoch": 1.02, + "learning_rate": 1.4087310816627499e-05, + "loss": 3.8579, + "step": 2193408 + }, + { + "epoch": 1.02, + "learning_rate": 1.407892486911698e-05, + "loss": 3.8598, + "step": 2193920 + }, + { + "epoch": 1.02, + "learning_rate": 1.407053892160646e-05, + "loss": 3.8694, + "step": 2194432 + }, + { + "epoch": 1.02, + "learning_rate": 1.4062169352899671e-05, + "loss": 3.8643, + "step": 2194944 + }, + { + "epoch": 1.02, + "learning_rate": 1.4053783405389151e-05, + "loss": 3.8681, + "step": 2195456 + }, + { + "epoch": 1.02, + "learning_rate": 1.4045397457878631e-05, + "loss": 3.8657, + "step": 2195968 + }, + { + "epoch": 1.02, + "learning_rate": 1.4037011510368111e-05, + "loss": 3.8667, + "step": 2196480 + }, + { + "epoch": 1.02, + "learning_rate": 1.4028641941661322e-05, + "loss": 3.8661, + "step": 2196992 + }, + { + "epoch": 1.02, + "learning_rate": 1.4020255994150802e-05, + "loss": 3.8588, + "step": 2197504 + }, + { + "epoch": 1.02, + "learning_rate": 1.4011870046640282e-05, + "loss": 3.8655, + "step": 2198016 + }, + { + "epoch": 1.02, + "learning_rate": 1.4003484099129764e-05, + "loss": 3.8658, + "step": 2198528 + }, + { + "epoch": 1.02, + "learning_rate": 1.3995114530422973e-05, + "loss": 3.854, + "step": 2199040 + }, + { + "epoch": 1.02, + "learning_rate": 1.3986728582912453e-05, + "loss": 3.8618, + "step": 2199552 + }, + { + "epoch": 1.02, + "learning_rate": 1.3978342635401934e-05, + "loss": 3.8572, + "step": 2200064 + }, + { + "epoch": 1.02, + "learning_rate": 1.3969956687891414e-05, + "loss": 3.8626, + "step": 2200576 + }, + { + "epoch": 1.02, + "learning_rate": 1.3961570740380894e-05, + "loss": 3.8635, + "step": 2201088 + }, + { + "epoch": 1.02, + "learning_rate": 1.3953201171674105e-05, + "loss": 3.8538, + "step": 2201600 + }, + { + "epoch": 1.02, + "learning_rate": 1.3944815224163585e-05, + "loss": 3.8559, + "step": 2202112 + }, + { + "epoch": 1.02, + "learning_rate": 1.3936445655456796e-05, + "loss": 3.8589, + "step": 2202624 + }, + { + "epoch": 1.02, + "learning_rate": 1.3928076086750008e-05, + "loss": 3.8766, + "step": 2203136 + }, + { + "epoch": 1.02, + "learning_rate": 1.3919690139239487e-05, + "loss": 3.8641, + "step": 2203648 + }, + { + "epoch": 1.02, + "learning_rate": 1.3911304191728966e-05, + "loss": 3.8659, + "step": 2204160 + }, + { + "epoch": 1.02, + "learning_rate": 1.3902918244218446e-05, + "loss": 3.859, + "step": 2204672 + }, + { + "epoch": 1.02, + "learning_rate": 1.3894532296707926e-05, + "loss": 3.8693, + "step": 2205184 + }, + { + "epoch": 1.02, + "learning_rate": 1.3886146349197406e-05, + "loss": 3.869, + "step": 2205696 + }, + { + "epoch": 1.02, + "learning_rate": 1.3877760401686888e-05, + "loss": 3.8724, + "step": 2206208 + }, + { + "epoch": 1.02, + "learning_rate": 1.3869374454176368e-05, + "loss": 3.872, + "step": 2206720 + }, + { + "epoch": 1.02, + "learning_rate": 1.3860988506665845e-05, + "loss": 3.8665, + "step": 2207232 + }, + { + "epoch": 1.02, + "learning_rate": 1.3852602559155326e-05, + "loss": 3.8714, + "step": 2207744 + }, + { + "epoch": 1.02, + "learning_rate": 1.3844232990448539e-05, + "loss": 3.876, + "step": 2208256 + }, + { + "epoch": 1.02, + "learning_rate": 1.3835847042938015e-05, + "loss": 3.8541, + "step": 2208768 + }, + { + "epoch": 1.02, + "learning_rate": 1.3827461095427497e-05, + "loss": 3.8698, + "step": 2209280 + }, + { + "epoch": 1.02, + "learning_rate": 1.3819075147916977e-05, + "loss": 3.8614, + "step": 2209792 + }, + { + "epoch": 1.02, + "learning_rate": 1.3810689200406457e-05, + "loss": 3.8645, + "step": 2210304 + }, + { + "epoch": 1.02, + "learning_rate": 1.3802303252895937e-05, + "loss": 3.8556, + "step": 2210816 + }, + { + "epoch": 1.02, + "learning_rate": 1.3793917305385418e-05, + "loss": 3.863, + "step": 2211328 + }, + { + "epoch": 1.02, + "learning_rate": 1.3785531357874898e-05, + "loss": 3.8585, + "step": 2211840 + }, + { + "epoch": 1.02, + "learning_rate": 1.3777145410364375e-05, + "loss": 3.8635, + "step": 2212352 + }, + { + "epoch": 1.02, + "learning_rate": 1.3768775841657589e-05, + "loss": 3.8668, + "step": 2212864 + }, + { + "epoch": 1.03, + "eval_loss": 3.978376626968384, + "eval_runtime": 293.1154, + "eval_samples_per_second": 1301.846, + "eval_steps_per_second": 40.684, + "step": 2213280 + }, + { + "epoch": 0.0, + "learning_rate": 1.3760389894147069e-05, + "loss": 3.877, + "step": 2213376 + }, + { + "epoch": 0.0, + "learning_rate": 1.3752003946636549e-05, + "loss": 3.8517, + "step": 2213888 + }, + { + "epoch": 0.0, + "learning_rate": 1.3743617999126027e-05, + "loss": 3.8591, + "step": 2214400 + }, + { + "epoch": 0.0, + "learning_rate": 1.3735232051615507e-05, + "loss": 3.8702, + "step": 2214912 + }, + { + "epoch": 0.0, + "learning_rate": 1.3726846104104987e-05, + "loss": 3.8635, + "step": 2215424 + }, + { + "epoch": 0.0, + "learning_rate": 1.3718460156594467e-05, + "loss": 3.8624, + "step": 2215936 + }, + { + "epoch": 0.0, + "learning_rate": 1.3710074209083947e-05, + "loss": 3.8633, + "step": 2216448 + }, + { + "epoch": 0.0, + "learning_rate": 1.3701688261573429e-05, + "loss": 3.8569, + "step": 2216960 + }, + { + "epoch": 0.0, + "learning_rate": 1.3693302314062905e-05, + "loss": 3.8575, + "step": 2217472 + }, + { + "epoch": 0.0, + "learning_rate": 1.3684916366552385e-05, + "loss": 3.8687, + "step": 2217984 + }, + { + "epoch": 0.0, + "learning_rate": 1.36765467978456e-05, + "loss": 3.8673, + "step": 2218496 + }, + { + "epoch": 0.0, + "learning_rate": 1.366816085033508e-05, + "loss": 3.8648, + "step": 2219008 + }, + { + "epoch": 0.0, + "learning_rate": 1.3659774902824558e-05, + "loss": 3.8763, + "step": 2219520 + }, + { + "epoch": 0.0, + "learning_rate": 1.3651388955314038e-05, + "loss": 3.8429, + "step": 2220032 + }, + { + "epoch": 0.0, + "learning_rate": 1.3643003007803518e-05, + "loss": 3.8609, + "step": 2220544 + }, + { + "epoch": 0.0, + "learning_rate": 1.3634617060292998e-05, + "loss": 3.8481, + "step": 2221056 + }, + { + "epoch": 0.0, + "learning_rate": 1.3626231112782477e-05, + "loss": 3.8656, + "step": 2221568 + }, + { + "epoch": 0.0, + "learning_rate": 1.3617845165271959e-05, + "loss": 3.8638, + "step": 2222080 + }, + { + "epoch": 0.0, + "learning_rate": 1.3609459217761439e-05, + "loss": 3.8538, + "step": 2222592 + }, + { + "epoch": 0.0, + "learning_rate": 1.3601073270250916e-05, + "loss": 3.8625, + "step": 2223104 + }, + { + "epoch": 0.0, + "learning_rate": 1.3592687322740397e-05, + "loss": 3.8839, + "step": 2223616 + }, + { + "epoch": 0.0, + "learning_rate": 1.3584301375229877e-05, + "loss": 3.864, + "step": 2224128 + }, + { + "epoch": 0.0, + "learning_rate": 1.3575915427719357e-05, + "loss": 3.8689, + "step": 2224640 + }, + { + "epoch": 0.0, + "learning_rate": 1.3567545859012568e-05, + "loss": 3.8706, + "step": 2225152 + }, + { + "epoch": 0.0, + "learning_rate": 1.3559159911502048e-05, + "loss": 3.8703, + "step": 2225664 + }, + { + "epoch": 0.0, + "learning_rate": 1.3550773963991528e-05, + "loss": 3.8589, + "step": 2226176 + }, + { + "epoch": 0.0, + "learning_rate": 1.3542388016481008e-05, + "loss": 3.8575, + "step": 2226688 + }, + { + "epoch": 0.0, + "learning_rate": 1.353400206897049e-05, + "loss": 3.8635, + "step": 2227200 + }, + { + "epoch": 0.0, + "learning_rate": 1.352561612145997e-05, + "loss": 3.8594, + "step": 2227712 + }, + { + "epoch": 0.0, + "learning_rate": 1.3517230173949446e-05, + "loss": 3.8599, + "step": 2228224 + }, + { + "epoch": 0.01, + "learning_rate": 1.3508844226438928e-05, + "loss": 3.8713, + "step": 2228736 + }, + { + "epoch": 0.01, + "learning_rate": 1.3500458278928408e-05, + "loss": 3.8679, + "step": 2229248 + }, + { + "epoch": 0.01, + "learning_rate": 1.3492105089025351e-05, + "loss": 3.8667, + "step": 2229760 + }, + { + "epoch": 0.01, + "learning_rate": 1.3483719141514831e-05, + "loss": 3.8715, + "step": 2230272 + }, + { + "epoch": 0.01, + "learning_rate": 1.3475333194004311e-05, + "loss": 3.8599, + "step": 2230784 + }, + { + "epoch": 0.01, + "learning_rate": 1.3466963625297522e-05, + "loss": 3.8692, + "step": 2231296 + }, + { + "epoch": 0.01, + "learning_rate": 1.3458577677787002e-05, + "loss": 3.8686, + "step": 2231808 + }, + { + "epoch": 0.01, + "learning_rate": 1.3450191730276482e-05, + "loss": 3.8463, + "step": 2232320 + }, + { + "epoch": 0.01, + "learning_rate": 1.3441805782765962e-05, + "loss": 3.8648, + "step": 2232832 + }, + { + "epoch": 0.01, + "learning_rate": 1.3433419835255443e-05, + "loss": 3.8552, + "step": 2233344 + }, + { + "epoch": 0.01, + "learning_rate": 1.3425050266548652e-05, + "loss": 3.8533, + "step": 2233856 + }, + { + "epoch": 0.01, + "learning_rate": 1.3416664319038132e-05, + "loss": 3.8654, + "step": 2234368 + }, + { + "epoch": 0.01, + "learning_rate": 1.3408278371527614e-05, + "loss": 3.8719, + "step": 2234880 + }, + { + "epoch": 0.01, + "learning_rate": 1.339989242401709e-05, + "loss": 3.8559, + "step": 2235392 + }, + { + "epoch": 0.01, + "learning_rate": 1.339150647650657e-05, + "loss": 3.8638, + "step": 2235904 + }, + { + "epoch": 0.01, + "learning_rate": 1.3383120528996052e-05, + "loss": 3.867, + "step": 2236416 + }, + { + "epoch": 0.01, + "learning_rate": 1.3374734581485532e-05, + "loss": 3.8576, + "step": 2236928 + }, + { + "epoch": 0.01, + "learning_rate": 1.3366348633975012e-05, + "loss": 3.8674, + "step": 2237440 + }, + { + "epoch": 0.01, + "learning_rate": 1.3357962686464492e-05, + "loss": 3.8474, + "step": 2237952 + }, + { + "epoch": 0.01, + "learning_rate": 1.3349576738953974e-05, + "loss": 3.8604, + "step": 2238464 + }, + { + "epoch": 0.01, + "learning_rate": 1.334119079144345e-05, + "loss": 3.8619, + "step": 2238976 + }, + { + "epoch": 0.01, + "learning_rate": 1.333280484393293e-05, + "loss": 3.872, + "step": 2239488 + }, + { + "epoch": 0.01, + "learning_rate": 1.3324435275226144e-05, + "loss": 3.8608, + "step": 2240000 + }, + { + "epoch": 0.01, + "learning_rate": 1.3316049327715624e-05, + "loss": 3.8517, + "step": 2240512 + }, + { + "epoch": 0.01, + "learning_rate": 1.33076633802051e-05, + "loss": 3.8554, + "step": 2241024 + }, + { + "epoch": 0.01, + "learning_rate": 1.3299277432694582e-05, + "loss": 3.8571, + "step": 2241536 + }, + { + "epoch": 0.01, + "learning_rate": 1.3290907863987795e-05, + "loss": 3.8717, + "step": 2242048 + }, + { + "epoch": 0.01, + "learning_rate": 1.3282521916477273e-05, + "loss": 3.8467, + "step": 2242560 + }, + { + "epoch": 0.01, + "learning_rate": 1.3274135968966753e-05, + "loss": 3.8724, + "step": 2243072 + }, + { + "epoch": 0.01, + "learning_rate": 1.3265750021456233e-05, + "loss": 3.86, + "step": 2243584 + }, + { + "epoch": 0.01, + "learning_rate": 1.3257380452749446e-05, + "loss": 3.8434, + "step": 2244096 + }, + { + "epoch": 0.01, + "learning_rate": 1.3248994505238924e-05, + "loss": 3.8667, + "step": 2244608 + }, + { + "epoch": 0.01, + "learning_rate": 1.3240608557728404e-05, + "loss": 3.8502, + "step": 2245120 + }, + { + "epoch": 0.01, + "learning_rate": 1.3232238989021616e-05, + "loss": 3.844, + "step": 2245632 + }, + { + "epoch": 0.01, + "learning_rate": 1.3223853041511098e-05, + "loss": 3.8518, + "step": 2246144 + }, + { + "epoch": 0.01, + "learning_rate": 1.3215467094000574e-05, + "loss": 3.8637, + "step": 2246656 + }, + { + "epoch": 0.01, + "learning_rate": 1.3207081146490054e-05, + "loss": 3.8581, + "step": 2247168 + }, + { + "epoch": 0.01, + "learning_rate": 1.3198695198979536e-05, + "loss": 3.8535, + "step": 2247680 + }, + { + "epoch": 0.01, + "learning_rate": 1.3190309251469016e-05, + "loss": 3.8508, + "step": 2248192 + }, + { + "epoch": 0.01, + "learning_rate": 1.3181923303958496e-05, + "loss": 3.8493, + "step": 2248704 + }, + { + "epoch": 0.01, + "learning_rate": 1.3173553735251707e-05, + "loss": 3.8617, + "step": 2249216 + }, + { + "epoch": 0.01, + "learning_rate": 1.316518416654492e-05, + "loss": 3.8637, + "step": 2249728 + }, + { + "epoch": 0.01, + "learning_rate": 1.3156798219034398e-05, + "loss": 3.8611, + "step": 2250240 + }, + { + "epoch": 0.01, + "learning_rate": 1.3148412271523878e-05, + "loss": 3.8683, + "step": 2250752 + }, + { + "epoch": 0.01, + "learning_rate": 1.3140026324013357e-05, + "loss": 3.8647, + "step": 2251264 + }, + { + "epoch": 0.01, + "learning_rate": 1.3131640376502837e-05, + "loss": 3.8554, + "step": 2251776 + }, + { + "epoch": 0.01, + "learning_rate": 1.3123270807796048e-05, + "loss": 3.8624, + "step": 2252288 + }, + { + "epoch": 0.01, + "learning_rate": 1.3114884860285528e-05, + "loss": 3.8577, + "step": 2252800 + }, + { + "epoch": 0.01, + "learning_rate": 1.3106498912775008e-05, + "loss": 3.8575, + "step": 2253312 + }, + { + "epoch": 0.01, + "learning_rate": 1.309811296526449e-05, + "loss": 3.8545, + "step": 2253824 + }, + { + "epoch": 0.01, + "learning_rate": 1.308972701775397e-05, + "loss": 3.8559, + "step": 2254336 + }, + { + "epoch": 0.01, + "learning_rate": 1.308134107024345e-05, + "loss": 3.8695, + "step": 2254848 + }, + { + "epoch": 0.01, + "learning_rate": 1.3072955122732928e-05, + "loss": 3.871, + "step": 2255360 + }, + { + "epoch": 0.01, + "learning_rate": 1.3064569175222408e-05, + "loss": 3.864, + "step": 2255872 + }, + { + "epoch": 0.01, + "learning_rate": 1.3056183227711888e-05, + "loss": 3.8434, + "step": 2256384 + }, + { + "epoch": 0.01, + "learning_rate": 1.3047797280201368e-05, + "loss": 3.8609, + "step": 2256896 + }, + { + "epoch": 0.01, + "learning_rate": 1.3039411332690848e-05, + "loss": 3.8672, + "step": 2257408 + }, + { + "epoch": 0.01, + "learning_rate": 1.3031041763984059e-05, + "loss": 3.862, + "step": 2257920 + }, + { + "epoch": 0.01, + "learning_rate": 1.3022655816473539e-05, + "loss": 3.8616, + "step": 2258432 + }, + { + "epoch": 0.01, + "learning_rate": 1.301426986896302e-05, + "loss": 3.8713, + "step": 2258944 + }, + { + "epoch": 0.02, + "learning_rate": 1.30058839214525e-05, + "loss": 3.8631, + "step": 2259456 + }, + { + "epoch": 0.02, + "learning_rate": 1.299749797394198e-05, + "loss": 3.8623, + "step": 2259968 + }, + { + "epoch": 0.02, + "learning_rate": 1.2989128405235191e-05, + "loss": 3.8589, + "step": 2260480 + }, + { + "epoch": 0.02, + "learning_rate": 1.298074245772467e-05, + "loss": 3.8678, + "step": 2260992 + }, + { + "epoch": 0.02, + "learning_rate": 1.297235651021415e-05, + "loss": 3.8642, + "step": 2261504 + }, + { + "epoch": 0.02, + "learning_rate": 1.296397056270363e-05, + "loss": 3.8709, + "step": 2262016 + }, + { + "epoch": 0.02, + "learning_rate": 1.2955584615193109e-05, + "loss": 3.8562, + "step": 2262528 + }, + { + "epoch": 0.02, + "learning_rate": 1.2947215046486321e-05, + "loss": 3.8518, + "step": 2263040 + }, + { + "epoch": 0.02, + "learning_rate": 1.2938829098975801e-05, + "loss": 3.8572, + "step": 2263552 + }, + { + "epoch": 0.02, + "learning_rate": 1.2930443151465283e-05, + "loss": 3.8715, + "step": 2264064 + }, + { + "epoch": 0.02, + "learning_rate": 1.2922073582758492e-05, + "loss": 3.8651, + "step": 2264576 + }, + { + "epoch": 0.02, + "learning_rate": 1.2913687635247974e-05, + "loss": 3.8528, + "step": 2265088 + }, + { + "epoch": 0.02, + "learning_rate": 1.2905301687737454e-05, + "loss": 3.8597, + "step": 2265600 + }, + { + "epoch": 0.02, + "learning_rate": 1.289691574022693e-05, + "loss": 3.853, + "step": 2266112 + }, + { + "epoch": 0.02, + "learning_rate": 1.288852979271641e-05, + "loss": 3.8593, + "step": 2266624 + }, + { + "epoch": 0.02, + "learning_rate": 1.2880143845205892e-05, + "loss": 3.8547, + "step": 2267136 + }, + { + "epoch": 0.02, + "learning_rate": 1.2871757897695372e-05, + "loss": 3.8539, + "step": 2267648 + }, + { + "epoch": 0.02, + "learning_rate": 1.2863388328988583e-05, + "loss": 3.8616, + "step": 2268160 + }, + { + "epoch": 0.02, + "learning_rate": 1.2855002381478063e-05, + "loss": 3.8597, + "step": 2268672 + }, + { + "epoch": 0.02, + "learning_rate": 1.2846616433967543e-05, + "loss": 3.8563, + "step": 2269184 + }, + { + "epoch": 0.02, + "learning_rate": 1.2838230486457023e-05, + "loss": 3.8556, + "step": 2269696 + }, + { + "epoch": 0.02, + "learning_rate": 1.2829844538946503e-05, + "loss": 3.8566, + "step": 2270208 + }, + { + "epoch": 0.02, + "learning_rate": 1.2821458591435984e-05, + "loss": 3.8647, + "step": 2270720 + }, + { + "epoch": 0.02, + "learning_rate": 1.2813072643925464e-05, + "loss": 3.8618, + "step": 2271232 + }, + { + "epoch": 0.02, + "learning_rate": 1.280468669641494e-05, + "loss": 3.8661, + "step": 2271744 + }, + { + "epoch": 0.02, + "learning_rate": 1.2796317127708155e-05, + "loss": 3.8569, + "step": 2272256 + }, + { + "epoch": 0.02, + "learning_rate": 1.2787931180197635e-05, + "loss": 3.8659, + "step": 2272768 + }, + { + "epoch": 0.02, + "learning_rate": 1.2779545232687113e-05, + "loss": 3.8597, + "step": 2273280 + }, + { + "epoch": 0.02, + "learning_rate": 1.2771159285176593e-05, + "loss": 3.854, + "step": 2273792 + }, + { + "epoch": 0.02, + "learning_rate": 1.2762789716469806e-05, + "loss": 3.8645, + "step": 2274304 + }, + { + "epoch": 0.02, + "learning_rate": 1.2754403768959285e-05, + "loss": 3.8608, + "step": 2274816 + }, + { + "epoch": 0.02, + "learning_rate": 1.2746017821448764e-05, + "loss": 3.8515, + "step": 2275328 + }, + { + "epoch": 0.02, + "learning_rate": 1.2737631873938244e-05, + "loss": 3.8555, + "step": 2275840 + }, + { + "epoch": 0.02, + "learning_rate": 1.2729245926427724e-05, + "loss": 3.857, + "step": 2276352 + }, + { + "epoch": 0.02, + "learning_rate": 1.2720859978917205e-05, + "loss": 3.8608, + "step": 2276864 + }, + { + "epoch": 0.02, + "learning_rate": 1.2712474031406685e-05, + "loss": 3.8547, + "step": 2277376 + }, + { + "epoch": 0.02, + "learning_rate": 1.2704088083896165e-05, + "loss": 3.8536, + "step": 2277888 + }, + { + "epoch": 0.02, + "learning_rate": 1.2695702136385645e-05, + "loss": 3.8527, + "step": 2278400 + }, + { + "epoch": 0.02, + "learning_rate": 1.2687332567678856e-05, + "loss": 3.8567, + "step": 2278912 + }, + { + "epoch": 0.02, + "learning_rate": 1.2678946620168336e-05, + "loss": 3.873, + "step": 2279424 + }, + { + "epoch": 0.02, + "learning_rate": 1.2670560672657816e-05, + "loss": 3.8628, + "step": 2279936 + }, + { + "epoch": 0.02, + "learning_rate": 1.2662174725147294e-05, + "loss": 3.8623, + "step": 2280448 + }, + { + "epoch": 0.02, + "learning_rate": 1.2653805156440507e-05, + "loss": 3.853, + "step": 2280960 + }, + { + "epoch": 0.02, + "learning_rate": 1.2645419208929987e-05, + "loss": 3.8681, + "step": 2281472 + }, + { + "epoch": 0.02, + "learning_rate": 1.2637033261419468e-05, + "loss": 3.8671, + "step": 2281984 + }, + { + "epoch": 0.02, + "learning_rate": 1.2628647313908945e-05, + "loss": 3.8683, + "step": 2282496 + }, + { + "epoch": 0.02, + "learning_rate": 1.2620261366398425e-05, + "loss": 3.864, + "step": 2283008 + }, + { + "epoch": 0.02, + "learning_rate": 1.2611875418887906e-05, + "loss": 3.8636, + "step": 2283520 + }, + { + "epoch": 0.02, + "learning_rate": 1.2603505850181119e-05, + "loss": 3.87, + "step": 2284032 + }, + { + "epoch": 0.02, + "learning_rate": 1.2595119902670595e-05, + "loss": 3.8724, + "step": 2284544 + }, + { + "epoch": 0.02, + "learning_rate": 1.2586733955160077e-05, + "loss": 3.8519, + "step": 2285056 + }, + { + "epoch": 0.02, + "learning_rate": 1.2578348007649557e-05, + "loss": 3.8628, + "step": 2285568 + }, + { + "epoch": 0.02, + "learning_rate": 1.2569962060139037e-05, + "loss": 3.8595, + "step": 2286080 + }, + { + "epoch": 0.02, + "learning_rate": 1.2561576112628517e-05, + "loss": 3.8611, + "step": 2286592 + }, + { + "epoch": 0.02, + "learning_rate": 1.2553190165117999e-05, + "loss": 3.8509, + "step": 2287104 + }, + { + "epoch": 0.02, + "learning_rate": 1.2544804217607475e-05, + "loss": 3.8597, + "step": 2287616 + }, + { + "epoch": 0.02, + "learning_rate": 1.2536434648900688e-05, + "loss": 3.8509, + "step": 2288128 + }, + { + "epoch": 0.02, + "learning_rate": 1.252804870139017e-05, + "loss": 3.866, + "step": 2288640 + }, + { + "epoch": 0.02, + "learning_rate": 1.251966275387965e-05, + "loss": 3.8576, + "step": 2289152 + }, + { + "epoch": 0.03, + "eval_loss": 3.9773764610290527, + "eval_runtime": 292.6886, + "eval_samples_per_second": 1303.744, + "eval_steps_per_second": 40.743, + "step": 2289600 + }, + { + "epoch": 1.0, + "learning_rate": 1.2511276806369126e-05, + "loss": 3.8632, + "step": 2289664 + }, + { + "epoch": 1.0, + "learning_rate": 1.250290723766234e-05, + "loss": 3.8512, + "step": 2290176 + }, + { + "epoch": 1.0, + "learning_rate": 1.2494521290151818e-05, + "loss": 3.8544, + "step": 2290688 + }, + { + "epoch": 1.0, + "learning_rate": 1.2486135342641298e-05, + "loss": 3.8659, + "step": 2291200 + }, + { + "epoch": 1.0, + "learning_rate": 1.247774939513078e-05, + "loss": 3.8612, + "step": 2291712 + }, + { + "epoch": 1.0, + "learning_rate": 1.2469363447620258e-05, + "loss": 3.8584, + "step": 2292224 + }, + { + "epoch": 1.0, + "learning_rate": 1.2460977500109738e-05, + "loss": 3.8553, + "step": 2292736 + }, + { + "epoch": 1.0, + "learning_rate": 1.2452591552599218e-05, + "loss": 3.8521, + "step": 2293248 + }, + { + "epoch": 1.0, + "learning_rate": 1.244422198389243e-05, + "loss": 3.8542, + "step": 2293760 + }, + { + "epoch": 1.0, + "learning_rate": 1.2435836036381909e-05, + "loss": 3.8663, + "step": 2294272 + }, + { + "epoch": 1.0, + "learning_rate": 1.242745008887139e-05, + "loss": 3.8631, + "step": 2294784 + }, + { + "epoch": 1.0, + "learning_rate": 1.241906414136087e-05, + "loss": 3.8619, + "step": 2295296 + }, + { + "epoch": 1.0, + "learning_rate": 1.2410694572654081e-05, + "loss": 3.8704, + "step": 2295808 + }, + { + "epoch": 1.0, + "learning_rate": 1.2402308625143561e-05, + "loss": 3.8416, + "step": 2296320 + }, + { + "epoch": 1.0, + "learning_rate": 1.2393922677633041e-05, + "loss": 3.8546, + "step": 2296832 + }, + { + "epoch": 1.0, + "learning_rate": 1.2385536730122521e-05, + "loss": 3.8487, + "step": 2297344 + }, + { + "epoch": 1.0, + "learning_rate": 1.2377150782612e-05, + "loss": 3.8604, + "step": 2297856 + }, + { + "epoch": 1.0, + "learning_rate": 1.2368781213905212e-05, + "loss": 3.8553, + "step": 2298368 + }, + { + "epoch": 1.0, + "learning_rate": 1.2360395266394692e-05, + "loss": 3.8532, + "step": 2298880 + }, + { + "epoch": 1.0, + "learning_rate": 1.2352009318884172e-05, + "loss": 3.8578, + "step": 2299392 + }, + { + "epoch": 1.0, + "learning_rate": 1.2343623371373652e-05, + "loss": 3.8775, + "step": 2299904 + }, + { + "epoch": 1.0, + "learning_rate": 1.2335237423863132e-05, + "loss": 3.8614, + "step": 2300416 + }, + { + "epoch": 1.0, + "learning_rate": 1.2326851476352612e-05, + "loss": 3.8623, + "step": 2300928 + }, + { + "epoch": 1.0, + "learning_rate": 1.2318465528842092e-05, + "loss": 3.8631, + "step": 2301440 + }, + { + "epoch": 1.0, + "learning_rate": 1.2310079581331572e-05, + "loss": 3.8715, + "step": 2301952 + }, + { + "epoch": 1.0, + "learning_rate": 1.2301693633821051e-05, + "loss": 3.8498, + "step": 2302464 + }, + { + "epoch": 1.0, + "learning_rate": 1.2293324065114262e-05, + "loss": 3.8553, + "step": 2302976 + }, + { + "epoch": 1.0, + "learning_rate": 1.2284938117603742e-05, + "loss": 3.8636, + "step": 2303488 + }, + { + "epoch": 1.0, + "learning_rate": 1.2276552170093222e-05, + "loss": 3.8516, + "step": 2304000 + }, + { + "epoch": 1.0, + "learning_rate": 1.2268166222582702e-05, + "loss": 3.8566, + "step": 2304512 + }, + { + "epoch": 1.01, + "learning_rate": 1.2259780275072182e-05, + "loss": 3.8629, + "step": 2305024 + }, + { + "epoch": 1.01, + "learning_rate": 1.2251410706365393e-05, + "loss": 3.866, + "step": 2305536 + }, + { + "epoch": 1.01, + "learning_rate": 1.2243024758854873e-05, + "loss": 3.8636, + "step": 2306048 + }, + { + "epoch": 1.01, + "learning_rate": 1.2234638811344353e-05, + "loss": 3.8659, + "step": 2306560 + }, + { + "epoch": 1.01, + "learning_rate": 1.2226252863833833e-05, + "loss": 3.8553, + "step": 2307072 + }, + { + "epoch": 1.01, + "learning_rate": 1.2217899673930776e-05, + "loss": 3.869, + "step": 2307584 + }, + { + "epoch": 1.01, + "learning_rate": 1.2209513726420256e-05, + "loss": 3.8597, + "step": 2308096 + }, + { + "epoch": 1.01, + "learning_rate": 1.2201127778909734e-05, + "loss": 3.8446, + "step": 2308608 + }, + { + "epoch": 1.01, + "learning_rate": 1.2192741831399216e-05, + "loss": 3.862, + "step": 2309120 + }, + { + "epoch": 1.01, + "learning_rate": 1.2184355883888696e-05, + "loss": 3.8476, + "step": 2309632 + }, + { + "epoch": 1.01, + "learning_rate": 1.2175969936378176e-05, + "loss": 3.85, + "step": 2310144 + }, + { + "epoch": 1.01, + "learning_rate": 1.2167583988867654e-05, + "loss": 3.8604, + "step": 2310656 + }, + { + "epoch": 1.01, + "learning_rate": 1.2159198041357136e-05, + "loss": 3.8667, + "step": 2311168 + }, + { + "epoch": 1.01, + "learning_rate": 1.2150812093846616e-05, + "loss": 3.8491, + "step": 2311680 + }, + { + "epoch": 1.01, + "learning_rate": 1.2142426146336094e-05, + "loss": 3.8636, + "step": 2312192 + }, + { + "epoch": 1.01, + "learning_rate": 1.2134056577629306e-05, + "loss": 3.8609, + "step": 2312704 + }, + { + "epoch": 1.01, + "learning_rate": 1.2125670630118786e-05, + "loss": 3.8585, + "step": 2313216 + }, + { + "epoch": 1.01, + "learning_rate": 1.2117284682608266e-05, + "loss": 3.8622, + "step": 2313728 + }, + { + "epoch": 1.01, + "learning_rate": 1.2108898735097746e-05, + "loss": 3.8447, + "step": 2314240 + }, + { + "epoch": 1.01, + "learning_rate": 1.2100512787587226e-05, + "loss": 3.8568, + "step": 2314752 + }, + { + "epoch": 1.01, + "learning_rate": 1.2092143218880437e-05, + "loss": 3.8581, + "step": 2315264 + }, + { + "epoch": 1.01, + "learning_rate": 1.2083757271369917e-05, + "loss": 3.8635, + "step": 2315776 + }, + { + "epoch": 1.01, + "learning_rate": 1.2075371323859397e-05, + "loss": 3.8583, + "step": 2316288 + }, + { + "epoch": 1.01, + "learning_rate": 1.2066985376348877e-05, + "loss": 3.844, + "step": 2316800 + }, + { + "epoch": 1.01, + "learning_rate": 1.2058599428838357e-05, + "loss": 3.8501, + "step": 2317312 + }, + { + "epoch": 1.01, + "learning_rate": 1.2050213481327837e-05, + "loss": 3.8524, + "step": 2317824 + }, + { + "epoch": 1.01, + "learning_rate": 1.2041827533817317e-05, + "loss": 3.8718, + "step": 2318336 + }, + { + "epoch": 1.01, + "learning_rate": 1.2033457965110528e-05, + "loss": 3.8387, + "step": 2318848 + }, + { + "epoch": 1.01, + "learning_rate": 1.2025072017600008e-05, + "loss": 3.8669, + "step": 2319360 + }, + { + "epoch": 1.01, + "learning_rate": 1.2016686070089487e-05, + "loss": 3.8567, + "step": 2319872 + }, + { + "epoch": 1.01, + "learning_rate": 1.2008300122578967e-05, + "loss": 3.8412, + "step": 2320384 + }, + { + "epoch": 1.01, + "learning_rate": 1.199993055387218e-05, + "loss": 3.8608, + "step": 2320896 + }, + { + "epoch": 1.01, + "learning_rate": 1.1991544606361658e-05, + "loss": 3.8512, + "step": 2321408 + }, + { + "epoch": 1.01, + "learning_rate": 1.1983158658851138e-05, + "loss": 3.8417, + "step": 2321920 + }, + { + "epoch": 1.01, + "learning_rate": 1.197477271134062e-05, + "loss": 3.8435, + "step": 2322432 + }, + { + "epoch": 1.01, + "learning_rate": 1.1966386763830098e-05, + "loss": 3.8633, + "step": 2322944 + }, + { + "epoch": 1.01, + "learning_rate": 1.1958000816319578e-05, + "loss": 3.8545, + "step": 2323456 + }, + { + "epoch": 1.01, + "learning_rate": 1.1949614868809058e-05, + "loss": 3.8473, + "step": 2323968 + }, + { + "epoch": 1.01, + "learning_rate": 1.194124530010227e-05, + "loss": 3.8421, + "step": 2324480 + }, + { + "epoch": 1.01, + "learning_rate": 1.1932859352591749e-05, + "loss": 3.8467, + "step": 2324992 + }, + { + "epoch": 1.01, + "learning_rate": 1.192447340508123e-05, + "loss": 3.8587, + "step": 2325504 + }, + { + "epoch": 1.01, + "learning_rate": 1.191608745757071e-05, + "loss": 3.8589, + "step": 2326016 + }, + { + "epoch": 1.01, + "learning_rate": 1.1907701510060189e-05, + "loss": 3.8584, + "step": 2326528 + }, + { + "epoch": 1.01, + "learning_rate": 1.1899315562549669e-05, + "loss": 3.8626, + "step": 2327040 + }, + { + "epoch": 1.01, + "learning_rate": 1.189092961503915e-05, + "loss": 3.861, + "step": 2327552 + }, + { + "epoch": 1.01, + "learning_rate": 1.188254366752863e-05, + "loss": 3.8587, + "step": 2328064 + }, + { + "epoch": 1.01, + "learning_rate": 1.1874157720018108e-05, + "loss": 3.8557, + "step": 2328576 + }, + { + "epoch": 1.01, + "learning_rate": 1.1865771772507588e-05, + "loss": 3.8507, + "step": 2329088 + }, + { + "epoch": 1.01, + "learning_rate": 1.1857402203800801e-05, + "loss": 3.855, + "step": 2329600 + }, + { + "epoch": 1.01, + "learning_rate": 1.1849016256290279e-05, + "loss": 3.854, + "step": 2330112 + }, + { + "epoch": 1.01, + "learning_rate": 1.1840630308779759e-05, + "loss": 3.8533, + "step": 2330624 + }, + { + "epoch": 1.01, + "learning_rate": 1.183224436126924e-05, + "loss": 3.8607, + "step": 2331136 + }, + { + "epoch": 1.01, + "learning_rate": 1.182385841375872e-05, + "loss": 3.8703, + "step": 2331648 + }, + { + "epoch": 1.01, + "learning_rate": 1.1815488845051931e-05, + "loss": 3.8584, + "step": 2332160 + }, + { + "epoch": 1.01, + "learning_rate": 1.1807102897541411e-05, + "loss": 3.8405, + "step": 2332672 + }, + { + "epoch": 1.01, + "learning_rate": 1.1798716950030891e-05, + "loss": 3.8574, + "step": 2333184 + }, + { + "epoch": 1.01, + "learning_rate": 1.179033100252037e-05, + "loss": 3.8608, + "step": 2333696 + }, + { + "epoch": 1.01, + "learning_rate": 1.1781945055009851e-05, + "loss": 3.8617, + "step": 2334208 + }, + { + "epoch": 1.01, + "learning_rate": 1.1773559107499331e-05, + "loss": 3.8533, + "step": 2334720 + }, + { + "epoch": 1.01, + "learning_rate": 1.1765173159988811e-05, + "loss": 3.8704, + "step": 2335232 + }, + { + "epoch": 1.02, + "learning_rate": 1.175678721247829e-05, + "loss": 3.8607, + "step": 2335744 + }, + { + "epoch": 1.02, + "learning_rate": 1.1748434022575233e-05, + "loss": 3.8549, + "step": 2336256 + }, + { + "epoch": 1.02, + "learning_rate": 1.1740048075064713e-05, + "loss": 3.8537, + "step": 2336768 + }, + { + "epoch": 1.02, + "learning_rate": 1.1731662127554193e-05, + "loss": 3.8658, + "step": 2337280 + }, + { + "epoch": 1.02, + "learning_rate": 1.1723276180043673e-05, + "loss": 3.857, + "step": 2337792 + }, + { + "epoch": 1.02, + "learning_rate": 1.1714890232533153e-05, + "loss": 3.8659, + "step": 2338304 + }, + { + "epoch": 1.02, + "learning_rate": 1.1706504285022633e-05, + "loss": 3.8517, + "step": 2338816 + }, + { + "epoch": 1.02, + "learning_rate": 1.1698134716315843e-05, + "loss": 3.8491, + "step": 2339328 + }, + { + "epoch": 1.02, + "learning_rate": 1.1689748768805323e-05, + "loss": 3.855, + "step": 2339840 + }, + { + "epoch": 1.02, + "learning_rate": 1.1681362821294805e-05, + "loss": 3.8679, + "step": 2340352 + }, + { + "epoch": 1.02, + "learning_rate": 1.1672976873784283e-05, + "loss": 3.8619, + "step": 2340864 + }, + { + "epoch": 1.02, + "learning_rate": 1.1664590926273763e-05, + "loss": 3.8527, + "step": 2341376 + }, + { + "epoch": 1.02, + "learning_rate": 1.1656221357566976e-05, + "loss": 3.853, + "step": 2341888 + }, + { + "epoch": 1.02, + "learning_rate": 1.1647835410056456e-05, + "loss": 3.8475, + "step": 2342400 + }, + { + "epoch": 1.02, + "learning_rate": 1.1639449462545934e-05, + "loss": 3.8609, + "step": 2342912 + }, + { + "epoch": 1.02, + "learning_rate": 1.1631063515035416e-05, + "loss": 3.8494, + "step": 2343424 + }, + { + "epoch": 1.02, + "learning_rate": 1.1622693946328626e-05, + "loss": 3.8488, + "step": 2343936 + }, + { + "epoch": 1.02, + "learning_rate": 1.1614307998818106e-05, + "loss": 3.8577, + "step": 2344448 + }, + { + "epoch": 1.02, + "learning_rate": 1.1605922051307586e-05, + "loss": 3.8572, + "step": 2344960 + }, + { + "epoch": 1.02, + "learning_rate": 1.1597536103797066e-05, + "loss": 3.8567, + "step": 2345472 + }, + { + "epoch": 1.02, + "learning_rate": 1.1589150156286546e-05, + "loss": 3.8549, + "step": 2345984 + }, + { + "epoch": 1.02, + "learning_rate": 1.1580780587579757e-05, + "loss": 3.8482, + "step": 2346496 + }, + { + "epoch": 1.02, + "learning_rate": 1.1572394640069237e-05, + "loss": 3.8592, + "step": 2347008 + }, + { + "epoch": 1.02, + "learning_rate": 1.1564008692558717e-05, + "loss": 3.8602, + "step": 2347520 + }, + { + "epoch": 1.02, + "learning_rate": 1.1555622745048197e-05, + "loss": 3.8559, + "step": 2348032 + }, + { + "epoch": 1.02, + "learning_rate": 1.1547236797537677e-05, + "loss": 3.8612, + "step": 2348544 + }, + { + "epoch": 1.02, + "learning_rate": 1.1538850850027157e-05, + "loss": 3.8633, + "step": 2349056 + }, + { + "epoch": 1.02, + "learning_rate": 1.1530464902516637e-05, + "loss": 3.8547, + "step": 2349568 + }, + { + "epoch": 1.02, + "learning_rate": 1.1522095333809847e-05, + "loss": 3.8507, + "step": 2350080 + }, + { + "epoch": 1.02, + "learning_rate": 1.1513709386299327e-05, + "loss": 3.8615, + "step": 2350592 + }, + { + "epoch": 1.02, + "learning_rate": 1.1505323438788807e-05, + "loss": 3.8542, + "step": 2351104 + }, + { + "epoch": 1.02, + "learning_rate": 1.1496937491278289e-05, + "loss": 3.8479, + "step": 2351616 + }, + { + "epoch": 1.02, + "learning_rate": 1.1488567922571498e-05, + "loss": 3.8544, + "step": 2352128 + }, + { + "epoch": 1.02, + "learning_rate": 1.1480181975060978e-05, + "loss": 3.8509, + "step": 2352640 + }, + { + "epoch": 1.02, + "learning_rate": 1.147179602755046e-05, + "loss": 3.8579, + "step": 2353152 + }, + { + "epoch": 1.02, + "learning_rate": 1.1463410080039938e-05, + "loss": 3.8445, + "step": 2353664 + }, + { + "epoch": 1.02, + "learning_rate": 1.1455024132529418e-05, + "loss": 3.8575, + "step": 2354176 + }, + { + "epoch": 1.02, + "learning_rate": 1.144665456382263e-05, + "loss": 3.8487, + "step": 2354688 + }, + { + "epoch": 1.02, + "learning_rate": 1.143826861631211e-05, + "loss": 3.8531, + "step": 2355200 + }, + { + "epoch": 1.02, + "learning_rate": 1.1429899047605321e-05, + "loss": 3.8608, + "step": 2355712 + }, + { + "epoch": 1.02, + "learning_rate": 1.1421513100094801e-05, + "loss": 3.864, + "step": 2356224 + }, + { + "epoch": 1.02, + "learning_rate": 1.1413127152584281e-05, + "loss": 3.8577, + "step": 2356736 + }, + { + "epoch": 1.02, + "learning_rate": 1.1404741205073761e-05, + "loss": 3.8501, + "step": 2357248 + }, + { + "epoch": 1.02, + "learning_rate": 1.1396355257563241e-05, + "loss": 3.8642, + "step": 2357760 + }, + { + "epoch": 1.02, + "learning_rate": 1.1387969310052721e-05, + "loss": 3.8602, + "step": 2358272 + }, + { + "epoch": 1.02, + "learning_rate": 1.1379583362542201e-05, + "loss": 3.8632, + "step": 2358784 + }, + { + "epoch": 1.02, + "learning_rate": 1.1371197415031679e-05, + "loss": 3.8622, + "step": 2359296 + }, + { + "epoch": 1.02, + "learning_rate": 1.1362827846324892e-05, + "loss": 3.8593, + "step": 2359808 + }, + { + "epoch": 1.02, + "learning_rate": 1.1354441898814372e-05, + "loss": 3.8676, + "step": 2360320 + }, + { + "epoch": 1.02, + "learning_rate": 1.1346055951303852e-05, + "loss": 3.8657, + "step": 2360832 + }, + { + "epoch": 1.02, + "learning_rate": 1.1337670003793332e-05, + "loss": 3.848, + "step": 2361344 + }, + { + "epoch": 1.02, + "learning_rate": 1.1329284056282811e-05, + "loss": 3.8579, + "step": 2361856 + }, + { + "epoch": 1.02, + "learning_rate": 1.1320914487576024e-05, + "loss": 3.8559, + "step": 2362368 + }, + { + "epoch": 1.02, + "learning_rate": 1.1312528540065502e-05, + "loss": 3.8552, + "step": 2362880 + }, + { + "epoch": 1.02, + "learning_rate": 1.1304158971358713e-05, + "loss": 3.852, + "step": 2363392 + }, + { + "epoch": 1.02, + "learning_rate": 1.1295773023848195e-05, + "loss": 3.8547, + "step": 2363904 + }, + { + "epoch": 1.02, + "learning_rate": 1.1287387076337675e-05, + "loss": 3.8483, + "step": 2364416 + }, + { + "epoch": 1.02, + "learning_rate": 1.1279001128827153e-05, + "loss": 3.8638, + "step": 2364928 + }, + { + "epoch": 1.02, + "learning_rate": 1.1270615181316633e-05, + "loss": 3.8531, + "step": 2365440 + }, + { + "epoch": 1.03, + "eval_loss": 3.9758923053741455, + "eval_runtime": 291.828, + "eval_samples_per_second": 1307.589, + "eval_steps_per_second": 40.863, + "step": 2365920 + }, + { + "epoch": 0.0, + "learning_rate": 1.1262229233806114e-05, + "loss": 3.8174, + "step": 2365952 + }, + { + "epoch": 0.0, + "learning_rate": 1.1253843286295593e-05, + "loss": 3.8525, + "step": 2366464 + }, + { + "epoch": 0.0, + "learning_rate": 1.1245457338785073e-05, + "loss": 3.8466, + "step": 2366976 + }, + { + "epoch": 0.0, + "learning_rate": 1.1237071391274553e-05, + "loss": 3.8621, + "step": 2367488 + }, + { + "epoch": 0.0, + "learning_rate": 1.1228685443764034e-05, + "loss": 3.8584, + "step": 2368000 + }, + { + "epoch": 0.0, + "learning_rate": 1.1220299496253513e-05, + "loss": 3.8562, + "step": 2368512 + }, + { + "epoch": 0.0, + "learning_rate": 1.1211913548742993e-05, + "loss": 3.8502, + "step": 2369024 + }, + { + "epoch": 0.0, + "learning_rate": 1.1203527601232472e-05, + "loss": 3.8468, + "step": 2369536 + }, + { + "epoch": 0.0, + "learning_rate": 1.1195141653721952e-05, + "loss": 3.8556, + "step": 2370048 + }, + { + "epoch": 0.0, + "learning_rate": 1.1186755706211432e-05, + "loss": 3.8587, + "step": 2370560 + }, + { + "epoch": 0.0, + "learning_rate": 1.1178369758700912e-05, + "loss": 3.8592, + "step": 2371072 + }, + { + "epoch": 0.0, + "learning_rate": 1.1169983811190392e-05, + "loss": 3.8567, + "step": 2371584 + }, + { + "epoch": 0.0, + "learning_rate": 1.1161597863679872e-05, + "loss": 3.8677, + "step": 2372096 + }, + { + "epoch": 0.0, + "learning_rate": 1.1153211916169352e-05, + "loss": 3.8379, + "step": 2372608 + }, + { + "epoch": 0.0, + "learning_rate": 1.1144825968658832e-05, + "loss": 3.8522, + "step": 2373120 + }, + { + "epoch": 0.0, + "learning_rate": 1.1136440021148312e-05, + "loss": 3.8459, + "step": 2373632 + }, + { + "epoch": 0.0, + "learning_rate": 1.1128054073637792e-05, + "loss": 3.8531, + "step": 2374144 + }, + { + "epoch": 0.0, + "learning_rate": 1.1119668126127272e-05, + "loss": 3.8544, + "step": 2374656 + }, + { + "epoch": 0.0, + "learning_rate": 1.1111298557420483e-05, + "loss": 3.8486, + "step": 2375168 + }, + { + "epoch": 0.0, + "learning_rate": 1.1102912609909963e-05, + "loss": 3.8534, + "step": 2375680 + }, + { + "epoch": 0.0, + "learning_rate": 1.1094526662399443e-05, + "loss": 3.8749, + "step": 2376192 + }, + { + "epoch": 0.0, + "learning_rate": 1.1086140714888923e-05, + "loss": 3.8579, + "step": 2376704 + }, + { + "epoch": 0.0, + "learning_rate": 1.1077754767378403e-05, + "loss": 3.8551, + "step": 2377216 + }, + { + "epoch": 0.0, + "learning_rate": 1.1069368819867883e-05, + "loss": 3.8644, + "step": 2377728 + }, + { + "epoch": 0.0, + "learning_rate": 1.1060982872357363e-05, + "loss": 3.8675, + "step": 2378240 + }, + { + "epoch": 0.0, + "learning_rate": 1.1052613303650573e-05, + "loss": 3.8504, + "step": 2378752 + }, + { + "epoch": 0.0, + "learning_rate": 1.1044227356140053e-05, + "loss": 3.8481, + "step": 2379264 + }, + { + "epoch": 0.0, + "learning_rate": 1.1035841408629533e-05, + "loss": 3.86, + "step": 2379776 + }, + { + "epoch": 0.0, + "learning_rate": 1.1027455461119013e-05, + "loss": 3.847, + "step": 2380288 + }, + { + "epoch": 0.0, + "learning_rate": 1.1019069513608493e-05, + "loss": 3.8561, + "step": 2380800 + }, + { + "epoch": 0.01, + "learning_rate": 1.1010699944901706e-05, + "loss": 3.8559, + "step": 2381312 + }, + { + "epoch": 0.01, + "learning_rate": 1.1002313997391186e-05, + "loss": 3.8638, + "step": 2381824 + }, + { + "epoch": 0.01, + "learning_rate": 1.0993928049880664e-05, + "loss": 3.8591, + "step": 2382336 + }, + { + "epoch": 0.01, + "learning_rate": 1.0985542102370144e-05, + "loss": 3.8582, + "step": 2382848 + }, + { + "epoch": 0.01, + "learning_rate": 1.0977172533663356e-05, + "loss": 3.8547, + "step": 2383360 + }, + { + "epoch": 0.01, + "learning_rate": 1.0968802964956567e-05, + "loss": 3.8676, + "step": 2383872 + }, + { + "epoch": 0.01, + "learning_rate": 1.0960417017446047e-05, + "loss": 3.8576, + "step": 2384384 + }, + { + "epoch": 0.01, + "learning_rate": 1.0952031069935527e-05, + "loss": 3.8397, + "step": 2384896 + }, + { + "epoch": 0.01, + "learning_rate": 1.0943645122425007e-05, + "loss": 3.8592, + "step": 2385408 + }, + { + "epoch": 0.01, + "learning_rate": 1.0935259174914487e-05, + "loss": 3.8452, + "step": 2385920 + }, + { + "epoch": 0.01, + "learning_rate": 1.0926873227403967e-05, + "loss": 3.8514, + "step": 2386432 + }, + { + "epoch": 0.01, + "learning_rate": 1.0918487279893447e-05, + "loss": 3.8534, + "step": 2386944 + }, + { + "epoch": 0.01, + "learning_rate": 1.0910101332382927e-05, + "loss": 3.8627, + "step": 2387456 + }, + { + "epoch": 0.01, + "learning_rate": 1.0901715384872407e-05, + "loss": 3.8509, + "step": 2387968 + }, + { + "epoch": 0.01, + "learning_rate": 1.0893329437361887e-05, + "loss": 3.853, + "step": 2388480 + }, + { + "epoch": 0.01, + "learning_rate": 1.0884959868655097e-05, + "loss": 3.8627, + "step": 2388992 + }, + { + "epoch": 0.01, + "learning_rate": 1.0876573921144577e-05, + "loss": 3.8508, + "step": 2389504 + }, + { + "epoch": 0.01, + "learning_rate": 1.0868187973634057e-05, + "loss": 3.8632, + "step": 2390016 + }, + { + "epoch": 0.01, + "learning_rate": 1.0859802026123537e-05, + "loss": 3.8419, + "step": 2390528 + }, + { + "epoch": 0.01, + "learning_rate": 1.085143245741675e-05, + "loss": 3.848, + "step": 2391040 + }, + { + "epoch": 0.01, + "learning_rate": 1.0843046509906228e-05, + "loss": 3.8571, + "step": 2391552 + }, + { + "epoch": 0.01, + "learning_rate": 1.0834660562395708e-05, + "loss": 3.8582, + "step": 2392064 + }, + { + "epoch": 0.01, + "learning_rate": 1.0826274614885188e-05, + "loss": 3.8572, + "step": 2392576 + }, + { + "epoch": 0.01, + "learning_rate": 1.08179050461784e-05, + "loss": 3.84, + "step": 2393088 + }, + { + "epoch": 0.01, + "learning_rate": 1.0809519098667879e-05, + "loss": 3.8525, + "step": 2393600 + }, + { + "epoch": 0.01, + "learning_rate": 1.080113315115736e-05, + "loss": 3.8444, + "step": 2394112 + }, + { + "epoch": 0.01, + "learning_rate": 1.079274720364684e-05, + "loss": 3.8689, + "step": 2394624 + }, + { + "epoch": 0.01, + "learning_rate": 1.0784361256136319e-05, + "loss": 3.8351, + "step": 2395136 + }, + { + "epoch": 0.01, + "learning_rate": 1.0775975308625799e-05, + "loss": 3.8649, + "step": 2395648 + }, + { + "epoch": 0.01, + "learning_rate": 1.076758936111528e-05, + "loss": 3.8558, + "step": 2396160 + }, + { + "epoch": 0.01, + "learning_rate": 1.0759203413604758e-05, + "loss": 3.8374, + "step": 2396672 + }, + { + "epoch": 0.01, + "learning_rate": 1.0750817466094238e-05, + "loss": 3.8555, + "step": 2397184 + }, + { + "epoch": 0.01, + "learning_rate": 1.0742431518583718e-05, + "loss": 3.8489, + "step": 2397696 + }, + { + "epoch": 0.01, + "learning_rate": 1.07340455710732e-05, + "loss": 3.8347, + "step": 2398208 + }, + { + "epoch": 0.01, + "learning_rate": 1.0725659623562678e-05, + "loss": 3.8414, + "step": 2398720 + }, + { + "epoch": 0.01, + "learning_rate": 1.0717290054855889e-05, + "loss": 3.8632, + "step": 2399232 + }, + { + "epoch": 0.01, + "learning_rate": 1.070890410734537e-05, + "loss": 3.8491, + "step": 2399744 + }, + { + "epoch": 0.01, + "learning_rate": 1.0700518159834849e-05, + "loss": 3.8445, + "step": 2400256 + }, + { + "epoch": 0.01, + "learning_rate": 1.0692148591128061e-05, + "loss": 3.8386, + "step": 2400768 + }, + { + "epoch": 0.01, + "learning_rate": 1.0683762643617541e-05, + "loss": 3.8409, + "step": 2401280 + }, + { + "epoch": 0.01, + "learning_rate": 1.0675376696107021e-05, + "loss": 3.855, + "step": 2401792 + }, + { + "epoch": 0.01, + "learning_rate": 1.06669907485965e-05, + "loss": 3.8567, + "step": 2402304 + }, + { + "epoch": 0.01, + "learning_rate": 1.0658621179889712e-05, + "loss": 3.8521, + "step": 2402816 + }, + { + "epoch": 0.01, + "learning_rate": 1.0650235232379192e-05, + "loss": 3.8614, + "step": 2403328 + }, + { + "epoch": 0.01, + "learning_rate": 1.0641849284868672e-05, + "loss": 3.8599, + "step": 2403840 + }, + { + "epoch": 0.01, + "learning_rate": 1.0633463337358152e-05, + "loss": 3.8513, + "step": 2404352 + }, + { + "epoch": 0.01, + "learning_rate": 1.0625077389847632e-05, + "loss": 3.8522, + "step": 2404864 + }, + { + "epoch": 0.01, + "learning_rate": 1.0616691442337112e-05, + "loss": 3.8505, + "step": 2405376 + }, + { + "epoch": 0.01, + "learning_rate": 1.0608321873630323e-05, + "loss": 3.8508, + "step": 2405888 + }, + { + "epoch": 0.01, + "learning_rate": 1.0599935926119803e-05, + "loss": 3.853, + "step": 2406400 + }, + { + "epoch": 0.01, + "learning_rate": 1.0591549978609283e-05, + "loss": 3.8455, + "step": 2406912 + }, + { + "epoch": 0.01, + "learning_rate": 1.0583164031098763e-05, + "loss": 3.8596, + "step": 2407424 + }, + { + "epoch": 0.01, + "learning_rate": 1.0574778083588243e-05, + "loss": 3.8601, + "step": 2407936 + }, + { + "epoch": 0.01, + "learning_rate": 1.0566392136077722e-05, + "loss": 3.8573, + "step": 2408448 + }, + { + "epoch": 0.01, + "learning_rate": 1.0558006188567202e-05, + "loss": 3.8389, + "step": 2408960 + }, + { + "epoch": 0.01, + "learning_rate": 1.0549620241056682e-05, + "loss": 3.8488, + "step": 2409472 + }, + { + "epoch": 0.01, + "learning_rate": 1.0541234293546162e-05, + "loss": 3.8633, + "step": 2409984 + }, + { + "epoch": 0.01, + "learning_rate": 1.0532848346035642e-05, + "loss": 3.8554, + "step": 2410496 + }, + { + "epoch": 0.01, + "learning_rate": 1.0524478777328853e-05, + "loss": 3.8534, + "step": 2411008 + }, + { + "epoch": 0.01, + "learning_rate": 1.0516092829818333e-05, + "loss": 3.8657, + "step": 2411520 + }, + { + "epoch": 0.02, + "learning_rate": 1.0507706882307813e-05, + "loss": 3.8555, + "step": 2412032 + }, + { + "epoch": 0.02, + "learning_rate": 1.0499320934797293e-05, + "loss": 3.8518, + "step": 2412544 + }, + { + "epoch": 0.02, + "learning_rate": 1.0490951366090504e-05, + "loss": 3.8503, + "step": 2413056 + }, + { + "epoch": 0.02, + "learning_rate": 1.0482565418579984e-05, + "loss": 3.8603, + "step": 2413568 + }, + { + "epoch": 0.02, + "learning_rate": 1.0474179471069465e-05, + "loss": 3.8518, + "step": 2414080 + }, + { + "epoch": 0.02, + "learning_rate": 1.0465793523558944e-05, + "loss": 3.8669, + "step": 2414592 + }, + { + "epoch": 0.02, + "learning_rate": 1.0457407576048424e-05, + "loss": 3.843, + "step": 2415104 + }, + { + "epoch": 0.02, + "learning_rate": 1.0449038007341636e-05, + "loss": 3.8526, + "step": 2415616 + }, + { + "epoch": 0.02, + "learning_rate": 1.0440652059831116e-05, + "loss": 3.8463, + "step": 2416128 + }, + { + "epoch": 0.02, + "learning_rate": 1.0432266112320594e-05, + "loss": 3.8599, + "step": 2416640 + }, + { + "epoch": 0.02, + "learning_rate": 1.0423880164810074e-05, + "loss": 3.8654, + "step": 2417152 + }, + { + "epoch": 0.02, + "learning_rate": 1.0415494217299556e-05, + "loss": 3.846, + "step": 2417664 + }, + { + "epoch": 0.02, + "learning_rate": 1.0407108269789034e-05, + "loss": 3.8534, + "step": 2418176 + }, + { + "epoch": 0.02, + "learning_rate": 1.0398722322278514e-05, + "loss": 3.8453, + "step": 2418688 + }, + { + "epoch": 0.02, + "learning_rate": 1.0390336374767996e-05, + "loss": 3.8549, + "step": 2419200 + }, + { + "epoch": 0.02, + "learning_rate": 1.0381966806061207e-05, + "loss": 3.8402, + "step": 2419712 + }, + { + "epoch": 0.02, + "learning_rate": 1.0373580858550685e-05, + "loss": 3.8501, + "step": 2420224 + }, + { + "epoch": 0.02, + "learning_rate": 1.0365194911040166e-05, + "loss": 3.8541, + "step": 2420736 + }, + { + "epoch": 0.02, + "learning_rate": 1.0356808963529646e-05, + "loss": 3.851, + "step": 2421248 + }, + { + "epoch": 0.02, + "learning_rate": 1.034845577362659e-05, + "loss": 3.8558, + "step": 2421760 + }, + { + "epoch": 0.02, + "learning_rate": 1.0340069826116068e-05, + "loss": 3.8523, + "step": 2422272 + }, + { + "epoch": 0.02, + "learning_rate": 1.0331683878605548e-05, + "loss": 3.8429, + "step": 2422784 + }, + { + "epoch": 0.02, + "learning_rate": 1.0323297931095028e-05, + "loss": 3.8605, + "step": 2423296 + }, + { + "epoch": 0.02, + "learning_rate": 1.0314911983584508e-05, + "loss": 3.8549, + "step": 2423808 + }, + { + "epoch": 0.02, + "learning_rate": 1.0306526036073988e-05, + "loss": 3.8517, + "step": 2424320 + }, + { + "epoch": 0.02, + "learning_rate": 1.0298140088563468e-05, + "loss": 3.857, + "step": 2424832 + }, + { + "epoch": 0.02, + "learning_rate": 1.028977051985668e-05, + "loss": 3.8601, + "step": 2425344 + }, + { + "epoch": 0.02, + "learning_rate": 1.0281384572346159e-05, + "loss": 3.8532, + "step": 2425856 + }, + { + "epoch": 0.02, + "learning_rate": 1.0273015003639371e-05, + "loss": 3.8452, + "step": 2426368 + }, + { + "epoch": 0.02, + "learning_rate": 1.0264629056128851e-05, + "loss": 3.8574, + "step": 2426880 + }, + { + "epoch": 0.02, + "learning_rate": 1.0256243108618331e-05, + "loss": 3.8484, + "step": 2427392 + }, + { + "epoch": 0.02, + "learning_rate": 1.024785716110781e-05, + "loss": 3.8437, + "step": 2427904 + }, + { + "epoch": 0.02, + "learning_rate": 1.023947121359729e-05, + "loss": 3.8489, + "step": 2428416 + }, + { + "epoch": 0.02, + "learning_rate": 1.0231101644890502e-05, + "loss": 3.8492, + "step": 2428928 + }, + { + "epoch": 0.02, + "learning_rate": 1.0222715697379982e-05, + "loss": 3.8548, + "step": 2429440 + }, + { + "epoch": 0.02, + "learning_rate": 1.0214329749869462e-05, + "loss": 3.8464, + "step": 2429952 + }, + { + "epoch": 0.02, + "learning_rate": 1.0205943802358941e-05, + "loss": 3.8526, + "step": 2430464 + }, + { + "epoch": 0.02, + "learning_rate": 1.0197557854848421e-05, + "loss": 3.8456, + "step": 2430976 + }, + { + "epoch": 0.02, + "learning_rate": 1.0189171907337901e-05, + "loss": 3.8524, + "step": 2431488 + }, + { + "epoch": 0.02, + "learning_rate": 1.0180802338631112e-05, + "loss": 3.8536, + "step": 2432000 + }, + { + "epoch": 0.02, + "learning_rate": 1.0172416391120592e-05, + "loss": 3.8578, + "step": 2432512 + }, + { + "epoch": 0.02, + "learning_rate": 1.0164030443610072e-05, + "loss": 3.8546, + "step": 2433024 + }, + { + "epoch": 0.02, + "learning_rate": 1.0155644496099552e-05, + "loss": 3.8485, + "step": 2433536 + }, + { + "epoch": 0.02, + "learning_rate": 1.0147258548589032e-05, + "loss": 3.8571, + "step": 2434048 + }, + { + "epoch": 0.02, + "learning_rate": 1.0138872601078512e-05, + "loss": 3.8582, + "step": 2434560 + }, + { + "epoch": 0.02, + "learning_rate": 1.0130486653567992e-05, + "loss": 3.8629, + "step": 2435072 + }, + { + "epoch": 0.02, + "learning_rate": 1.0122100706057472e-05, + "loss": 3.861, + "step": 2435584 + }, + { + "epoch": 0.02, + "learning_rate": 1.0113714758546952e-05, + "loss": 3.8544, + "step": 2436096 + }, + { + "epoch": 0.02, + "learning_rate": 1.0105345189840163e-05, + "loss": 3.8656, + "step": 2436608 + }, + { + "epoch": 0.02, + "learning_rate": 1.0096959242329643e-05, + "loss": 3.8595, + "step": 2437120 + }, + { + "epoch": 0.02, + "learning_rate": 1.0088573294819123e-05, + "loss": 3.8489, + "step": 2437632 + }, + { + "epoch": 0.02, + "learning_rate": 1.0080203726112335e-05, + "loss": 3.8545, + "step": 2438144 + }, + { + "epoch": 0.02, + "learning_rate": 1.0071817778601813e-05, + "loss": 3.8481, + "step": 2438656 + }, + { + "epoch": 0.02, + "learning_rate": 1.0063431831091293e-05, + "loss": 3.8507, + "step": 2439168 + }, + { + "epoch": 0.02, + "learning_rate": 1.0055045883580775e-05, + "loss": 3.8454, + "step": 2439680 + }, + { + "epoch": 0.02, + "learning_rate": 1.0046659936070253e-05, + "loss": 3.8578, + "step": 2440192 + }, + { + "epoch": 0.02, + "learning_rate": 1.0038273988559733e-05, + "loss": 3.8451, + "step": 2440704 + }, + { + "epoch": 0.02, + "learning_rate": 1.0029904419852946e-05, + "loss": 3.8578, + "step": 2441216 + }, + { + "epoch": 0.02, + "learning_rate": 1.0021518472342426e-05, + "loss": 3.8545, + "step": 2441728 + }, + { + "epoch": 0.03, + "learning_rate": 1.0013132524831904e-05, + "loss": 3.8521, + "step": 2442240 + }, + { + "epoch": 0.03, + "eval_loss": 3.9749667644500732, + "eval_runtime": 294.3301, + "eval_samples_per_second": 1296.473, + "eval_steps_per_second": 40.516, + "step": 2442240 + }, + { + "epoch": 1.0, + "learning_rate": 1.0004746577321385e-05, + "loss": 3.8455, + "step": 2442752 + }, + { + "epoch": 1.0, + "learning_rate": 9.996360629810865e-06, + "loss": 3.8459, + "step": 2443264 + }, + { + "epoch": 1.0, + "learning_rate": 9.987974682300344e-06, + "loss": 3.8571, + "step": 2443776 + }, + { + "epoch": 1.0, + "learning_rate": 9.979588734789824e-06, + "loss": 3.8584, + "step": 2444288 + }, + { + "epoch": 1.0, + "learning_rate": 9.971202787279305e-06, + "loss": 3.8547, + "step": 2444800 + }, + { + "epoch": 1.0, + "learning_rate": 9.962816839768784e-06, + "loss": 3.846, + "step": 2445312 + }, + { + "epoch": 1.0, + "learning_rate": 9.954447271061994e-06, + "loss": 3.8462, + "step": 2445824 + }, + { + "epoch": 1.0, + "learning_rate": 9.946061323551476e-06, + "loss": 3.8463, + "step": 2446336 + }, + { + "epoch": 1.0, + "learning_rate": 9.937675376040956e-06, + "loss": 3.8589, + "step": 2446848 + }, + { + "epoch": 1.0, + "learning_rate": 9.929289428530434e-06, + "loss": 3.8536, + "step": 2447360 + }, + { + "epoch": 1.0, + "learning_rate": 9.920903481019916e-06, + "loss": 3.8605, + "step": 2447872 + }, + { + "epoch": 1.0, + "learning_rate": 9.912533912313127e-06, + "loss": 3.8649, + "step": 2448384 + }, + { + "epoch": 1.0, + "learning_rate": 9.904147964802607e-06, + "loss": 3.8372, + "step": 2448896 + }, + { + "epoch": 1.0, + "learning_rate": 9.895762017292087e-06, + "loss": 3.845, + "step": 2449408 + }, + { + "epoch": 1.0, + "learning_rate": 9.887376069781567e-06, + "loss": 3.8423, + "step": 2449920 + }, + { + "epoch": 1.0, + "learning_rate": 9.878990122271046e-06, + "loss": 3.8491, + "step": 2450432 + }, + { + "epoch": 1.0, + "learning_rate": 9.870604174760525e-06, + "loss": 3.8509, + "step": 2450944 + }, + { + "epoch": 1.0, + "learning_rate": 9.862234606053737e-06, + "loss": 3.8518, + "step": 2451456 + }, + { + "epoch": 1.0, + "learning_rate": 9.853848658543217e-06, + "loss": 3.8476, + "step": 2451968 + }, + { + "epoch": 1.0, + "learning_rate": 9.845462711032697e-06, + "loss": 3.8724, + "step": 2452480 + }, + { + "epoch": 1.0, + "learning_rate": 9.837076763522177e-06, + "loss": 3.8534, + "step": 2452992 + }, + { + "epoch": 1.0, + "learning_rate": 9.828690816011657e-06, + "loss": 3.8566, + "step": 2453504 + }, + { + "epoch": 1.0, + "learning_rate": 9.820321247304868e-06, + "loss": 3.8552, + "step": 2454016 + }, + { + "epoch": 1.0, + "learning_rate": 9.811935299794348e-06, + "loss": 3.8684, + "step": 2454528 + }, + { + "epoch": 1.0, + "learning_rate": 9.803549352283828e-06, + "loss": 3.8462, + "step": 2455040 + }, + { + "epoch": 1.0, + "learning_rate": 9.795163404773308e-06, + "loss": 3.8499, + "step": 2455552 + }, + { + "epoch": 1.0, + "learning_rate": 9.78677745726279e-06, + "loss": 3.8554, + "step": 2456064 + }, + { + "epoch": 1.0, + "learning_rate": 9.778391509752268e-06, + "loss": 3.8443, + "step": 2456576 + }, + { + "epoch": 1.0, + "learning_rate": 9.770005562241748e-06, + "loss": 3.8509, + "step": 2457088 + }, + { + "epoch": 1.01, + "learning_rate": 9.76163599353496e-06, + "loss": 3.8522, + "step": 2457600 + }, + { + "epoch": 1.01, + "learning_rate": 9.753250046024438e-06, + "loss": 3.8628, + "step": 2458112 + }, + { + "epoch": 1.01, + "learning_rate": 9.744864098513918e-06, + "loss": 3.8542, + "step": 2458624 + }, + { + "epoch": 1.01, + "learning_rate": 9.736478151003398e-06, + "loss": 3.8576, + "step": 2459136 + }, + { + "epoch": 1.01, + "learning_rate": 9.72809220349288e-06, + "loss": 3.8545, + "step": 2459648 + }, + { + "epoch": 1.01, + "learning_rate": 9.719722634786089e-06, + "loss": 3.8594, + "step": 2460160 + }, + { + "epoch": 1.01, + "learning_rate": 9.71133668727557e-06, + "loss": 3.8549, + "step": 2460672 + }, + { + "epoch": 1.01, + "learning_rate": 9.70295073976505e-06, + "loss": 3.8393, + "step": 2461184 + }, + { + "epoch": 1.01, + "learning_rate": 9.694564792254529e-06, + "loss": 3.8506, + "step": 2461696 + }, + { + "epoch": 1.01, + "learning_rate": 9.686178844744009e-06, + "loss": 3.8407, + "step": 2462208 + }, + { + "epoch": 1.01, + "learning_rate": 9.677809276037221e-06, + "loss": 3.8499, + "step": 2462720 + }, + { + "epoch": 1.01, + "learning_rate": 9.669423328526701e-06, + "loss": 3.849, + "step": 2463232 + }, + { + "epoch": 1.01, + "learning_rate": 9.66103738101618e-06, + "loss": 3.8587, + "step": 2463744 + }, + { + "epoch": 1.01, + "learning_rate": 9.652651433505661e-06, + "loss": 3.8481, + "step": 2464256 + }, + { + "epoch": 1.01, + "learning_rate": 9.644265485995141e-06, + "loss": 3.8503, + "step": 2464768 + }, + { + "epoch": 1.01, + "learning_rate": 9.63587953848462e-06, + "loss": 3.8591, + "step": 2465280 + }, + { + "epoch": 1.01, + "learning_rate": 9.627509969777832e-06, + "loss": 3.8491, + "step": 2465792 + }, + { + "epoch": 1.01, + "learning_rate": 9.619124022267312e-06, + "loss": 3.8596, + "step": 2466304 + }, + { + "epoch": 1.01, + "learning_rate": 9.610738074756792e-06, + "loss": 3.8364, + "step": 2466816 + }, + { + "epoch": 1.01, + "learning_rate": 9.602368506050003e-06, + "loss": 3.8467, + "step": 2467328 + }, + { + "epoch": 1.01, + "learning_rate": 9.593982558539482e-06, + "loss": 3.8576, + "step": 2467840 + }, + { + "epoch": 1.01, + "learning_rate": 9.585596611028962e-06, + "loss": 3.8541, + "step": 2468352 + }, + { + "epoch": 1.01, + "learning_rate": 9.577210663518444e-06, + "loss": 3.8513, + "step": 2468864 + }, + { + "epoch": 1.01, + "learning_rate": 9.568824716007922e-06, + "loss": 3.8342, + "step": 2469376 + }, + { + "epoch": 1.01, + "learning_rate": 9.560438768497402e-06, + "loss": 3.8526, + "step": 2469888 + }, + { + "epoch": 1.01, + "learning_rate": 9.552052820986882e-06, + "loss": 3.8387, + "step": 2470400 + }, + { + "epoch": 1.01, + "learning_rate": 9.543666873476362e-06, + "loss": 3.8658, + "step": 2470912 + }, + { + "epoch": 1.01, + "learning_rate": 9.535297304769573e-06, + "loss": 3.8364, + "step": 2471424 + }, + { + "epoch": 1.01, + "learning_rate": 9.526911357259053e-06, + "loss": 3.8579, + "step": 2471936 + }, + { + "epoch": 1.01, + "learning_rate": 9.518525409748535e-06, + "loss": 3.8473, + "step": 2472448 + }, + { + "epoch": 1.01, + "learning_rate": 9.510139462238013e-06, + "loss": 3.8353, + "step": 2472960 + }, + { + "epoch": 1.01, + "learning_rate": 9.501753514727493e-06, + "loss": 3.8533, + "step": 2473472 + }, + { + "epoch": 1.01, + "learning_rate": 9.493367567216973e-06, + "loss": 3.8448, + "step": 2473984 + }, + { + "epoch": 1.01, + "learning_rate": 9.484981619706453e-06, + "loss": 3.8301, + "step": 2474496 + }, + { + "epoch": 1.01, + "learning_rate": 9.476595672195933e-06, + "loss": 3.8393, + "step": 2475008 + }, + { + "epoch": 1.01, + "learning_rate": 9.468226103489145e-06, + "loss": 3.8583, + "step": 2475520 + }, + { + "epoch": 1.01, + "learning_rate": 9.459840155978625e-06, + "loss": 3.8469, + "step": 2476032 + }, + { + "epoch": 1.01, + "learning_rate": 9.451454208468103e-06, + "loss": 3.8399, + "step": 2476544 + }, + { + "epoch": 1.01, + "learning_rate": 9.443068260957583e-06, + "loss": 3.8407, + "step": 2477056 + }, + { + "epoch": 1.01, + "learning_rate": 9.434682313447065e-06, + "loss": 3.8373, + "step": 2477568 + }, + { + "epoch": 1.01, + "learning_rate": 9.426312744740274e-06, + "loss": 3.8502, + "step": 2478080 + }, + { + "epoch": 1.01, + "learning_rate": 9.417926797229756e-06, + "loss": 3.854, + "step": 2478592 + }, + { + "epoch": 1.01, + "learning_rate": 9.409540849719236e-06, + "loss": 3.8501, + "step": 2479104 + }, + { + "epoch": 1.01, + "learning_rate": 9.401154902208714e-06, + "loss": 3.8586, + "step": 2479616 + }, + { + "epoch": 1.01, + "learning_rate": 9.392768954698194e-06, + "loss": 3.8533, + "step": 2480128 + }, + { + "epoch": 1.01, + "learning_rate": 9.384383007187676e-06, + "loss": 3.8553, + "step": 2480640 + }, + { + "epoch": 1.01, + "learning_rate": 9.376013438480886e-06, + "loss": 3.8434, + "step": 2481152 + }, + { + "epoch": 1.01, + "learning_rate": 9.367627490970365e-06, + "loss": 3.8502, + "step": 2481664 + }, + { + "epoch": 1.01, + "learning_rate": 9.359241543459846e-06, + "loss": 3.8512, + "step": 2482176 + }, + { + "epoch": 1.01, + "learning_rate": 9.350855595949326e-06, + "loss": 3.845, + "step": 2482688 + }, + { + "epoch": 1.01, + "learning_rate": 9.342469648438804e-06, + "loss": 3.8436, + "step": 2483200 + }, + { + "epoch": 1.01, + "learning_rate": 9.334100079732017e-06, + "loss": 3.8553, + "step": 2483712 + }, + { + "epoch": 1.01, + "learning_rate": 9.325714132221497e-06, + "loss": 3.8603, + "step": 2484224 + }, + { + "epoch": 1.01, + "learning_rate": 9.317328184710977e-06, + "loss": 3.8527, + "step": 2484736 + }, + { + "epoch": 1.01, + "learning_rate": 9.308942237200457e-06, + "loss": 3.8353, + "step": 2485248 + }, + { + "epoch": 1.01, + "learning_rate": 9.300556289689937e-06, + "loss": 3.8498, + "step": 2485760 + }, + { + "epoch": 1.01, + "learning_rate": 9.292186720983148e-06, + "loss": 3.859, + "step": 2486272 + }, + { + "epoch": 1.01, + "learning_rate": 9.28380077347263e-06, + "loss": 3.8571, + "step": 2486784 + }, + { + "epoch": 1.01, + "learning_rate": 9.275414825962108e-06, + "loss": 3.847, + "step": 2487296 + }, + { + "epoch": 1.01, + "learning_rate": 9.267028878451587e-06, + "loss": 3.8634, + "step": 2487808 + }, + { + "epoch": 1.02, + "learning_rate": 9.258642930941067e-06, + "loss": 3.8532, + "step": 2488320 + }, + { + "epoch": 1.02, + "learning_rate": 9.250273362234278e-06, + "loss": 3.847, + "step": 2488832 + }, + { + "epoch": 1.02, + "learning_rate": 9.241887414723758e-06, + "loss": 3.8489, + "step": 2489344 + }, + { + "epoch": 1.02, + "learning_rate": 9.233501467213238e-06, + "loss": 3.8575, + "step": 2489856 + }, + { + "epoch": 1.02, + "learning_rate": 9.22511551970272e-06, + "loss": 3.8466, + "step": 2490368 + }, + { + "epoch": 1.02, + "learning_rate": 9.216729572192198e-06, + "loss": 3.8659, + "step": 2490880 + }, + { + "epoch": 1.02, + "learning_rate": 9.208343624681678e-06, + "loss": 3.8451, + "step": 2491392 + }, + { + "epoch": 1.02, + "learning_rate": 9.199957677171158e-06, + "loss": 3.8452, + "step": 2491904 + }, + { + "epoch": 1.02, + "learning_rate": 9.191571729660638e-06, + "loss": 3.8468, + "step": 2492416 + }, + { + "epoch": 1.02, + "learning_rate": 9.183202160953849e-06, + "loss": 3.86, + "step": 2492928 + }, + { + "epoch": 1.02, + "learning_rate": 9.17481621344333e-06, + "loss": 3.8553, + "step": 2493440 + }, + { + "epoch": 1.02, + "learning_rate": 9.16643026593281e-06, + "loss": 3.8458, + "step": 2493952 + }, + { + "epoch": 1.02, + "learning_rate": 9.15806069722602e-06, + "loss": 3.8469, + "step": 2494464 + }, + { + "epoch": 1.02, + "learning_rate": 9.149674749715501e-06, + "loss": 3.8432, + "step": 2494976 + }, + { + "epoch": 1.02, + "learning_rate": 9.141288802204981e-06, + "loss": 3.8562, + "step": 2495488 + }, + { + "epoch": 1.02, + "learning_rate": 9.13290285469446e-06, + "loss": 3.8348, + "step": 2496000 + }, + { + "epoch": 1.02, + "learning_rate": 9.124533285987672e-06, + "loss": 3.847, + "step": 2496512 + }, + { + "epoch": 1.02, + "learning_rate": 9.116147338477152e-06, + "loss": 3.8525, + "step": 2497024 + }, + { + "epoch": 1.02, + "learning_rate": 9.107761390966632e-06, + "loss": 3.8473, + "step": 2497536 + }, + { + "epoch": 1.02, + "learning_rate": 9.099375443456112e-06, + "loss": 3.8509, + "step": 2498048 + }, + { + "epoch": 1.02, + "learning_rate": 9.091005874749322e-06, + "loss": 3.8513, + "step": 2498560 + }, + { + "epoch": 1.02, + "learning_rate": 9.082619927238802e-06, + "loss": 3.839, + "step": 2499072 + }, + { + "epoch": 1.02, + "learning_rate": 9.074233979728284e-06, + "loss": 3.8525, + "step": 2499584 + }, + { + "epoch": 1.02, + "learning_rate": 9.065864411021493e-06, + "loss": 3.8515, + "step": 2500096 + }, + { + "epoch": 1.02, + "learning_rate": 9.057478463510973e-06, + "loss": 3.8494, + "step": 2500608 + }, + { + "epoch": 1.02, + "learning_rate": 9.049092516000455e-06, + "loss": 3.8537, + "step": 2501120 + }, + { + "epoch": 1.02, + "learning_rate": 9.040706568489933e-06, + "loss": 3.8562, + "step": 2501632 + }, + { + "epoch": 1.02, + "learning_rate": 9.032320620979413e-06, + "loss": 3.8503, + "step": 2502144 + }, + { + "epoch": 1.02, + "learning_rate": 9.023934673468893e-06, + "loss": 3.8455, + "step": 2502656 + }, + { + "epoch": 1.02, + "learning_rate": 9.015548725958375e-06, + "loss": 3.8501, + "step": 2503168 + }, + { + "epoch": 1.02, + "learning_rate": 9.007162778447853e-06, + "loss": 3.8476, + "step": 2503680 + }, + { + "epoch": 1.02, + "learning_rate": 8.998776830937333e-06, + "loss": 3.8394, + "step": 2504192 + }, + { + "epoch": 1.02, + "learning_rate": 8.990390883426814e-06, + "loss": 3.8464, + "step": 2504704 + }, + { + "epoch": 1.02, + "learning_rate": 8.982004935916293e-06, + "loss": 3.8455, + "step": 2505216 + }, + { + "epoch": 1.02, + "learning_rate": 8.973635367209503e-06, + "loss": 3.8556, + "step": 2505728 + }, + { + "epoch": 1.02, + "learning_rate": 8.965249419698985e-06, + "loss": 3.8411, + "step": 2506240 + }, + { + "epoch": 1.02, + "learning_rate": 8.956863472188465e-06, + "loss": 3.8497, + "step": 2506752 + }, + { + "epoch": 1.02, + "learning_rate": 8.948477524677943e-06, + "loss": 3.8402, + "step": 2507264 + }, + { + "epoch": 1.02, + "learning_rate": 8.940107955971156e-06, + "loss": 3.8517, + "step": 2507776 + }, + { + "epoch": 1.02, + "learning_rate": 8.931722008460636e-06, + "loss": 3.8453, + "step": 2508288 + }, + { + "epoch": 1.02, + "learning_rate": 8.923336060950114e-06, + "loss": 3.864, + "step": 2508800 + }, + { + "epoch": 1.02, + "learning_rate": 8.914950113439596e-06, + "loss": 3.8505, + "step": 2509312 + }, + { + "epoch": 1.02, + "learning_rate": 8.906564165929076e-06, + "loss": 3.8491, + "step": 2509824 + }, + { + "epoch": 1.02, + "learning_rate": 8.898178218418556e-06, + "loss": 3.8503, + "step": 2510336 + }, + { + "epoch": 1.02, + "learning_rate": 8.889792270908034e-06, + "loss": 3.8526, + "step": 2510848 + }, + { + "epoch": 1.02, + "learning_rate": 8.881422702201246e-06, + "loss": 3.8585, + "step": 2511360 + }, + { + "epoch": 1.02, + "learning_rate": 8.873036754690726e-06, + "loss": 3.8582, + "step": 2511872 + }, + { + "epoch": 1.02, + "learning_rate": 8.864650807180205e-06, + "loss": 3.8536, + "step": 2512384 + }, + { + "epoch": 1.02, + "learning_rate": 8.856264859669686e-06, + "loss": 3.8613, + "step": 2512896 + }, + { + "epoch": 1.02, + "learning_rate": 8.847895290962897e-06, + "loss": 3.8564, + "step": 2513408 + }, + { + "epoch": 1.02, + "learning_rate": 8.839509343452377e-06, + "loss": 3.8479, + "step": 2513920 + }, + { + "epoch": 1.02, + "learning_rate": 8.831123395941857e-06, + "loss": 3.8473, + "step": 2514432 + }, + { + "epoch": 1.02, + "learning_rate": 8.822737448431337e-06, + "loss": 3.8518, + "step": 2514944 + }, + { + "epoch": 1.02, + "learning_rate": 8.81436787972455e-06, + "loss": 3.8499, + "step": 2515456 + }, + { + "epoch": 1.02, + "learning_rate": 8.80598193221403e-06, + "loss": 3.8393, + "step": 2515968 + }, + { + "epoch": 1.02, + "learning_rate": 8.797595984703508e-06, + "loss": 3.8515, + "step": 2516480 + }, + { + "epoch": 1.02, + "learning_rate": 8.789210037192988e-06, + "loss": 3.8458, + "step": 2516992 + }, + { + "epoch": 1.02, + "learning_rate": 8.78082408968247e-06, + "loss": 3.8545, + "step": 2517504 + }, + { + "epoch": 1.02, + "learning_rate": 8.77247089977941e-06, + "loss": 3.8505, + "step": 2518016 + }, + { + "epoch": 1.02, + "learning_rate": 8.76408495226889e-06, + "loss": 3.849, + "step": 2518528 + }, + { + "epoch": 1.03, + "eval_loss": 3.973785400390625, + "eval_runtime": 291.1941, + "eval_samples_per_second": 1310.435, + "eval_steps_per_second": 40.952, + "step": 2518560 + }, + { + "epoch": 0.0, + "learning_rate": 8.75569900475837e-06, + "loss": 3.8411, + "step": 2519040 + }, + { + "epoch": 0.0, + "learning_rate": 8.74731305724785e-06, + "loss": 3.8445, + "step": 2519552 + }, + { + "epoch": 0.0, + "learning_rate": 8.73892710973733e-06, + "loss": 3.856, + "step": 2520064 + }, + { + "epoch": 0.0, + "learning_rate": 8.73054116222681e-06, + "loss": 3.8522, + "step": 2520576 + }, + { + "epoch": 0.0, + "learning_rate": 8.72215521471629e-06, + "loss": 3.8525, + "step": 2521088 + }, + { + "epoch": 0.0, + "learning_rate": 8.713769267205769e-06, + "loss": 3.8447, + "step": 2521600 + }, + { + "epoch": 0.0, + "learning_rate": 8.70538331969525e-06, + "loss": 3.8412, + "step": 2522112 + }, + { + "epoch": 0.0, + "learning_rate": 8.69699737218473e-06, + "loss": 3.8437, + "step": 2522624 + }, + { + "epoch": 0.0, + "learning_rate": 8.688611424674209e-06, + "loss": 3.8542, + "step": 2523136 + }, + { + "epoch": 0.0, + "learning_rate": 8.680225477163689e-06, + "loss": 3.8526, + "step": 2523648 + }, + { + "epoch": 0.0, + "learning_rate": 8.67183952965317e-06, + "loss": 3.8524, + "step": 2524160 + }, + { + "epoch": 0.0, + "learning_rate": 8.66345358214265e-06, + "loss": 3.8586, + "step": 2524672 + }, + { + "epoch": 0.0, + "learning_rate": 8.655084013435861e-06, + "loss": 3.8366, + "step": 2525184 + }, + { + "epoch": 0.0, + "learning_rate": 8.646698065925341e-06, + "loss": 3.8444, + "step": 2525696 + }, + { + "epoch": 0.0, + "learning_rate": 8.638312118414821e-06, + "loss": 3.845, + "step": 2526208 + }, + { + "epoch": 0.0, + "learning_rate": 8.6299261709043e-06, + "loss": 3.8383, + "step": 2526720 + }, + { + "epoch": 0.0, + "learning_rate": 8.62154022339378e-06, + "loss": 3.8499, + "step": 2527232 + }, + { + "epoch": 0.0, + "learning_rate": 8.61315427588326e-06, + "loss": 3.8436, + "step": 2527744 + }, + { + "epoch": 0.0, + "learning_rate": 8.60476832837274e-06, + "loss": 3.8449, + "step": 2528256 + }, + { + "epoch": 0.0, + "learning_rate": 8.596382380862219e-06, + "loss": 3.8739, + "step": 2528768 + }, + { + "epoch": 0.0, + "learning_rate": 8.5879964333517e-06, + "loss": 3.8486, + "step": 2529280 + }, + { + "epoch": 0.0, + "learning_rate": 8.57961048584118e-06, + "loss": 3.8526, + "step": 2529792 + }, + { + "epoch": 0.0, + "learning_rate": 8.57124091713439e-06, + "loss": 3.8527, + "step": 2530304 + }, + { + "epoch": 0.0, + "learning_rate": 8.562854969623871e-06, + "loss": 3.8616, + "step": 2530816 + }, + { + "epoch": 0.0, + "learning_rate": 8.554469022113351e-06, + "loss": 3.8453, + "step": 2531328 + }, + { + "epoch": 0.0, + "learning_rate": 8.546083074602831e-06, + "loss": 3.845, + "step": 2531840 + }, + { + "epoch": 0.0, + "learning_rate": 8.537713505896042e-06, + "loss": 3.8489, + "step": 2532352 + }, + { + "epoch": 0.0, + "learning_rate": 8.529327558385522e-06, + "loss": 3.8462, + "step": 2532864 + }, + { + "epoch": 0.0, + "learning_rate": 8.520957989678734e-06, + "loss": 3.8458, + "step": 2533376 + }, + { + "epoch": 0.01, + "learning_rate": 8.512572042168214e-06, + "loss": 3.844, + "step": 2533888 + }, + { + "epoch": 0.01, + "learning_rate": 8.504186094657693e-06, + "loss": 3.8638, + "step": 2534400 + }, + { + "epoch": 0.01, + "learning_rate": 8.495800147147173e-06, + "loss": 3.8512, + "step": 2534912 + }, + { + "epoch": 0.01, + "learning_rate": 8.487414199636654e-06, + "loss": 3.8516, + "step": 2535424 + }, + { + "epoch": 0.01, + "learning_rate": 8.479028252126133e-06, + "loss": 3.852, + "step": 2535936 + }, + { + "epoch": 0.01, + "learning_rate": 8.470658683419343e-06, + "loss": 3.8569, + "step": 2536448 + }, + { + "epoch": 0.01, + "learning_rate": 8.462272735908825e-06, + "loss": 3.8518, + "step": 2536960 + }, + { + "epoch": 0.01, + "learning_rate": 8.453886788398305e-06, + "loss": 3.8363, + "step": 2537472 + }, + { + "epoch": 0.01, + "learning_rate": 8.445500840887783e-06, + "loss": 3.8479, + "step": 2537984 + }, + { + "epoch": 0.01, + "learning_rate": 8.437114893377263e-06, + "loss": 3.8352, + "step": 2538496 + }, + { + "epoch": 0.01, + "learning_rate": 8.428728945866745e-06, + "loss": 3.85, + "step": 2539008 + }, + { + "epoch": 0.01, + "learning_rate": 8.420342998356223e-06, + "loss": 3.8456, + "step": 2539520 + }, + { + "epoch": 0.01, + "learning_rate": 8.411957050845703e-06, + "loss": 3.8547, + "step": 2540032 + }, + { + "epoch": 0.01, + "learning_rate": 8.403571103335183e-06, + "loss": 3.8449, + "step": 2540544 + }, + { + "epoch": 0.01, + "learning_rate": 8.395185155824663e-06, + "loss": 3.8475, + "step": 2541056 + }, + { + "epoch": 0.01, + "learning_rate": 8.386799208314143e-06, + "loss": 3.8565, + "step": 2541568 + }, + { + "epoch": 0.01, + "learning_rate": 8.378413260803623e-06, + "loss": 3.847, + "step": 2542080 + }, + { + "epoch": 0.01, + "learning_rate": 8.370043692096835e-06, + "loss": 3.8519, + "step": 2542592 + }, + { + "epoch": 0.01, + "learning_rate": 8.361657744586314e-06, + "loss": 3.8395, + "step": 2543104 + }, + { + "epoch": 0.01, + "learning_rate": 8.353271797075794e-06, + "loss": 3.8435, + "step": 2543616 + }, + { + "epoch": 0.01, + "learning_rate": 8.344902228369006e-06, + "loss": 3.8504, + "step": 2544128 + }, + { + "epoch": 0.01, + "learning_rate": 8.336516280858486e-06, + "loss": 3.8513, + "step": 2544640 + }, + { + "epoch": 0.01, + "learning_rate": 8.328130333347966e-06, + "loss": 3.8527, + "step": 2545152 + }, + { + "epoch": 0.01, + "learning_rate": 8.319744385837446e-06, + "loss": 3.8288, + "step": 2545664 + }, + { + "epoch": 0.01, + "learning_rate": 8.311358438326926e-06, + "loss": 3.8508, + "step": 2546176 + }, + { + "epoch": 0.01, + "learning_rate": 8.302972490816404e-06, + "loss": 3.8321, + "step": 2546688 + }, + { + "epoch": 0.01, + "learning_rate": 8.294586543305886e-06, + "loss": 3.8629, + "step": 2547200 + }, + { + "epoch": 0.01, + "learning_rate": 8.286216974599097e-06, + "loss": 3.8364, + "step": 2547712 + }, + { + "epoch": 0.01, + "learning_rate": 8.277831027088577e-06, + "loss": 3.8538, + "step": 2548224 + }, + { + "epoch": 0.01, + "learning_rate": 8.269445079578056e-06, + "loss": 3.8479, + "step": 2548736 + }, + { + "epoch": 0.01, + "learning_rate": 8.261059132067536e-06, + "loss": 3.836, + "step": 2549248 + }, + { + "epoch": 0.01, + "learning_rate": 8.252673184557016e-06, + "loss": 3.8435, + "step": 2549760 + }, + { + "epoch": 0.01, + "learning_rate": 8.244287237046495e-06, + "loss": 3.8452, + "step": 2550272 + }, + { + "epoch": 0.01, + "learning_rate": 8.235917668339707e-06, + "loss": 3.8283, + "step": 2550784 + }, + { + "epoch": 0.01, + "learning_rate": 8.227531720829187e-06, + "loss": 3.8378, + "step": 2551296 + }, + { + "epoch": 0.01, + "learning_rate": 8.219145773318667e-06, + "loss": 3.8516, + "step": 2551808 + }, + { + "epoch": 0.01, + "learning_rate": 8.210759825808147e-06, + "loss": 3.8465, + "step": 2552320 + }, + { + "epoch": 0.01, + "learning_rate": 8.20240663590509e-06, + "loss": 3.8398, + "step": 2552832 + }, + { + "epoch": 0.01, + "learning_rate": 8.19402068839457e-06, + "loss": 3.8359, + "step": 2553344 + }, + { + "epoch": 0.01, + "learning_rate": 8.185634740884049e-06, + "loss": 3.8303, + "step": 2553856 + }, + { + "epoch": 0.01, + "learning_rate": 8.177248793373529e-06, + "loss": 3.8478, + "step": 2554368 + }, + { + "epoch": 0.01, + "learning_rate": 8.16886284586301e-06, + "loss": 3.8482, + "step": 2554880 + }, + { + "epoch": 0.01, + "learning_rate": 8.16047689835249e-06, + "loss": 3.8485, + "step": 2555392 + }, + { + "epoch": 0.01, + "learning_rate": 8.152090950841968e-06, + "loss": 3.8554, + "step": 2555904 + }, + { + "epoch": 0.01, + "learning_rate": 8.143705003331448e-06, + "loss": 3.8504, + "step": 2556416 + }, + { + "epoch": 0.01, + "learning_rate": 8.13531905582093e-06, + "loss": 3.855, + "step": 2556928 + }, + { + "epoch": 0.01, + "learning_rate": 8.126949487114139e-06, + "loss": 3.8358, + "step": 2557440 + }, + { + "epoch": 0.01, + "learning_rate": 8.11856353960362e-06, + "loss": 3.849, + "step": 2557952 + }, + { + "epoch": 0.01, + "learning_rate": 8.110193970896832e-06, + "loss": 3.8443, + "step": 2558464 + }, + { + "epoch": 0.01, + "learning_rate": 8.101808023386311e-06, + "loss": 3.8434, + "step": 2558976 + }, + { + "epoch": 0.01, + "learning_rate": 8.093422075875791e-06, + "loss": 3.8426, + "step": 2559488 + }, + { + "epoch": 0.01, + "learning_rate": 8.085036128365271e-06, + "loss": 3.8491, + "step": 2560000 + }, + { + "epoch": 0.01, + "learning_rate": 8.076650180854751e-06, + "loss": 3.8592, + "step": 2560512 + }, + { + "epoch": 0.01, + "learning_rate": 8.06826423334423e-06, + "loss": 3.8505, + "step": 2561024 + }, + { + "epoch": 0.01, + "learning_rate": 8.059878285833711e-06, + "loss": 3.8346, + "step": 2561536 + }, + { + "epoch": 0.01, + "learning_rate": 8.051492338323191e-06, + "loss": 3.8402, + "step": 2562048 + }, + { + "epoch": 0.01, + "learning_rate": 8.043106390812671e-06, + "loss": 3.8565, + "step": 2562560 + }, + { + "epoch": 0.01, + "learning_rate": 8.034736822105882e-06, + "loss": 3.8528, + "step": 2563072 + }, + { + "epoch": 0.01, + "learning_rate": 8.026350874595362e-06, + "loss": 3.8474, + "step": 2563584 + }, + { + "epoch": 0.01, + "learning_rate": 8.017964927084842e-06, + "loss": 3.8566, + "step": 2564096 + }, + { + "epoch": 0.02, + "learning_rate": 8.009578979574322e-06, + "loss": 3.8537, + "step": 2564608 + }, + { + "epoch": 0.02, + "learning_rate": 8.001225789671263e-06, + "loss": 3.8409, + "step": 2565120 + }, + { + "epoch": 0.02, + "learning_rate": 7.992839842160745e-06, + "loss": 3.8459, + "step": 2565632 + }, + { + "epoch": 0.02, + "learning_rate": 7.984453894650225e-06, + "loss": 3.8548, + "step": 2566144 + }, + { + "epoch": 0.02, + "learning_rate": 7.976067947139703e-06, + "loss": 3.8425, + "step": 2566656 + }, + { + "epoch": 0.02, + "learning_rate": 7.967681999629183e-06, + "loss": 3.8631, + "step": 2567168 + }, + { + "epoch": 0.02, + "learning_rate": 7.959296052118665e-06, + "loss": 3.8414, + "step": 2567680 + }, + { + "epoch": 0.02, + "learning_rate": 7.950910104608145e-06, + "loss": 3.8415, + "step": 2568192 + }, + { + "epoch": 0.02, + "learning_rate": 7.942524157097623e-06, + "loss": 3.8475, + "step": 2568704 + }, + { + "epoch": 0.02, + "learning_rate": 7.934138209587103e-06, + "loss": 3.8552, + "step": 2569216 + }, + { + "epoch": 0.02, + "learning_rate": 7.925752262076585e-06, + "loss": 3.8557, + "step": 2569728 + }, + { + "epoch": 0.02, + "learning_rate": 7.917366314566063e-06, + "loss": 3.8439, + "step": 2570240 + }, + { + "epoch": 0.02, + "learning_rate": 7.908980367055543e-06, + "loss": 3.8414, + "step": 2570752 + }, + { + "epoch": 0.02, + "learning_rate": 7.900594419545025e-06, + "loss": 3.8388, + "step": 2571264 + }, + { + "epoch": 0.02, + "learning_rate": 7.892208472034503e-06, + "loss": 3.8562, + "step": 2571776 + }, + { + "epoch": 0.02, + "learning_rate": 7.883838903327714e-06, + "loss": 3.8312, + "step": 2572288 + }, + { + "epoch": 0.02, + "learning_rate": 7.875452955817195e-06, + "loss": 3.8375, + "step": 2572800 + }, + { + "epoch": 0.02, + "learning_rate": 7.867067008306675e-06, + "loss": 3.8546, + "step": 2573312 + }, + { + "epoch": 0.02, + "learning_rate": 7.858681060796154e-06, + "loss": 3.8474, + "step": 2573824 + }, + { + "epoch": 0.02, + "learning_rate": 7.850311492089366e-06, + "loss": 3.8431, + "step": 2574336 + }, + { + "epoch": 0.02, + "learning_rate": 7.841925544578846e-06, + "loss": 3.8482, + "step": 2574848 + }, + { + "epoch": 0.02, + "learning_rate": 7.833539597068326e-06, + "loss": 3.8403, + "step": 2575360 + }, + { + "epoch": 0.02, + "learning_rate": 7.825153649557806e-06, + "loss": 3.8497, + "step": 2575872 + }, + { + "epoch": 0.02, + "learning_rate": 7.816767702047286e-06, + "loss": 3.847, + "step": 2576384 + }, + { + "epoch": 0.02, + "learning_rate": 7.808381754536766e-06, + "loss": 3.8472, + "step": 2576896 + }, + { + "epoch": 0.02, + "learning_rate": 7.799995807026244e-06, + "loss": 3.8489, + "step": 2577408 + }, + { + "epoch": 0.02, + "learning_rate": 7.791626238319457e-06, + "loss": 3.8563, + "step": 2577920 + }, + { + "epoch": 0.02, + "learning_rate": 7.783256669612667e-06, + "loss": 3.8448, + "step": 2578432 + }, + { + "epoch": 0.02, + "learning_rate": 7.774870722102149e-06, + "loss": 3.8406, + "step": 2578944 + }, + { + "epoch": 0.02, + "learning_rate": 7.766484774591627e-06, + "loss": 3.848, + "step": 2579456 + }, + { + "epoch": 0.02, + "learning_rate": 7.758098827081107e-06, + "loss": 3.846, + "step": 2579968 + }, + { + "epoch": 0.02, + "learning_rate": 7.749712879570587e-06, + "loss": 3.8347, + "step": 2580480 + }, + { + "epoch": 0.02, + "learning_rate": 7.741326932060067e-06, + "loss": 3.8441, + "step": 2580992 + }, + { + "epoch": 0.02, + "learning_rate": 7.732940984549547e-06, + "loss": 3.8413, + "step": 2581504 + }, + { + "epoch": 0.02, + "learning_rate": 7.724555037039027e-06, + "loss": 3.8537, + "step": 2582016 + }, + { + "epoch": 0.02, + "learning_rate": 7.716169089528507e-06, + "loss": 3.8392, + "step": 2582528 + }, + { + "epoch": 0.02, + "learning_rate": 7.707783142017987e-06, + "loss": 3.848, + "step": 2583040 + }, + { + "epoch": 0.02, + "learning_rate": 7.699413573311198e-06, + "loss": 3.8314, + "step": 2583552 + }, + { + "epoch": 0.02, + "learning_rate": 7.69102762580068e-06, + "loss": 3.8467, + "step": 2584064 + }, + { + "epoch": 0.02, + "learning_rate": 7.682641678290158e-06, + "loss": 3.845, + "step": 2584576 + }, + { + "epoch": 0.02, + "learning_rate": 7.674272109583368e-06, + "loss": 3.8591, + "step": 2585088 + }, + { + "epoch": 0.02, + "learning_rate": 7.66588616207285e-06, + "loss": 3.8493, + "step": 2585600 + }, + { + "epoch": 0.02, + "learning_rate": 7.65750021456233e-06, + "loss": 3.8488, + "step": 2586112 + }, + { + "epoch": 0.02, + "learning_rate": 7.649114267051808e-06, + "loss": 3.8435, + "step": 2586624 + }, + { + "epoch": 0.02, + "learning_rate": 7.640728319541288e-06, + "loss": 3.8474, + "step": 2587136 + }, + { + "epoch": 0.02, + "learning_rate": 7.63234237203077e-06, + "loss": 3.8578, + "step": 2587648 + }, + { + "epoch": 0.02, + "learning_rate": 7.623956424520248e-06, + "loss": 3.8577, + "step": 2588160 + }, + { + "epoch": 0.02, + "learning_rate": 7.615570477009729e-06, + "loss": 3.8535, + "step": 2588672 + }, + { + "epoch": 0.02, + "learning_rate": 7.607200908302941e-06, + "loss": 3.8555, + "step": 2589184 + }, + { + "epoch": 0.02, + "learning_rate": 7.598831339596152e-06, + "loss": 3.8508, + "step": 2589696 + }, + { + "epoch": 0.02, + "learning_rate": 7.5904453920856305e-06, + "loss": 3.8464, + "step": 2590208 + }, + { + "epoch": 0.02, + "learning_rate": 7.582059444575111e-06, + "loss": 3.8449, + "step": 2590720 + }, + { + "epoch": 0.02, + "learning_rate": 7.573673497064591e-06, + "loss": 3.8504, + "step": 2591232 + }, + { + "epoch": 0.02, + "learning_rate": 7.56528754955407e-06, + "loss": 3.848, + "step": 2591744 + }, + { + "epoch": 0.02, + "learning_rate": 7.556917980847282e-06, + "loss": 3.8366, + "step": 2592256 + }, + { + "epoch": 0.02, + "learning_rate": 7.548532033336762e-06, + "loss": 3.8487, + "step": 2592768 + }, + { + "epoch": 0.02, + "learning_rate": 7.540146085826243e-06, + "loss": 3.8442, + "step": 2593280 + }, + { + "epoch": 0.02, + "learning_rate": 7.531760138315722e-06, + "loss": 3.8496, + "step": 2593792 + }, + { + "epoch": 0.02, + "learning_rate": 7.523406948412664e-06, + "loss": 3.8441, + "step": 2594304 + }, + { + "epoch": 0.02, + "learning_rate": 7.515021000902145e-06, + "loss": 3.8478, + "step": 2594816 + }, + { + "epoch": 0.03, + "eval_loss": 3.9727272987365723, + "eval_runtime": 290.8725, + "eval_samples_per_second": 1311.884, + "eval_steps_per_second": 40.997, + "step": 2594880 + }, + { + "epoch": 1.0, + "learning_rate": 7.506635053391625e-06, + "loss": 3.8391, + "step": 2595328 + }, + { + "epoch": 1.0, + "learning_rate": 7.498249105881104e-06, + "loss": 3.8418, + "step": 2595840 + }, + { + "epoch": 1.0, + "learning_rate": 7.489863158370584e-06, + "loss": 3.8503, + "step": 2596352 + }, + { + "epoch": 1.0, + "learning_rate": 7.481477210860065e-06, + "loss": 3.849, + "step": 2596864 + }, + { + "epoch": 1.0, + "learning_rate": 7.473091263349544e-06, + "loss": 3.8546, + "step": 2597376 + }, + { + "epoch": 1.0, + "learning_rate": 7.464705315839024e-06, + "loss": 3.8356, + "step": 2597888 + }, + { + "epoch": 1.0, + "learning_rate": 7.456319368328504e-06, + "loss": 3.8421, + "step": 2598400 + }, + { + "epoch": 1.0, + "learning_rate": 7.447933420817985e-06, + "loss": 3.8386, + "step": 2598912 + }, + { + "epoch": 1.0, + "learning_rate": 7.439547473307464e-06, + "loss": 3.8503, + "step": 2599424 + }, + { + "epoch": 1.0, + "learning_rate": 7.431161525796944e-06, + "loss": 3.8501, + "step": 2599936 + }, + { + "epoch": 1.0, + "learning_rate": 7.422775578286424e-06, + "loss": 3.8496, + "step": 2600448 + }, + { + "epoch": 1.0, + "learning_rate": 7.414389630775903e-06, + "loss": 3.8532, + "step": 2600960 + }, + { + "epoch": 1.0, + "learning_rate": 7.406003683265384e-06, + "loss": 3.8358, + "step": 2601472 + }, + { + "epoch": 1.0, + "learning_rate": 7.397617735754864e-06, + "loss": 3.8385, + "step": 2601984 + }, + { + "epoch": 1.0, + "learning_rate": 7.389231788244343e-06, + "loss": 3.8431, + "step": 2602496 + }, + { + "epoch": 1.0, + "learning_rate": 7.380845840733823e-06, + "loss": 3.8377, + "step": 2603008 + }, + { + "epoch": 1.0, + "learning_rate": 7.3724598932233035e-06, + "loss": 3.8466, + "step": 2603520 + }, + { + "epoch": 1.0, + "learning_rate": 7.364090324516515e-06, + "loss": 3.841, + "step": 2604032 + }, + { + "epoch": 1.0, + "learning_rate": 7.3557043770059934e-06, + "loss": 3.8419, + "step": 2604544 + }, + { + "epoch": 1.0, + "learning_rate": 7.347318429495474e-06, + "loss": 3.873, + "step": 2605056 + }, + { + "epoch": 1.0, + "learning_rate": 7.338932481984954e-06, + "loss": 3.8446, + "step": 2605568 + }, + { + "epoch": 1.0, + "learning_rate": 7.330546534474433e-06, + "loss": 3.8527, + "step": 2606080 + }, + { + "epoch": 1.0, + "learning_rate": 7.322176965767645e-06, + "loss": 3.8503, + "step": 2606592 + }, + { + "epoch": 1.0, + "learning_rate": 7.313791018257126e-06, + "loss": 3.8595, + "step": 2607104 + }, + { + "epoch": 1.0, + "learning_rate": 7.305405070746606e-06, + "loss": 3.8415, + "step": 2607616 + }, + { + "epoch": 1.0, + "learning_rate": 7.297019123236085e-06, + "loss": 3.8427, + "step": 2608128 + }, + { + "epoch": 1.0, + "learning_rate": 7.288633175725565e-06, + "loss": 3.8466, + "step": 2608640 + }, + { + "epoch": 1.0, + "learning_rate": 7.2802472282150456e-06, + "loss": 3.848, + "step": 2609152 + }, + { + "epoch": 1.0, + "learning_rate": 7.271861280704524e-06, + "loss": 3.838, + "step": 2609664 + }, + { + "epoch": 1.01, + "learning_rate": 7.2634917119977355e-06, + "loss": 3.8452, + "step": 2610176 + }, + { + "epoch": 1.01, + "learning_rate": 7.255105764487216e-06, + "loss": 3.8593, + "step": 2610688 + }, + { + "epoch": 1.01, + "learning_rate": 7.246736195780428e-06, + "loss": 3.8497, + "step": 2611200 + }, + { + "epoch": 1.01, + "learning_rate": 7.238350248269907e-06, + "loss": 3.8453, + "step": 2611712 + }, + { + "epoch": 1.01, + "learning_rate": 7.229964300759387e-06, + "loss": 3.8533, + "step": 2612224 + }, + { + "epoch": 1.01, + "learning_rate": 7.221594732052599e-06, + "loss": 3.8511, + "step": 2612736 + }, + { + "epoch": 1.01, + "learning_rate": 7.213208784542079e-06, + "loss": 3.8484, + "step": 2613248 + }, + { + "epoch": 1.01, + "learning_rate": 7.204822837031558e-06, + "loss": 3.8339, + "step": 2613760 + }, + { + "epoch": 1.01, + "learning_rate": 7.1964368895210385e-06, + "loss": 3.8479, + "step": 2614272 + }, + { + "epoch": 1.01, + "learning_rate": 7.1880509420105184e-06, + "loss": 3.8343, + "step": 2614784 + }, + { + "epoch": 1.01, + "learning_rate": 7.1796649944999975e-06, + "loss": 3.8451, + "step": 2615296 + }, + { + "epoch": 1.01, + "learning_rate": 7.1712790469894775e-06, + "loss": 3.8433, + "step": 2615808 + }, + { + "epoch": 1.01, + "learning_rate": 7.162893099478958e-06, + "loss": 3.8529, + "step": 2616320 + }, + { + "epoch": 1.01, + "learning_rate": 7.154507151968438e-06, + "loss": 3.8447, + "step": 2616832 + }, + { + "epoch": 1.01, + "learning_rate": 7.146137583261649e-06, + "loss": 3.8431, + "step": 2617344 + }, + { + "epoch": 1.01, + "learning_rate": 7.137751635751129e-06, + "loss": 3.8522, + "step": 2617856 + }, + { + "epoch": 1.01, + "learning_rate": 7.129365688240609e-06, + "loss": 3.8466, + "step": 2618368 + }, + { + "epoch": 1.01, + "learning_rate": 7.120996119533821e-06, + "loss": 3.8508, + "step": 2618880 + }, + { + "epoch": 1.01, + "learning_rate": 7.1126101720233e-06, + "loss": 3.8371, + "step": 2619392 + }, + { + "epoch": 1.01, + "learning_rate": 7.1042242245127805e-06, + "loss": 3.8386, + "step": 2619904 + }, + { + "epoch": 1.01, + "learning_rate": 7.0958382770022605e-06, + "loss": 3.8503, + "step": 2620416 + }, + { + "epoch": 1.01, + "learning_rate": 7.0874523294917396e-06, + "loss": 3.8481, + "step": 2620928 + }, + { + "epoch": 1.01, + "learning_rate": 7.0790663819812195e-06, + "loss": 3.8451, + "step": 2621440 + }, + { + "epoch": 1.01, + "learning_rate": 7.0706804344707e-06, + "loss": 3.8306, + "step": 2621952 + }, + { + "epoch": 1.01, + "learning_rate": 7.062294486960179e-06, + "loss": 3.85, + "step": 2622464 + }, + { + "epoch": 1.01, + "learning_rate": 7.053908539449659e-06, + "loss": 3.8289, + "step": 2622976 + }, + { + "epoch": 1.01, + "learning_rate": 7.045522591939139e-06, + "loss": 3.8585, + "step": 2623488 + }, + { + "epoch": 1.01, + "learning_rate": 7.0371366444286184e-06, + "loss": 3.8298, + "step": 2624000 + }, + { + "epoch": 1.01, + "learning_rate": 7.02876707572183e-06, + "loss": 3.854, + "step": 2624512 + }, + { + "epoch": 1.01, + "learning_rate": 7.020381128211311e-06, + "loss": 3.842, + "step": 2625024 + }, + { + "epoch": 1.01, + "learning_rate": 7.011995180700791e-06, + "loss": 3.8386, + "step": 2625536 + }, + { + "epoch": 1.01, + "learning_rate": 7.00360923319027e-06, + "loss": 3.8397, + "step": 2626048 + }, + { + "epoch": 1.01, + "learning_rate": 6.99522328567975e-06, + "loss": 3.8429, + "step": 2626560 + }, + { + "epoch": 1.01, + "learning_rate": 6.9868537169729615e-06, + "loss": 3.8243, + "step": 2627072 + }, + { + "epoch": 1.01, + "learning_rate": 6.978467769462442e-06, + "loss": 3.837, + "step": 2627584 + }, + { + "epoch": 1.01, + "learning_rate": 6.970081821951921e-06, + "loss": 3.8444, + "step": 2628096 + }, + { + "epoch": 1.01, + "learning_rate": 6.961695874441401e-06, + "loss": 3.8465, + "step": 2628608 + }, + { + "epoch": 1.01, + "learning_rate": 6.953309926930881e-06, + "loss": 3.8313, + "step": 2629120 + }, + { + "epoch": 1.01, + "learning_rate": 6.944940358224092e-06, + "loss": 3.8362, + "step": 2629632 + }, + { + "epoch": 1.01, + "learning_rate": 6.936554410713572e-06, + "loss": 3.8319, + "step": 2630144 + }, + { + "epoch": 1.01, + "learning_rate": 6.928168463203052e-06, + "loss": 3.8388, + "step": 2630656 + }, + { + "epoch": 1.01, + "learning_rate": 6.919798894496264e-06, + "loss": 3.8447, + "step": 2631168 + }, + { + "epoch": 1.01, + "learning_rate": 6.911412946985743e-06, + "loss": 3.8453, + "step": 2631680 + }, + { + "epoch": 1.01, + "learning_rate": 6.903026999475224e-06, + "loss": 3.8551, + "step": 2632192 + }, + { + "epoch": 1.01, + "learning_rate": 6.8946410519647036e-06, + "loss": 3.8514, + "step": 2632704 + }, + { + "epoch": 1.01, + "learning_rate": 6.886255104454183e-06, + "loss": 3.8507, + "step": 2633216 + }, + { + "epoch": 1.01, + "learning_rate": 6.877869156943663e-06, + "loss": 3.8347, + "step": 2633728 + }, + { + "epoch": 1.01, + "learning_rate": 6.8694832094331434e-06, + "loss": 3.8448, + "step": 2634240 + }, + { + "epoch": 1.01, + "learning_rate": 6.861097261922623e-06, + "loss": 3.8473, + "step": 2634752 + }, + { + "epoch": 1.01, + "learning_rate": 6.8527113144121025e-06, + "loss": 3.837, + "step": 2635264 + }, + { + "epoch": 1.01, + "learning_rate": 6.8443253669015825e-06, + "loss": 3.8444, + "step": 2635776 + }, + { + "epoch": 1.01, + "learning_rate": 6.835939419391063e-06, + "loss": 3.8446, + "step": 2636288 + }, + { + "epoch": 1.01, + "learning_rate": 6.827569850684273e-06, + "loss": 3.8565, + "step": 2636800 + }, + { + "epoch": 1.01, + "learning_rate": 6.819183903173754e-06, + "loss": 3.8471, + "step": 2637312 + }, + { + "epoch": 1.01, + "learning_rate": 6.810797955663234e-06, + "loss": 3.8323, + "step": 2637824 + }, + { + "epoch": 1.01, + "learning_rate": 6.802412008152714e-06, + "loss": 3.839, + "step": 2638336 + }, + { + "epoch": 1.01, + "learning_rate": 6.794026060642193e-06, + "loss": 3.8502, + "step": 2638848 + }, + { + "epoch": 1.01, + "learning_rate": 6.785656491935405e-06, + "loss": 3.8496, + "step": 2639360 + }, + { + "epoch": 1.01, + "learning_rate": 6.7772705444248855e-06, + "loss": 3.8467, + "step": 2639872 + }, + { + "epoch": 1.01, + "learning_rate": 6.768884596914364e-06, + "loss": 3.8549, + "step": 2640384 + }, + { + "epoch": 1.02, + "learning_rate": 6.7604986494038445e-06, + "loss": 3.8524, + "step": 2640896 + }, + { + "epoch": 1.02, + "learning_rate": 6.7521127018933245e-06, + "loss": 3.8365, + "step": 2641408 + }, + { + "epoch": 1.02, + "learning_rate": 6.743726754382805e-06, + "loss": 3.8473, + "step": 2641920 + }, + { + "epoch": 1.02, + "learning_rate": 6.735357185676015e-06, + "loss": 3.8464, + "step": 2642432 + }, + { + "epoch": 1.02, + "learning_rate": 6.726987616969227e-06, + "loss": 3.8402, + "step": 2642944 + }, + { + "epoch": 1.02, + "learning_rate": 6.718601669458708e-06, + "loss": 3.8609, + "step": 2643456 + }, + { + "epoch": 1.02, + "learning_rate": 6.710215721948188e-06, + "loss": 3.8443, + "step": 2643968 + }, + { + "epoch": 1.02, + "learning_rate": 6.701829774437667e-06, + "loss": 3.8362, + "step": 2644480 + }, + { + "epoch": 1.02, + "learning_rate": 6.693443826927147e-06, + "loss": 3.8453, + "step": 2644992 + }, + { + "epoch": 1.02, + "learning_rate": 6.6850578794166275e-06, + "loss": 3.8535, + "step": 2645504 + }, + { + "epoch": 1.02, + "learning_rate": 6.676671931906106e-06, + "loss": 3.8503, + "step": 2646016 + }, + { + "epoch": 1.02, + "learning_rate": 6.668302363199317e-06, + "loss": 3.8438, + "step": 2646528 + }, + { + "epoch": 1.02, + "learning_rate": 6.659916415688798e-06, + "loss": 3.8356, + "step": 2647040 + }, + { + "epoch": 1.02, + "learning_rate": 6.651530468178278e-06, + "loss": 3.837, + "step": 2647552 + }, + { + "epoch": 1.02, + "learning_rate": 6.643144520667757e-06, + "loss": 3.854, + "step": 2648064 + }, + { + "epoch": 1.02, + "learning_rate": 6.634758573157237e-06, + "loss": 3.8273, + "step": 2648576 + }, + { + "epoch": 1.02, + "learning_rate": 6.626372625646718e-06, + "loss": 3.8401, + "step": 2649088 + }, + { + "epoch": 1.02, + "learning_rate": 6.617986678136197e-06, + "loss": 3.8484, + "step": 2649600 + }, + { + "epoch": 1.02, + "learning_rate": 6.609600730625677e-06, + "loss": 3.8411, + "step": 2650112 + }, + { + "epoch": 1.02, + "learning_rate": 6.601231161918889e-06, + "loss": 3.8403, + "step": 2650624 + }, + { + "epoch": 1.02, + "learning_rate": 6.5928452144083695e-06, + "loss": 3.8466, + "step": 2651136 + }, + { + "epoch": 1.02, + "learning_rate": 6.584459266897848e-06, + "loss": 3.8399, + "step": 2651648 + }, + { + "epoch": 1.02, + "learning_rate": 6.5760896981910594e-06, + "loss": 3.8472, + "step": 2652160 + }, + { + "epoch": 1.02, + "learning_rate": 6.56770375068054e-06, + "loss": 3.8439, + "step": 2652672 + }, + { + "epoch": 1.02, + "learning_rate": 6.559317803170019e-06, + "loss": 3.8425, + "step": 2653184 + }, + { + "epoch": 1.02, + "learning_rate": 6.550931855659499e-06, + "loss": 3.8498, + "step": 2653696 + }, + { + "epoch": 1.02, + "learning_rate": 6.542545908148979e-06, + "loss": 3.8531, + "step": 2654208 + }, + { + "epoch": 1.02, + "learning_rate": 6.53415996063846e-06, + "loss": 3.848, + "step": 2654720 + }, + { + "epoch": 1.02, + "learning_rate": 6.525774013127939e-06, + "loss": 3.837, + "step": 2655232 + }, + { + "epoch": 1.02, + "learning_rate": 6.517388065617419e-06, + "loss": 3.8452, + "step": 2655744 + }, + { + "epoch": 1.02, + "learning_rate": 6.509002118106899e-06, + "loss": 3.8428, + "step": 2656256 + }, + { + "epoch": 1.02, + "learning_rate": 6.500616170596378e-06, + "loss": 3.8308, + "step": 2656768 + }, + { + "epoch": 1.02, + "learning_rate": 6.49224660188959e-06, + "loss": 3.8473, + "step": 2657280 + }, + { + "epoch": 1.02, + "learning_rate": 6.483860654379071e-06, + "loss": 3.8339, + "step": 2657792 + }, + { + "epoch": 1.02, + "learning_rate": 6.475474706868549e-06, + "loss": 3.8506, + "step": 2658304 + }, + { + "epoch": 1.02, + "learning_rate": 6.46708875935803e-06, + "loss": 3.8356, + "step": 2658816 + }, + { + "epoch": 1.02, + "learning_rate": 6.45870281184751e-06, + "loss": 3.8461, + "step": 2659328 + }, + { + "epoch": 1.02, + "learning_rate": 6.450333243140721e-06, + "loss": 3.8329, + "step": 2659840 + }, + { + "epoch": 1.02, + "learning_rate": 6.4419472956302e-06, + "loss": 3.8451, + "step": 2660352 + }, + { + "epoch": 1.02, + "learning_rate": 6.43356134811968e-06, + "loss": 3.8367, + "step": 2660864 + }, + { + "epoch": 1.02, + "learning_rate": 6.425175400609161e-06, + "loss": 3.8577, + "step": 2661376 + }, + { + "epoch": 1.02, + "learning_rate": 6.41678945309864e-06, + "loss": 3.8528, + "step": 2661888 + }, + { + "epoch": 1.02, + "learning_rate": 6.408419884391852e-06, + "loss": 3.8461, + "step": 2662400 + }, + { + "epoch": 1.02, + "learning_rate": 6.400033936881332e-06, + "loss": 3.8382, + "step": 2662912 + }, + { + "epoch": 1.02, + "learning_rate": 6.3916643681745435e-06, + "loss": 3.8452, + "step": 2663424 + }, + { + "epoch": 1.02, + "learning_rate": 6.383278420664023e-06, + "loss": 3.8552, + "step": 2663936 + }, + { + "epoch": 1.02, + "learning_rate": 6.3748924731535025e-06, + "loss": 3.8582, + "step": 2664448 + }, + { + "epoch": 1.02, + "learning_rate": 6.366506525642983e-06, + "loss": 3.8481, + "step": 2664960 + }, + { + "epoch": 1.02, + "learning_rate": 6.358120578132463e-06, + "loss": 3.8546, + "step": 2665472 + }, + { + "epoch": 1.02, + "learning_rate": 6.349734630621942e-06, + "loss": 3.8476, + "step": 2665984 + }, + { + "epoch": 1.02, + "learning_rate": 6.341365061915154e-06, + "loss": 3.8445, + "step": 2666496 + }, + { + "epoch": 1.02, + "learning_rate": 6.332979114404634e-06, + "loss": 3.8418, + "step": 2667008 + }, + { + "epoch": 1.02, + "learning_rate": 6.324593166894113e-06, + "loss": 3.8444, + "step": 2667520 + }, + { + "epoch": 1.02, + "learning_rate": 6.316207219383594e-06, + "loss": 3.8465, + "step": 2668032 + }, + { + "epoch": 1.02, + "learning_rate": 6.307821271873074e-06, + "loss": 3.8356, + "step": 2668544 + }, + { + "epoch": 1.02, + "learning_rate": 6.2994517031662855e-06, + "loss": 3.8417, + "step": 2669056 + }, + { + "epoch": 1.02, + "learning_rate": 6.291065755655765e-06, + "loss": 3.8461, + "step": 2669568 + }, + { + "epoch": 1.02, + "learning_rate": 6.2826798081452446e-06, + "loss": 3.8415, + "step": 2670080 + }, + { + "epoch": 1.02, + "learning_rate": 6.274293860634725e-06, + "loss": 3.843, + "step": 2670592 + }, + { + "epoch": 1.02, + "learning_rate": 6.265907913124204e-06, + "loss": 3.8397, + "step": 2671104 + }, + { + "epoch": 1.03, + "eval_loss": 3.9721450805664062, + "eval_runtime": 308.5372, + "eval_samples_per_second": 1236.775, + "eval_steps_per_second": 38.65, + "step": 2671200 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.0964642726663942e+18, + "trial_name": null, + "trial_params": null +}