diff --git "a/checkpoint-1984307/trainer_state.json" "b/checkpoint-1984307/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-1984307/trainer_state.json" @@ -0,0 +1,23483 @@ +{ + "best_metric": 3.9862301349639893, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/full/lstm/1/checkpoints/checkpoint-1984307", + "epoch": 0.025000606015738065, + "eval_steps": 10, + "global_step": 1984307, + "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": 10.8213, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 7.5645, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 7.0515, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 6.9831, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 6.9548, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 6.8802, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 6.736, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 6.6253, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 6.5411, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 6.4495, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 6.4027, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 6.3385, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 6.2752, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989098268236324e-05, + "loss": 6.2086, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988259673485272e-05, + "loss": 6.1566, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.98742107873422e-05, + "loss": 6.1122, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986582483983168e-05, + "loss": 6.0644, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985743889232116e-05, + "loss": 6.0115, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984905294481064e-05, + "loss": 5.9764, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984066699730012e-05, + "loss": 5.9421, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.9832281049789595e-05, + "loss": 5.8975, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.982391148108281e-05, + "loss": 5.8621, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.981552553357229e-05, + "loss": 5.8402, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.980713958606178e-05, + "loss": 5.8026, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.979875363855125e-05, + "loss": 5.7808, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790400448648195e-05, + "loss": 5.754, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 5.7313, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 5.7017, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 5.6683, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 5.6615, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748470711095595e-05, + "loss": 5.6285, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.974008476358507e-05, + "loss": 5.6122, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 5.586, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.9723329247367764e-05, + "loss": 5.5823, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.9714943299857244e-05, + "loss": 5.5499, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.9706557352346724e-05, + "loss": 5.5409, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 5.5269, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968980183612942e-05, + "loss": 5.5069, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.96814158886189e-05, + "loss": 5.4964, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967302994110837e-05, + "loss": 5.4737, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966464399359785e-05, + "loss": 5.4496, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965625804608733e-05, + "loss": 5.4441, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964787209857681e-05, + "loss": 5.4158, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963948615106629e-05, + "loss": 5.4276, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 5.4002, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962273063484898e-05, + "loss": 5.3954, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 5.3797, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 5.3764, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 5.3695, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.958920322361064e-05, + "loss": 5.3413, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958081727610012e-05, + "loss": 5.3289, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957244770739333e-05, + "loss": 5.3212, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956406175988281e-05, + "loss": 5.3278, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 5.3042, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 5.3119, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 5.2815, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 5.2791, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522148401133936e-05, + "loss": 5.2658, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951376245362342e-05, + "loss": 5.2593, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.95053765061129e-05, + "loss": 5.2565, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949699055860238e-05, + "loss": 5.2359, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948860461109186e-05, + "loss": 5.2316, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.948023504238507e-05, + "loss": 5.2351, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947184909487455e-05, + "loss": 5.2133, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946346314736403e-05, + "loss": 5.2125, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 5.2008, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944670763114672e-05, + "loss": 5.2003, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.94383216836362e-05, + "loss": 5.1851, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942993573612568e-05, + "loss": 5.1879, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942154978861516e-05, + "loss": 5.1751, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.941316384110464e-05, + "loss": 5.1642, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.940477789359412e-05, + "loss": 5.1667, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.93963919460836e-05, + "loss": 5.1528, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388022377376816e-05, + "loss": 5.1613, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379636429866296e-05, + "loss": 5.1582, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371266861159505e-05, + "loss": 5.1489, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362880913648985e-05, + "loss": 5.1294, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354494966138465e-05, + "loss": 5.1139, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346109018627945e-05, + "loss": 5.1069, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337723071117425e-05, + "loss": 5.112, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329337123606905e-05, + "loss": 5.1168, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932095117609638e-05, + "loss": 5.1102, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931256522858586e-05, + "loss": 5.0849, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930417928107534e-05, + "loss": 5.0786, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.9295793333564825e-05, + "loss": 5.0875, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.9287407386054305e-05, + "loss": 5.0727, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.9279021438543785e-05, + "loss": 5.0728, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.9270651869836994e-05, + "loss": 5.0653, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.9262265922326474e-05, + "loss": 5.0665, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.9253879974815954e-05, + "loss": 5.0551, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.9245494027305433e-05, + "loss": 5.047, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923712445859864e-05, + "loss": 5.0335, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922873851108812e-05, + "loss": 5.047, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.92203525635776e-05, + "loss": 5.0329, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921196661606708e-05, + "loss": 5.0162, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920358066855656e-05, + "loss": 5.0157, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919519472104604e-05, + "loss": 5.0278, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918682515233926e-05, + "loss": 5.0184, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917843920482874e-05, + "loss": 5.0099, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917005325731822e-05, + "loss": 4.9974, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.91616673098077e-05, + "loss": 5.0021, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915329774110091e-05, + "loss": 4.9813, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914491179359039e-05, + "loss": 4.9968, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.913652584607987e-05, + "loss": 4.9991, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.912813989856935e-05, + "loss": 4.9737, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.911975395105883e-05, + "loss": 4.9676, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.911136800354831e-05, + "loss": 4.9428, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910298205603779e-05, + "loss": 4.9555, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909459610852727e-05, + "loss": 4.9556, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.9086226539820476e-05, + "loss": 4.9508, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907785697111369e-05, + "loss": 4.9509, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906947102360317e-05, + "loss": 4.9356, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906110145489638e-05, + "loss": 4.9361, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905271550738586e-05, + "loss": 4.937, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904432955987534e-05, + "loss": 4.9393, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903594361236482e-05, + "loss": 4.9269, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.90275576648543e-05, + "loss": 4.9157, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901917171734378e-05, + "loss": 4.9165, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901078576983326e-05, + "loss": 4.92, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.900239982232274e-05, + "loss": 4.9154, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994013874812214e-05, + "loss": 4.91, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.898564430610543e-05, + "loss": 4.8992, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977274737398646e-05, + "loss": 4.8913, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968888789888125e-05, + "loss": 4.8854, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960502842377605e-05, + "loss": 4.8927, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952116894867085e-05, + "loss": 4.8904, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943730947356565e-05, + "loss": 4.8911, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.893534499984604e-05, + "loss": 4.8653, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892695905233552e-05, + "loss": 4.8793, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918573104825e-05, + "loss": 4.8787, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.891018715731448e-05, + "loss": 4.865, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890181758860769e-05, + "loss": 4.8807, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889343164109717e-05, + "loss": 4.8592, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888504569358665e-05, + "loss": 4.8725, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.8876659746076134e-05, + "loss": 4.8632, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.8868273798565614e-05, + "loss": 4.8408, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885990422985882e-05, + "loss": 4.8402, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.88515182823483e-05, + "loss": 4.8403, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884313233483778e-05, + "loss": 4.844, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883474638732726e-05, + "loss": 4.8483, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882637681862047e-05, + "loss": 4.8431, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881799087110995e-05, + "loss": 4.8381, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.880960492359943e-05, + "loss": 4.8284, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880121897608891e-05, + "loss": 4.8163, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879283302857839e-05, + "loss": 4.8157, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878444708106787e-05, + "loss": 4.8223, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877606113355735e-05, + "loss": 4.8298, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876767518604683e-05, + "loss": 4.8215, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875930561734005e-05, + "loss": 4.804, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875091966982953e-05, + "loss": 4.8036, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.769171237945557, + "eval_runtime": 589.0702, + "eval_samples_per_second": 647.785, + "eval_steps_per_second": 20.244, + "step": 76319 + }, + { + "epoch": 0.0, + "learning_rate": 4.874253372231901e-05, + "loss": 4.8109, + "step": 76800 + }, + { + "epoch": 0.0, + "learning_rate": 4.873414777480849e-05, + "loss": 4.8026, + "step": 77312 + }, + { + "epoch": 0.0, + "learning_rate": 4.872576182729797e-05, + "loss": 4.7949, + "step": 77824 + }, + { + "epoch": 0.0, + "learning_rate": 4.871737587978745e-05, + "loss": 4.7949, + "step": 78336 + }, + { + "epoch": 0.0, + "learning_rate": 4.870898993227693e-05, + "loss": 4.7846, + "step": 78848 + }, + { + "epoch": 0.0, + "learning_rate": 4.87006039847664e-05, + "loss": 4.7696, + "step": 79360 + }, + { + "epoch": 0.0, + "learning_rate": 4.869221803725588e-05, + "loss": 4.7767, + "step": 79872 + }, + { + "epoch": 0.0, + "learning_rate": 4.868383208974536e-05, + "loss": 4.7869, + "step": 80384 + }, + { + "epoch": 0.0, + "learning_rate": 4.867544614223484e-05, + "loss": 4.7699, + "step": 80896 + }, + { + "epoch": 0.0, + "learning_rate": 4.8667076573528056e-05, + "loss": 4.7771, + "step": 81408 + }, + { + "epoch": 0.0, + "learning_rate": 4.8658690626017536e-05, + "loss": 4.7817, + "step": 81920 + }, + { + "epoch": 0.0, + "learning_rate": 4.8650304678507016e-05, + "loss": 4.7796, + "step": 82432 + }, + { + "epoch": 0.0, + "learning_rate": 4.8641918730996496e-05, + "loss": 4.7685, + "step": 82944 + }, + { + "epoch": 0.0, + "learning_rate": 4.8633532783485976e-05, + "loss": 4.7648, + "step": 83456 + }, + { + "epoch": 0.0, + "learning_rate": 4.8625146835975456e-05, + "loss": 4.7622, + "step": 83968 + }, + { + "epoch": 0.0, + "learning_rate": 4.8616760888464936e-05, + "loss": 4.7531, + "step": 84480 + }, + { + "epoch": 0.0, + "learning_rate": 4.8608374940954416e-05, + "loss": 4.7559, + "step": 84992 + }, + { + "epoch": 0.0, + "learning_rate": 4.8599988993443896e-05, + "loss": 4.7563, + "step": 85504 + }, + { + "epoch": 0.0, + "learning_rate": 4.8591603045933376e-05, + "loss": 4.7553, + "step": 86016 + }, + { + "epoch": 0.0, + "learning_rate": 4.8583217098422856e-05, + "loss": 4.7532, + "step": 86528 + }, + { + "epoch": 0.0, + "learning_rate": 4.8574831150912336e-05, + "loss": 4.7413, + "step": 87040 + }, + { + "epoch": 0.0, + "learning_rate": 4.8566445203401816e-05, + "loss": 4.7521, + "step": 87552 + }, + { + "epoch": 0.0, + "learning_rate": 4.855805925589129e-05, + "loss": 4.7377, + "step": 88064 + }, + { + "epoch": 0.0, + "learning_rate": 4.854967330838077e-05, + "loss": 4.7476, + "step": 88576 + }, + { + "epoch": 0.0, + "learning_rate": 4.8541287360870256e-05, + "loss": 4.737, + "step": 89088 + }, + { + "epoch": 0.0, + "learning_rate": 4.85329341709672e-05, + "loss": 4.7359, + "step": 89600 + }, + { + "epoch": 0.0, + "learning_rate": 4.852454822345668e-05, + "loss": 4.7376, + "step": 90112 + }, + { + "epoch": 0.0, + "learning_rate": 4.851616227594616e-05, + "loss": 4.7198, + "step": 90624 + }, + { + "epoch": 0.0, + "learning_rate": 4.850777632843564e-05, + "loss": 4.7336, + "step": 91136 + }, + { + "epoch": 0.01, + "learning_rate": 4.8499390380925114e-05, + "loss": 4.714, + "step": 91648 + }, + { + "epoch": 0.01, + "learning_rate": 4.8491004433414594e-05, + "loss": 4.7198, + "step": 92160 + }, + { + "epoch": 0.01, + "learning_rate": 4.8482618485904074e-05, + "loss": 4.7157, + "step": 92672 + }, + { + "epoch": 0.01, + "learning_rate": 4.847424891719729e-05, + "loss": 4.7243, + "step": 93184 + }, + { + "epoch": 0.01, + "learning_rate": 4.84658793484905e-05, + "loss": 4.7119, + "step": 93696 + }, + { + "epoch": 0.01, + "learning_rate": 4.845749340097998e-05, + "loss": 4.7053, + "step": 94208 + }, + { + "epoch": 0.01, + "learning_rate": 4.844910745346946e-05, + "loss": 4.7219, + "step": 94720 + }, + { + "epoch": 0.01, + "learning_rate": 4.844072150595894e-05, + "loss": 4.7076, + "step": 95232 + }, + { + "epoch": 0.01, + "learning_rate": 4.843233555844842e-05, + "loss": 4.7151, + "step": 95744 + }, + { + "epoch": 0.01, + "learning_rate": 4.84239496109379e-05, + "loss": 4.7019, + "step": 96256 + }, + { + "epoch": 0.01, + "learning_rate": 4.841556366342738e-05, + "loss": 4.6875, + "step": 96768 + }, + { + "epoch": 0.01, + "learning_rate": 4.840717771591686e-05, + "loss": 4.6919, + "step": 97280 + }, + { + "epoch": 0.01, + "learning_rate": 4.839880814721007e-05, + "loss": 4.6831, + "step": 97792 + }, + { + "epoch": 0.01, + "learning_rate": 4.839042219969955e-05, + "loss": 4.6987, + "step": 98304 + }, + { + "epoch": 0.01, + "learning_rate": 4.838203625218903e-05, + "loss": 4.6872, + "step": 98816 + }, + { + "epoch": 0.01, + "learning_rate": 4.837365030467851e-05, + "loss": 4.6933, + "step": 99328 + }, + { + "epoch": 0.01, + "learning_rate": 4.836526435716799e-05, + "loss": 4.6852, + "step": 99840 + }, + { + "epoch": 0.01, + "learning_rate": 4.8356894788461196e-05, + "loss": 4.6899, + "step": 100352 + }, + { + "epoch": 0.01, + "learning_rate": 4.8348508840950676e-05, + "loss": 4.6865, + "step": 100864 + }, + { + "epoch": 0.01, + "learning_rate": 4.8340122893440156e-05, + "loss": 4.6644, + "step": 101376 + }, + { + "epoch": 0.01, + "learning_rate": 4.833173694592964e-05, + "loss": 4.668, + "step": 101888 + }, + { + "epoch": 0.01, + "learning_rate": 4.832336737722285e-05, + "loss": 4.6661, + "step": 102400 + }, + { + "epoch": 0.01, + "learning_rate": 4.831498142971233e-05, + "loss": 4.6784, + "step": 102912 + }, + { + "epoch": 0.01, + "learning_rate": 4.830659548220181e-05, + "loss": 4.6562, + "step": 103424 + }, + { + "epoch": 0.01, + "learning_rate": 4.829820953469129e-05, + "loss": 4.6805, + "step": 103936 + }, + { + "epoch": 0.01, + "learning_rate": 4.828982358718077e-05, + "loss": 4.6559, + "step": 104448 + }, + { + "epoch": 0.01, + "learning_rate": 4.828143763967025e-05, + "loss": 4.6552, + "step": 104960 + }, + { + "epoch": 0.01, + "learning_rate": 4.827305169215973e-05, + "loss": 4.6579, + "step": 105472 + }, + { + "epoch": 0.01, + "learning_rate": 4.826466574464921e-05, + "loss": 4.6531, + "step": 105984 + }, + { + "epoch": 0.01, + "learning_rate": 4.825627979713869e-05, + "loss": 4.6541, + "step": 106496 + }, + { + "epoch": 0.01, + "learning_rate": 4.824792660723563e-05, + "loss": 4.6459, + "step": 107008 + }, + { + "epoch": 0.01, + "learning_rate": 4.823954065972511e-05, + "loss": 4.6447, + "step": 107520 + }, + { + "epoch": 0.01, + "learning_rate": 4.8231171091018326e-05, + "loss": 4.6548, + "step": 108032 + }, + { + "epoch": 0.01, + "learning_rate": 4.8222785143507806e-05, + "loss": 4.6412, + "step": 108544 + }, + { + "epoch": 0.01, + "learning_rate": 4.8214399195997286e-05, + "loss": 4.6403, + "step": 109056 + }, + { + "epoch": 0.01, + "learning_rate": 4.8206013248486766e-05, + "loss": 4.6374, + "step": 109568 + }, + { + "epoch": 0.01, + "learning_rate": 4.8197627300976246e-05, + "loss": 4.643, + "step": 110080 + }, + { + "epoch": 0.01, + "learning_rate": 4.8189241353465726e-05, + "loss": 4.6266, + "step": 110592 + }, + { + "epoch": 0.01, + "learning_rate": 4.8180855405955206e-05, + "loss": 4.6451, + "step": 111104 + }, + { + "epoch": 0.01, + "learning_rate": 4.8172485837248415e-05, + "loss": 4.6328, + "step": 111616 + }, + { + "epoch": 0.01, + "learning_rate": 4.8164099889737895e-05, + "loss": 4.6304, + "step": 112128 + }, + { + "epoch": 0.01, + "learning_rate": 4.8155713942227375e-05, + "loss": 4.6366, + "step": 112640 + }, + { + "epoch": 0.01, + "learning_rate": 4.8147327994716854e-05, + "loss": 4.6245, + "step": 113152 + }, + { + "epoch": 0.01, + "learning_rate": 4.8138942047206334e-05, + "loss": 4.6417, + "step": 113664 + }, + { + "epoch": 0.01, + "learning_rate": 4.8130556099695814e-05, + "loss": 4.6454, + "step": 114176 + }, + { + "epoch": 0.01, + "learning_rate": 4.8122170152185294e-05, + "loss": 4.6396, + "step": 114688 + }, + { + "epoch": 0.01, + "learning_rate": 4.8113784204674774e-05, + "loss": 4.6219, + "step": 115200 + }, + { + "epoch": 0.01, + "learning_rate": 4.8105398257164254e-05, + "loss": 4.6139, + "step": 115712 + }, + { + "epoch": 0.01, + "learning_rate": 4.8097012309653734e-05, + "loss": 4.6101, + "step": 116224 + }, + { + "epoch": 0.01, + "learning_rate": 4.808864274094695e-05, + "loss": 4.6203, + "step": 116736 + }, + { + "epoch": 0.01, + "learning_rate": 4.808027317224016e-05, + "loss": 4.6318, + "step": 117248 + }, + { + "epoch": 0.01, + "learning_rate": 4.807188722472964e-05, + "loss": 4.6234, + "step": 117760 + }, + { + "epoch": 0.01, + "learning_rate": 4.806350127721912e-05, + "loss": 4.6095, + "step": 118272 + }, + { + "epoch": 0.01, + "learning_rate": 4.80551153297086e-05, + "loss": 4.5985, + "step": 118784 + }, + { + "epoch": 0.01, + "learning_rate": 4.804672938219807e-05, + "loss": 4.6168, + "step": 119296 + }, + { + "epoch": 0.01, + "learning_rate": 4.803834343468755e-05, + "loss": 4.6017, + "step": 119808 + }, + { + "epoch": 0.01, + "learning_rate": 4.802995748717703e-05, + "loss": 4.6049, + "step": 120320 + }, + { + "epoch": 0.01, + "learning_rate": 4.802157153966652e-05, + "loss": 4.6079, + "step": 120832 + }, + { + "epoch": 0.01, + "learning_rate": 4.801320197095973e-05, + "loss": 4.6147, + "step": 121344 + }, + { + "epoch": 0.01, + "learning_rate": 4.800481602344921e-05, + "loss": 4.6023, + "step": 121856 + }, + { + "epoch": 0.02, + "learning_rate": 4.799643007593869e-05, + "loss": 4.5988, + "step": 122368 + }, + { + "epoch": 0.02, + "learning_rate": 4.798804412842817e-05, + "loss": 4.5903, + "step": 122880 + }, + { + "epoch": 0.02, + "learning_rate": 4.797965818091765e-05, + "loss": 4.6031, + "step": 123392 + }, + { + "epoch": 0.02, + "learning_rate": 4.797128861221086e-05, + "loss": 4.601, + "step": 123904 + }, + { + "epoch": 0.02, + "learning_rate": 4.796290266470034e-05, + "loss": 4.5775, + "step": 124416 + }, + { + "epoch": 0.02, + "learning_rate": 4.795451671718982e-05, + "loss": 4.5858, + "step": 124928 + }, + { + "epoch": 0.02, + "learning_rate": 4.79461307696793e-05, + "loss": 4.6014, + "step": 125440 + }, + { + "epoch": 0.02, + "learning_rate": 4.793774482216878e-05, + "loss": 4.6017, + "step": 125952 + }, + { + "epoch": 0.02, + "learning_rate": 4.792935887465826e-05, + "loss": 4.588, + "step": 126464 + }, + { + "epoch": 0.02, + "learning_rate": 4.792098930595147e-05, + "loss": 4.5824, + "step": 126976 + }, + { + "epoch": 0.02, + "learning_rate": 4.791260335844095e-05, + "loss": 4.5923, + "step": 127488 + }, + { + "epoch": 0.02, + "learning_rate": 4.790421741093043e-05, + "loss": 4.5731, + "step": 128000 + }, + { + "epoch": 0.02, + "learning_rate": 4.789583146341991e-05, + "loss": 4.5881, + "step": 128512 + }, + { + "epoch": 0.02, + "learning_rate": 4.788744551590939e-05, + "loss": 4.5934, + "step": 129024 + }, + { + "epoch": 0.02, + "learning_rate": 4.78790759472026e-05, + "loss": 4.5784, + "step": 129536 + }, + { + "epoch": 0.02, + "learning_rate": 4.787068999969208e-05, + "loss": 4.5772, + "step": 130048 + }, + { + "epoch": 0.02, + "learning_rate": 4.786230405218156e-05, + "loss": 4.5558, + "step": 130560 + }, + { + "epoch": 0.02, + "learning_rate": 4.785393448347477e-05, + "loss": 4.5621, + "step": 131072 + }, + { + "epoch": 0.02, + "learning_rate": 4.784554853596425e-05, + "loss": 4.5681, + "step": 131584 + }, + { + "epoch": 0.02, + "learning_rate": 4.783716258845373e-05, + "loss": 4.5696, + "step": 132096 + }, + { + "epoch": 0.02, + "learning_rate": 4.782877664094321e-05, + "loss": 4.5729, + "step": 132608 + }, + { + "epoch": 0.02, + "learning_rate": 4.782039069343269e-05, + "loss": 4.5607, + "step": 133120 + }, + { + "epoch": 0.02, + "learning_rate": 4.781200474592217e-05, + "loss": 4.5587, + "step": 133632 + }, + { + "epoch": 0.02, + "learning_rate": 4.780361879841165e-05, + "loss": 4.5656, + "step": 134144 + }, + { + "epoch": 0.02, + "learning_rate": 4.779523285090114e-05, + "loss": 4.5725, + "step": 134656 + }, + { + "epoch": 0.02, + "learning_rate": 4.778684690339061e-05, + "loss": 4.5609, + "step": 135168 + }, + { + "epoch": 0.02, + "learning_rate": 4.7778477334683826e-05, + "loss": 4.5613, + "step": 135680 + }, + { + "epoch": 0.02, + "learning_rate": 4.7770091387173306e-05, + "loss": 4.5575, + "step": 136192 + }, + { + "epoch": 0.02, + "learning_rate": 4.7761705439662786e-05, + "loss": 4.561, + "step": 136704 + }, + { + "epoch": 0.02, + "learning_rate": 4.7753335870955995e-05, + "loss": 4.5606, + "step": 137216 + }, + { + "epoch": 0.02, + "learning_rate": 4.7744949923445475e-05, + "loss": 4.5546, + "step": 137728 + }, + { + "epoch": 0.02, + "learning_rate": 4.7736563975934955e-05, + "loss": 4.5515, + "step": 138240 + }, + { + "epoch": 0.02, + "learning_rate": 4.7728178028424435e-05, + "loss": 4.5472, + "step": 138752 + }, + { + "epoch": 0.02, + "learning_rate": 4.771979208091391e-05, + "loss": 4.5424, + "step": 139264 + }, + { + "epoch": 0.02, + "learning_rate": 4.771140613340339e-05, + "loss": 4.5481, + "step": 139776 + }, + { + "epoch": 0.02, + "learning_rate": 4.7703020185892875e-05, + "loss": 4.5508, + "step": 140288 + }, + { + "epoch": 0.02, + "learning_rate": 4.7694634238382355e-05, + "loss": 4.5538, + "step": 140800 + }, + { + "epoch": 0.02, + "learning_rate": 4.7686248290871835e-05, + "loss": 4.5356, + "step": 141312 + }, + { + "epoch": 0.02, + "learning_rate": 4.7677862343361315e-05, + "loss": 4.5436, + "step": 141824 + }, + { + "epoch": 0.02, + "learning_rate": 4.7669476395850795e-05, + "loss": 4.5556, + "step": 142336 + }, + { + "epoch": 0.02, + "learning_rate": 4.7661106827144004e-05, + "loss": 4.5395, + "step": 142848 + }, + { + "epoch": 0.02, + "learning_rate": 4.765273725843721e-05, + "loss": 4.5519, + "step": 143360 + }, + { + "epoch": 0.02, + "learning_rate": 4.764435131092669e-05, + "loss": 4.5363, + "step": 143872 + }, + { + "epoch": 0.02, + "learning_rate": 4.763596536341617e-05, + "loss": 4.5547, + "step": 144384 + }, + { + "epoch": 0.02, + "learning_rate": 4.762759579470938e-05, + "loss": 4.5418, + "step": 144896 + }, + { + "epoch": 0.02, + "learning_rate": 4.761920984719886e-05, + "loss": 4.5279, + "step": 145408 + }, + { + "epoch": 0.02, + "learning_rate": 4.761082389968834e-05, + "loss": 4.5299, + "step": 145920 + }, + { + "epoch": 0.02, + "learning_rate": 4.760243795217783e-05, + "loss": 4.525, + "step": 146432 + }, + { + "epoch": 0.02, + "learning_rate": 4.759405200466731e-05, + "loss": 4.5383, + "step": 146944 + }, + { + "epoch": 0.02, + "learning_rate": 4.758566605715679e-05, + "loss": 4.5384, + "step": 147456 + }, + { + "epoch": 0.02, + "learning_rate": 4.757728010964627e-05, + "loss": 4.5395, + "step": 147968 + }, + { + "epoch": 0.02, + "learning_rate": 4.756889416213575e-05, + "loss": 4.5332, + "step": 148480 + }, + { + "epoch": 0.02, + "learning_rate": 4.756050821462523e-05, + "loss": 4.5258, + "step": 148992 + }, + { + "epoch": 0.02, + "learning_rate": 4.755212226711471e-05, + "loss": 4.5207, + "step": 149504 + }, + { + "epoch": 0.02, + "learning_rate": 4.754373631960419e-05, + "loss": 4.5162, + "step": 150016 + }, + { + "epoch": 0.02, + "learning_rate": 4.75353667508974e-05, + "loss": 4.5269, + "step": 150528 + }, + { + "epoch": 0.02, + "learning_rate": 4.752698080338688e-05, + "loss": 4.5398, + "step": 151040 + }, + { + "epoch": 0.02, + "learning_rate": 4.751859485587636e-05, + "loss": 4.5253, + "step": 151552 + }, + { + "epoch": 0.02, + "learning_rate": 4.751020890836584e-05, + "loss": 4.516, + "step": 152064 + }, + { + "epoch": 0.02, + "learning_rate": 4.750182296085532e-05, + "loss": 4.5156, + "step": 152576 + }, + { + "epoch": 0.03, + "eval_loss": 4.485103130340576, + "eval_runtime": 527.7119, + "eval_samples_per_second": 723.105, + "eval_steps_per_second": 22.598, + "step": 152638 + }, + { + "epoch": 1.0, + "learning_rate": 4.74934370133448e-05, + "loss": 4.5263, + "step": 153088 + }, + { + "epoch": 1.0, + "learning_rate": 4.748505106583428e-05, + "loss": 4.5219, + "step": 153600 + }, + { + "epoch": 1.0, + "learning_rate": 4.747668149712749e-05, + "loss": 4.5095, + "step": 154112 + }, + { + "epoch": 1.0, + "learning_rate": 4.74683119284207e-05, + "loss": 4.5124, + "step": 154624 + }, + { + "epoch": 1.0, + "learning_rate": 4.745992598091018e-05, + "loss": 4.5079, + "step": 155136 + }, + { + "epoch": 1.0, + "learning_rate": 4.745154003339966e-05, + "loss": 4.4944, + "step": 155648 + }, + { + "epoch": 1.0, + "learning_rate": 4.744315408588914e-05, + "loss": 4.5033, + "step": 156160 + }, + { + "epoch": 1.0, + "learning_rate": 4.743478451718235e-05, + "loss": 4.5144, + "step": 156672 + }, + { + "epoch": 1.0, + "learning_rate": 4.742639856967183e-05, + "loss": 4.4941, + "step": 157184 + }, + { + "epoch": 1.0, + "learning_rate": 4.741802900096504e-05, + "loss": 4.5058, + "step": 157696 + }, + { + "epoch": 1.0, + "learning_rate": 4.740964305345452e-05, + "loss": 4.5157, + "step": 158208 + }, + { + "epoch": 1.0, + "learning_rate": 4.7401257105944e-05, + "loss": 4.5131, + "step": 158720 + }, + { + "epoch": 1.0, + "learning_rate": 4.739287115843348e-05, + "loss": 4.5003, + "step": 159232 + }, + { + "epoch": 1.0, + "learning_rate": 4.7384485210922966e-05, + "loss": 4.5014, + "step": 159744 + }, + { + "epoch": 1.0, + "learning_rate": 4.7376099263412446e-05, + "loss": 4.4991, + "step": 160256 + }, + { + "epoch": 1.0, + "learning_rate": 4.736771331590192e-05, + "loss": 4.4937, + "step": 160768 + }, + { + "epoch": 1.0, + "learning_rate": 4.73593273683914e-05, + "loss": 4.4923, + "step": 161280 + }, + { + "epoch": 1.0, + "learning_rate": 4.735094142088088e-05, + "loss": 4.4985, + "step": 161792 + }, + { + "epoch": 1.0, + "learning_rate": 4.734255547337036e-05, + "loss": 4.4993, + "step": 162304 + }, + { + "epoch": 1.0, + "learning_rate": 4.733416952585984e-05, + "loss": 4.4986, + "step": 162816 + }, + { + "epoch": 1.0, + "learning_rate": 4.732578357834932e-05, + "loss": 4.4894, + "step": 163328 + }, + { + "epoch": 1.0, + "learning_rate": 4.73173976308388e-05, + "loss": 4.5022, + "step": 163840 + }, + { + "epoch": 1.0, + "learning_rate": 4.730902806213201e-05, + "loss": 4.4888, + "step": 164352 + }, + { + "epoch": 1.0, + "learning_rate": 4.730064211462149e-05, + "loss": 4.4955, + "step": 164864 + }, + { + "epoch": 1.0, + "learning_rate": 4.729225616711097e-05, + "loss": 4.4897, + "step": 165376 + }, + { + "epoch": 1.0, + "learning_rate": 4.728387021960045e-05, + "loss": 4.4892, + "step": 165888 + }, + { + "epoch": 1.0, + "learning_rate": 4.727548427208993e-05, + "loss": 4.494, + "step": 166400 + }, + { + "epoch": 1.0, + "learning_rate": 4.7267098324579415e-05, + "loss": 4.4764, + "step": 166912 + }, + { + "epoch": 1.0, + "learning_rate": 4.7258728755872624e-05, + "loss": 4.4913, + "step": 167424 + }, + { + "epoch": 1.01, + "learning_rate": 4.7250342808362104e-05, + "loss": 4.4761, + "step": 167936 + }, + { + "epoch": 1.01, + "learning_rate": 4.7241956860851584e-05, + "loss": 4.4792, + "step": 168448 + }, + { + "epoch": 1.01, + "learning_rate": 4.7233570913341064e-05, + "loss": 4.4798, + "step": 168960 + }, + { + "epoch": 1.01, + "learning_rate": 4.7225184965830544e-05, + "loss": 4.4851, + "step": 169472 + }, + { + "epoch": 1.01, + "learning_rate": 4.721681539712375e-05, + "loss": 4.4783, + "step": 169984 + }, + { + "epoch": 1.01, + "learning_rate": 4.720842944961323e-05, + "loss": 4.4698, + "step": 170496 + }, + { + "epoch": 1.01, + "learning_rate": 4.720004350210271e-05, + "loss": 4.4887, + "step": 171008 + }, + { + "epoch": 1.01, + "learning_rate": 4.719165755459219e-05, + "loss": 4.4752, + "step": 171520 + }, + { + "epoch": 1.01, + "learning_rate": 4.718327160708167e-05, + "loss": 4.4876, + "step": 172032 + }, + { + "epoch": 1.01, + "learning_rate": 4.717488565957115e-05, + "loss": 4.4736, + "step": 172544 + }, + { + "epoch": 1.01, + "learning_rate": 4.716649971206063e-05, + "loss": 4.4606, + "step": 173056 + }, + { + "epoch": 1.01, + "learning_rate": 4.715811376455011e-05, + "loss": 4.4608, + "step": 173568 + }, + { + "epoch": 1.01, + "learning_rate": 4.714974419584333e-05, + "loss": 4.4621, + "step": 174080 + }, + { + "epoch": 1.01, + "learning_rate": 4.714137462713654e-05, + "loss": 4.4806, + "step": 174592 + }, + { + "epoch": 1.01, + "learning_rate": 4.713298867962602e-05, + "loss": 4.4587, + "step": 175104 + }, + { + "epoch": 1.01, + "learning_rate": 4.71246027321155e-05, + "loss": 4.4722, + "step": 175616 + }, + { + "epoch": 1.01, + "learning_rate": 4.711621678460498e-05, + "loss": 4.4669, + "step": 176128 + }, + { + "epoch": 1.01, + "learning_rate": 4.710783083709446e-05, + "loss": 4.4653, + "step": 176640 + }, + { + "epoch": 1.01, + "learning_rate": 4.709944488958393e-05, + "loss": 4.4728, + "step": 177152 + }, + { + "epoch": 1.01, + "learning_rate": 4.709105894207341e-05, + "loss": 4.4475, + "step": 177664 + }, + { + "epoch": 1.01, + "learning_rate": 4.708267299456289e-05, + "loss": 4.4513, + "step": 178176 + }, + { + "epoch": 1.01, + "learning_rate": 4.7074303425856106e-05, + "loss": 4.4476, + "step": 178688 + }, + { + "epoch": 1.01, + "learning_rate": 4.7065917478345586e-05, + "loss": 4.4672, + "step": 179200 + }, + { + "epoch": 1.01, + "learning_rate": 4.7057531530835066e-05, + "loss": 4.4459, + "step": 179712 + }, + { + "epoch": 1.01, + "learning_rate": 4.7049145583324546e-05, + "loss": 4.4699, + "step": 180224 + }, + { + "epoch": 1.01, + "learning_rate": 4.7040776014617755e-05, + "loss": 4.4456, + "step": 180736 + }, + { + "epoch": 1.01, + "learning_rate": 4.7032390067107235e-05, + "loss": 4.4458, + "step": 181248 + }, + { + "epoch": 1.01, + "learning_rate": 4.7024004119596715e-05, + "loss": 4.4455, + "step": 181760 + }, + { + "epoch": 1.01, + "learning_rate": 4.7015618172086195e-05, + "loss": 4.4435, + "step": 182272 + }, + { + "epoch": 1.01, + "learning_rate": 4.7007232224575675e-05, + "loss": 4.4497, + "step": 182784 + }, + { + "epoch": 1.01, + "learning_rate": 4.6998846277065155e-05, + "loss": 4.4447, + "step": 183296 + }, + { + "epoch": 1.01, + "learning_rate": 4.6990460329554635e-05, + "loss": 4.4335, + "step": 183808 + }, + { + "epoch": 1.01, + "learning_rate": 4.6982090760847844e-05, + "loss": 4.4508, + "step": 184320 + }, + { + "epoch": 1.01, + "learning_rate": 4.6973704813337324e-05, + "loss": 4.438, + "step": 184832 + }, + { + "epoch": 1.01, + "learning_rate": 4.696533524463054e-05, + "loss": 4.4411, + "step": 185344 + }, + { + "epoch": 1.01, + "learning_rate": 4.695694929712002e-05, + "loss": 4.438, + "step": 185856 + }, + { + "epoch": 1.01, + "learning_rate": 4.69485633496095e-05, + "loss": 4.4436, + "step": 186368 + }, + { + "epoch": 1.01, + "learning_rate": 4.694017740209898e-05, + "loss": 4.4244, + "step": 186880 + }, + { + "epoch": 1.01, + "learning_rate": 4.693179145458846e-05, + "loss": 4.4494, + "step": 187392 + }, + { + "epoch": 1.01, + "learning_rate": 4.692340550707794e-05, + "loss": 4.4339, + "step": 187904 + }, + { + "epoch": 1.01, + "learning_rate": 4.691501955956742e-05, + "loss": 4.4373, + "step": 188416 + }, + { + "epoch": 1.01, + "learning_rate": 4.69066336120569e-05, + "loss": 4.4395, + "step": 188928 + }, + { + "epoch": 1.01, + "learning_rate": 4.689826404335011e-05, + "loss": 4.4292, + "step": 189440 + }, + { + "epoch": 1.01, + "learning_rate": 4.688987809583959e-05, + "loss": 4.4479, + "step": 189952 + }, + { + "epoch": 1.01, + "learning_rate": 4.68815085271328e-05, + "loss": 4.4521, + "step": 190464 + }, + { + "epoch": 1.01, + "learning_rate": 4.687312257962228e-05, + "loss": 4.4497, + "step": 190976 + }, + { + "epoch": 1.01, + "learning_rate": 4.6864753010915494e-05, + "loss": 4.4338, + "step": 191488 + }, + { + "epoch": 1.01, + "learning_rate": 4.6856367063404974e-05, + "loss": 4.4249, + "step": 192000 + }, + { + "epoch": 1.01, + "learning_rate": 4.6847981115894454e-05, + "loss": 4.4181, + "step": 192512 + }, + { + "epoch": 1.01, + "learning_rate": 4.6839595168383934e-05, + "loss": 4.4363, + "step": 193024 + }, + { + "epoch": 1.01, + "learning_rate": 4.6831209220873414e-05, + "loss": 4.4439, + "step": 193536 + }, + { + "epoch": 1.01, + "learning_rate": 4.6822823273362894e-05, + "loss": 4.4378, + "step": 194048 + }, + { + "epoch": 1.01, + "learning_rate": 4.6814437325852373e-05, + "loss": 4.4247, + "step": 194560 + }, + { + "epoch": 1.01, + "learning_rate": 4.6806051378341853e-05, + "loss": 4.4157, + "step": 195072 + }, + { + "epoch": 1.01, + "learning_rate": 4.6797665430831333e-05, + "loss": 4.4293, + "step": 195584 + }, + { + "epoch": 1.01, + "learning_rate": 4.678927948332081e-05, + "loss": 4.4159, + "step": 196096 + }, + { + "epoch": 1.01, + "learning_rate": 4.678090991461402e-05, + "loss": 4.421, + "step": 196608 + }, + { + "epoch": 1.01, + "learning_rate": 4.67725239671035e-05, + "loss": 4.429, + "step": 197120 + }, + { + "epoch": 1.01, + "learning_rate": 4.676413801959298e-05, + "loss": 4.4286, + "step": 197632 + }, + { + "epoch": 1.01, + "learning_rate": 4.675575207208246e-05, + "loss": 4.4235, + "step": 198144 + }, + { + "epoch": 1.02, + "learning_rate": 4.674736612457194e-05, + "loss": 4.4243, + "step": 198656 + }, + { + "epoch": 1.02, + "learning_rate": 4.673899655586516e-05, + "loss": 4.4129, + "step": 199168 + }, + { + "epoch": 1.02, + "learning_rate": 4.673061060835464e-05, + "loss": 4.4243, + "step": 199680 + }, + { + "epoch": 1.02, + "learning_rate": 4.672222466084412e-05, + "loss": 4.4212, + "step": 200192 + }, + { + "epoch": 1.02, + "learning_rate": 4.671383871333359e-05, + "loss": 4.406, + "step": 200704 + }, + { + "epoch": 1.02, + "learning_rate": 4.670546914462681e-05, + "loss": 4.4093, + "step": 201216 + }, + { + "epoch": 1.02, + "learning_rate": 4.669708319711629e-05, + "loss": 4.4255, + "step": 201728 + }, + { + "epoch": 1.02, + "learning_rate": 4.668869724960576e-05, + "loss": 4.4273, + "step": 202240 + }, + { + "epoch": 1.02, + "learning_rate": 4.668031130209524e-05, + "loss": 4.4122, + "step": 202752 + }, + { + "epoch": 1.02, + "learning_rate": 4.6671941733388456e-05, + "loss": 4.4134, + "step": 203264 + }, + { + "epoch": 1.02, + "learning_rate": 4.6663555785877936e-05, + "loss": 4.4193, + "step": 203776 + }, + { + "epoch": 1.02, + "learning_rate": 4.6655169838367416e-05, + "loss": 4.4022, + "step": 204288 + }, + { + "epoch": 1.02, + "learning_rate": 4.6646783890856896e-05, + "loss": 4.4186, + "step": 204800 + }, + { + "epoch": 1.02, + "learning_rate": 4.6638397943346376e-05, + "loss": 4.4239, + "step": 205312 + }, + { + "epoch": 1.02, + "learning_rate": 4.663002837463959e-05, + "loss": 4.4078, + "step": 205824 + }, + { + "epoch": 1.02, + "learning_rate": 4.6621642427129065e-05, + "loss": 4.4144, + "step": 206336 + }, + { + "epoch": 1.02, + "learning_rate": 4.6613256479618545e-05, + "loss": 4.3884, + "step": 206848 + }, + { + "epoch": 1.02, + "learning_rate": 4.6604870532108025e-05, + "loss": 4.3918, + "step": 207360 + }, + { + "epoch": 1.02, + "learning_rate": 4.6596484584597505e-05, + "loss": 4.4015, + "step": 207872 + }, + { + "epoch": 1.02, + "learning_rate": 4.6588098637086985e-05, + "loss": 4.4042, + "step": 208384 + }, + { + "epoch": 1.02, + "learning_rate": 4.6579712689576465e-05, + "loss": 4.4107, + "step": 208896 + }, + { + "epoch": 1.02, + "learning_rate": 4.6571326742065945e-05, + "loss": 4.3957, + "step": 209408 + }, + { + "epoch": 1.02, + "learning_rate": 4.6562957173359154e-05, + "loss": 4.3936, + "step": 209920 + }, + { + "epoch": 1.02, + "learning_rate": 4.655458760465237e-05, + "loss": 4.3993, + "step": 210432 + }, + { + "epoch": 1.02, + "learning_rate": 4.654620165714185e-05, + "loss": 4.4114, + "step": 210944 + }, + { + "epoch": 1.02, + "learning_rate": 4.653781570963133e-05, + "loss": 4.4021, + "step": 211456 + }, + { + "epoch": 1.02, + "learning_rate": 4.652942976212081e-05, + "loss": 4.4048, + "step": 211968 + }, + { + "epoch": 1.02, + "learning_rate": 4.652104381461029e-05, + "loss": 4.3946, + "step": 212480 + }, + { + "epoch": 1.02, + "learning_rate": 4.651265786709977e-05, + "loss": 4.3957, + "step": 212992 + }, + { + "epoch": 1.02, + "learning_rate": 4.650428829839298e-05, + "loss": 4.4068, + "step": 213504 + }, + { + "epoch": 1.02, + "learning_rate": 4.649590235088246e-05, + "loss": 4.3947, + "step": 214016 + }, + { + "epoch": 1.02, + "learning_rate": 4.648751640337194e-05, + "loss": 4.3941, + "step": 214528 + }, + { + "epoch": 1.02, + "learning_rate": 4.647913045586142e-05, + "loss": 4.3924, + "step": 215040 + }, + { + "epoch": 1.02, + "learning_rate": 4.64707445083509e-05, + "loss": 4.3842, + "step": 215552 + }, + { + "epoch": 1.02, + "learning_rate": 4.646235856084038e-05, + "loss": 4.3928, + "step": 216064 + }, + { + "epoch": 1.02, + "learning_rate": 4.645397261332986e-05, + "loss": 4.3928, + "step": 216576 + }, + { + "epoch": 1.02, + "learning_rate": 4.644558666581934e-05, + "loss": 4.4017, + "step": 217088 + }, + { + "epoch": 1.02, + "learning_rate": 4.6437217097112554e-05, + "loss": 4.3809, + "step": 217600 + }, + { + "epoch": 1.02, + "learning_rate": 4.6428831149602034e-05, + "loss": 4.3875, + "step": 218112 + }, + { + "epoch": 1.02, + "learning_rate": 4.642046158089524e-05, + "loss": 4.4029, + "step": 218624 + }, + { + "epoch": 1.02, + "learning_rate": 4.641207563338472e-05, + "loss": 4.385, + "step": 219136 + }, + { + "epoch": 1.02, + "learning_rate": 4.64036896858742e-05, + "loss": 4.4004, + "step": 219648 + }, + { + "epoch": 1.02, + "learning_rate": 4.639530373836368e-05, + "loss": 4.3869, + "step": 220160 + }, + { + "epoch": 1.02, + "learning_rate": 4.638691779085316e-05, + "loss": 4.4033, + "step": 220672 + }, + { + "epoch": 1.02, + "learning_rate": 4.637853184334264e-05, + "loss": 4.3887, + "step": 221184 + }, + { + "epoch": 1.02, + "learning_rate": 4.637014589583212e-05, + "loss": 4.3809, + "step": 221696 + }, + { + "epoch": 1.02, + "learning_rate": 4.636179270592906e-05, + "loss": 4.3798, + "step": 222208 + }, + { + "epoch": 1.02, + "learning_rate": 4.635340675841854e-05, + "loss": 4.3751, + "step": 222720 + }, + { + "epoch": 1.02, + "learning_rate": 4.634502081090802e-05, + "loss": 4.3877, + "step": 223232 + }, + { + "epoch": 1.02, + "learning_rate": 4.633663486339751e-05, + "loss": 4.3948, + "step": 223744 + }, + { + "epoch": 1.02, + "learning_rate": 4.632824891588699e-05, + "loss": 4.3892, + "step": 224256 + }, + { + "epoch": 1.02, + "learning_rate": 4.631986296837647e-05, + "loss": 4.3858, + "step": 224768 + }, + { + "epoch": 1.02, + "learning_rate": 4.631147702086595e-05, + "loss": 4.3795, + "step": 225280 + }, + { + "epoch": 1.02, + "learning_rate": 4.630309107335542e-05, + "loss": 4.3773, + "step": 225792 + }, + { + "epoch": 1.02, + "learning_rate": 4.62947051258449e-05, + "loss": 4.3714, + "step": 226304 + }, + { + "epoch": 1.02, + "learning_rate": 4.628631917833438e-05, + "loss": 4.384, + "step": 226816 + }, + { + "epoch": 1.02, + "learning_rate": 4.627793323082386e-05, + "loss": 4.3931, + "step": 227328 + }, + { + "epoch": 1.02, + "learning_rate": 4.626956366211707e-05, + "loss": 4.3819, + "step": 227840 + }, + { + "epoch": 1.02, + "learning_rate": 4.626117771460655e-05, + "loss": 4.3746, + "step": 228352 + }, + { + "epoch": 1.02, + "learning_rate": 4.625279176709603e-05, + "loss": 4.3728, + "step": 228864 + }, + { + "epoch": 1.03, + "eval_loss": 4.3495965003967285, + "eval_runtime": 528.0293, + "eval_samples_per_second": 722.67, + "eval_steps_per_second": 22.584, + "step": 228957 + }, + { + "epoch": 0.0, + "learning_rate": 4.624440581958551e-05, + "loss": 4.3835, + "step": 229376 + }, + { + "epoch": 0.0, + "learning_rate": 4.623601987207499e-05, + "loss": 4.3841, + "step": 229888 + }, + { + "epoch": 0.0, + "learning_rate": 4.6227633924564476e-05, + "loss": 4.3702, + "step": 230400 + }, + { + "epoch": 0.0, + "learning_rate": 4.6219247977053956e-05, + "loss": 4.3685, + "step": 230912 + }, + { + "epoch": 0.0, + "learning_rate": 4.6210862029543436e-05, + "loss": 4.3712, + "step": 231424 + }, + { + "epoch": 0.0, + "learning_rate": 4.6202476082032916e-05, + "loss": 4.3529, + "step": 231936 + }, + { + "epoch": 0.0, + "learning_rate": 4.6194090134522396e-05, + "loss": 4.3629, + "step": 232448 + }, + { + "epoch": 0.0, + "learning_rate": 4.6185704187011876e-05, + "loss": 4.3723, + "step": 232960 + }, + { + "epoch": 0.0, + "learning_rate": 4.6177318239501356e-05, + "loss": 4.3615, + "step": 233472 + }, + { + "epoch": 0.0, + "learning_rate": 4.6168932291990836e-05, + "loss": 4.3695, + "step": 233984 + }, + { + "epoch": 0.0, + "learning_rate": 4.616054634448031e-05, + "loss": 4.3765, + "step": 234496 + }, + { + "epoch": 0.0, + "learning_rate": 4.615216039696979e-05, + "loss": 4.373, + "step": 235008 + }, + { + "epoch": 0.0, + "learning_rate": 4.614377444945927e-05, + "loss": 4.3642, + "step": 235520 + }, + { + "epoch": 0.0, + "learning_rate": 4.613538850194875e-05, + "loss": 4.3695, + "step": 236032 + }, + { + "epoch": 0.0, + "learning_rate": 4.612700255443823e-05, + "loss": 4.3618, + "step": 236544 + }, + { + "epoch": 0.0, + "learning_rate": 4.611861660692771e-05, + "loss": 4.3621, + "step": 237056 + }, + { + "epoch": 0.0, + "learning_rate": 4.611023065941719e-05, + "loss": 4.3548, + "step": 237568 + }, + { + "epoch": 0.0, + "learning_rate": 4.6101861090710405e-05, + "loss": 4.3633, + "step": 238080 + }, + { + "epoch": 0.0, + "learning_rate": 4.6093475143199885e-05, + "loss": 4.3644, + "step": 238592 + }, + { + "epoch": 0.0, + "learning_rate": 4.6085089195689365e-05, + "loss": 4.3678, + "step": 239104 + }, + { + "epoch": 0.0, + "learning_rate": 4.6076703248178845e-05, + "loss": 4.3579, + "step": 239616 + }, + { + "epoch": 0.0, + "learning_rate": 4.6068317300668325e-05, + "loss": 4.3697, + "step": 240128 + }, + { + "epoch": 0.0, + "learning_rate": 4.6059931353157805e-05, + "loss": 4.3595, + "step": 240640 + }, + { + "epoch": 0.0, + "learning_rate": 4.6051545405647285e-05, + "loss": 4.3603, + "step": 241152 + }, + { + "epoch": 0.0, + "learning_rate": 4.6043159458136764e-05, + "loss": 4.36, + "step": 241664 + }, + { + "epoch": 0.0, + "learning_rate": 4.6034789889429974e-05, + "loss": 4.3574, + "step": 242176 + }, + { + "epoch": 0.0, + "learning_rate": 4.6026403941919454e-05, + "loss": 4.3632, + "step": 242688 + }, + { + "epoch": 0.0, + "learning_rate": 4.601803437321266e-05, + "loss": 4.3485, + "step": 243200 + }, + { + "epoch": 0.0, + "learning_rate": 4.600964842570214e-05, + "loss": 4.3636, + "step": 243712 + }, + { + "epoch": 0.01, + "learning_rate": 4.600126247819162e-05, + "loss": 4.3482, + "step": 244224 + }, + { + "epoch": 0.01, + "learning_rate": 4.599287653068111e-05, + "loss": 4.3511, + "step": 244736 + }, + { + "epoch": 0.01, + "learning_rate": 4.598449058317059e-05, + "loss": 4.3541, + "step": 245248 + }, + { + "epoch": 0.01, + "learning_rate": 4.59761210144638e-05, + "loss": 4.3607, + "step": 245760 + }, + { + "epoch": 0.01, + "learning_rate": 4.596773506695328e-05, + "loss": 4.3465, + "step": 246272 + }, + { + "epoch": 0.01, + "learning_rate": 4.595934911944276e-05, + "loss": 4.3492, + "step": 246784 + }, + { + "epoch": 0.01, + "learning_rate": 4.595097955073597e-05, + "loss": 4.3564, + "step": 247296 + }, + { + "epoch": 0.01, + "learning_rate": 4.594259360322545e-05, + "loss": 4.351, + "step": 247808 + }, + { + "epoch": 0.01, + "learning_rate": 4.593420765571493e-05, + "loss": 4.3661, + "step": 248320 + }, + { + "epoch": 0.01, + "learning_rate": 4.592582170820441e-05, + "loss": 4.3496, + "step": 248832 + }, + { + "epoch": 0.01, + "learning_rate": 4.591743576069389e-05, + "loss": 4.3374, + "step": 249344 + }, + { + "epoch": 0.01, + "learning_rate": 4.590904981318337e-05, + "loss": 4.3399, + "step": 249856 + }, + { + "epoch": 0.01, + "learning_rate": 4.590066386567285e-05, + "loss": 4.3353, + "step": 250368 + }, + { + "epoch": 0.01, + "learning_rate": 4.589227791816233e-05, + "loss": 4.3579, + "step": 250880 + }, + { + "epoch": 0.01, + "learning_rate": 4.588389197065181e-05, + "loss": 4.3389, + "step": 251392 + }, + { + "epoch": 0.01, + "learning_rate": 4.587550602314129e-05, + "loss": 4.3493, + "step": 251904 + }, + { + "epoch": 0.01, + "learning_rate": 4.586712007563077e-05, + "loss": 4.3448, + "step": 252416 + }, + { + "epoch": 0.01, + "learning_rate": 4.585873412812025e-05, + "loss": 4.3442, + "step": 252928 + }, + { + "epoch": 0.01, + "learning_rate": 4.585038093821719e-05, + "loss": 4.3525, + "step": 253440 + }, + { + "epoch": 0.01, + "learning_rate": 4.584199499070667e-05, + "loss": 4.3274, + "step": 253952 + }, + { + "epoch": 0.01, + "learning_rate": 4.5833609043196145e-05, + "loss": 4.3281, + "step": 254464 + }, + { + "epoch": 0.01, + "learning_rate": 4.5825223095685625e-05, + "loss": 4.3346, + "step": 254976 + }, + { + "epoch": 0.01, + "learning_rate": 4.5816837148175105e-05, + "loss": 4.3477, + "step": 255488 + }, + { + "epoch": 0.01, + "learning_rate": 4.580846757946832e-05, + "loss": 4.3264, + "step": 256000 + }, + { + "epoch": 0.01, + "learning_rate": 4.58000816319578e-05, + "loss": 4.3472, + "step": 256512 + }, + { + "epoch": 0.01, + "learning_rate": 4.5791712063251017e-05, + "loss": 4.3282, + "step": 257024 + }, + { + "epoch": 0.01, + "learning_rate": 4.5783326115740497e-05, + "loss": 4.3255, + "step": 257536 + }, + { + "epoch": 0.01, + "learning_rate": 4.577494016822997e-05, + "loss": 4.3309, + "step": 258048 + }, + { + "epoch": 0.01, + "learning_rate": 4.576655422071945e-05, + "loss": 4.3202, + "step": 258560 + }, + { + "epoch": 0.01, + "learning_rate": 4.575816827320893e-05, + "loss": 4.3388, + "step": 259072 + }, + { + "epoch": 0.01, + "learning_rate": 4.5749798704502146e-05, + "loss": 4.3295, + "step": 259584 + }, + { + "epoch": 0.01, + "learning_rate": 4.574141275699162e-05, + "loss": 4.3151, + "step": 260096 + }, + { + "epoch": 0.01, + "learning_rate": 4.57330268094811e-05, + "loss": 4.3348, + "step": 260608 + }, + { + "epoch": 0.01, + "learning_rate": 4.572464086197058e-05, + "loss": 4.3234, + "step": 261120 + }, + { + "epoch": 0.01, + "learning_rate": 4.571625491446006e-05, + "loss": 4.3292, + "step": 261632 + }, + { + "epoch": 0.01, + "learning_rate": 4.570786896694954e-05, + "loss": 4.3206, + "step": 262144 + }, + { + "epoch": 0.01, + "learning_rate": 4.569948301943902e-05, + "loss": 4.3318, + "step": 262656 + }, + { + "epoch": 0.01, + "learning_rate": 4.56910970719285e-05, + "loss": 4.3128, + "step": 263168 + }, + { + "epoch": 0.01, + "learning_rate": 4.568271112441798e-05, + "loss": 4.3357, + "step": 263680 + }, + { + "epoch": 0.01, + "learning_rate": 4.5674325176907465e-05, + "loss": 4.3195, + "step": 264192 + }, + { + "epoch": 0.01, + "learning_rate": 4.5665939229396945e-05, + "loss": 4.3199, + "step": 264704 + }, + { + "epoch": 0.01, + "learning_rate": 4.5657553281886425e-05, + "loss": 4.3279, + "step": 265216 + }, + { + "epoch": 0.01, + "learning_rate": 4.5649183713179634e-05, + "loss": 4.3235, + "step": 265728 + }, + { + "epoch": 0.01, + "learning_rate": 4.5640797765669114e-05, + "loss": 4.331, + "step": 266240 + }, + { + "epoch": 0.01, + "learning_rate": 4.5632411818158594e-05, + "loss": 4.342, + "step": 266752 + }, + { + "epoch": 0.01, + "learning_rate": 4.5624025870648074e-05, + "loss": 4.3382, + "step": 267264 + }, + { + "epoch": 0.01, + "learning_rate": 4.561565630194128e-05, + "loss": 4.3233, + "step": 267776 + }, + { + "epoch": 0.01, + "learning_rate": 4.560727035443076e-05, + "loss": 4.317, + "step": 268288 + }, + { + "epoch": 0.01, + "learning_rate": 4.559888440692024e-05, + "loss": 4.3097, + "step": 268800 + }, + { + "epoch": 0.01, + "learning_rate": 4.559049845940972e-05, + "loss": 4.327, + "step": 269312 + }, + { + "epoch": 0.01, + "learning_rate": 4.558212889070293e-05, + "loss": 4.3345, + "step": 269824 + }, + { + "epoch": 0.01, + "learning_rate": 4.557374294319242e-05, + "loss": 4.3293, + "step": 270336 + }, + { + "epoch": 0.01, + "learning_rate": 4.55653569956819e-05, + "loss": 4.3153, + "step": 270848 + }, + { + "epoch": 0.01, + "learning_rate": 4.555697104817138e-05, + "loss": 4.3061, + "step": 271360 + }, + { + "epoch": 0.01, + "learning_rate": 4.554860147946459e-05, + "loss": 4.3241, + "step": 271872 + }, + { + "epoch": 0.01, + "learning_rate": 4.554021553195407e-05, + "loss": 4.3027, + "step": 272384 + }, + { + "epoch": 0.01, + "learning_rate": 4.553182958444355e-05, + "loss": 4.3173, + "step": 272896 + }, + { + "epoch": 0.01, + "learning_rate": 4.552344363693303e-05, + "loss": 4.3184, + "step": 273408 + }, + { + "epoch": 0.01, + "learning_rate": 4.551505768942251e-05, + "loss": 4.3222, + "step": 273920 + }, + { + "epoch": 0.01, + "learning_rate": 4.550667174191198e-05, + "loss": 4.3176, + "step": 274432 + }, + { + "epoch": 0.02, + "learning_rate": 4.549828579440146e-05, + "loss": 4.3239, + "step": 274944 + }, + { + "epoch": 0.02, + "learning_rate": 4.548989984689094e-05, + "loss": 4.3044, + "step": 275456 + }, + { + "epoch": 0.02, + "learning_rate": 4.548151389938042e-05, + "loss": 4.3166, + "step": 275968 + }, + { + "epoch": 0.02, + "learning_rate": 4.54731279518699e-05, + "loss": 4.3141, + "step": 276480 + }, + { + "epoch": 0.02, + "learning_rate": 4.5464758383163116e-05, + "loss": 4.3054, + "step": 276992 + }, + { + "epoch": 0.02, + "learning_rate": 4.5456372435652596e-05, + "loss": 4.3035, + "step": 277504 + }, + { + "epoch": 0.02, + "learning_rate": 4.5447986488142076e-05, + "loss": 4.3211, + "step": 278016 + }, + { + "epoch": 0.02, + "learning_rate": 4.5439600540631556e-05, + "loss": 4.319, + "step": 278528 + }, + { + "epoch": 0.02, + "learning_rate": 4.5431214593121036e-05, + "loss": 4.3152, + "step": 279040 + }, + { + "epoch": 0.02, + "learning_rate": 4.5422828645610516e-05, + "loss": 4.3086, + "step": 279552 + }, + { + "epoch": 0.02, + "learning_rate": 4.5414459076903725e-05, + "loss": 4.319, + "step": 280064 + }, + { + "epoch": 0.02, + "learning_rate": 4.5406073129393205e-05, + "loss": 4.3022, + "step": 280576 + }, + { + "epoch": 0.02, + "learning_rate": 4.5397703560686414e-05, + "loss": 4.3152, + "step": 281088 + }, + { + "epoch": 0.02, + "learning_rate": 4.5389317613175894e-05, + "loss": 4.3196, + "step": 281600 + }, + { + "epoch": 0.02, + "learning_rate": 4.5380931665665374e-05, + "loss": 4.3021, + "step": 282112 + }, + { + "epoch": 0.02, + "learning_rate": 4.5372545718154854e-05, + "loss": 4.3186, + "step": 282624 + }, + { + "epoch": 0.02, + "learning_rate": 4.536415977064434e-05, + "loss": 4.2845, + "step": 283136 + }, + { + "epoch": 0.02, + "learning_rate": 4.535577382313382e-05, + "loss": 4.292, + "step": 283648 + }, + { + "epoch": 0.02, + "learning_rate": 4.53473878756233e-05, + "loss": 4.3014, + "step": 284160 + }, + { + "epoch": 0.02, + "learning_rate": 4.533900192811278e-05, + "loss": 4.3046, + "step": 284672 + }, + { + "epoch": 0.02, + "learning_rate": 4.533061598060226e-05, + "loss": 4.3121, + "step": 285184 + }, + { + "epoch": 0.02, + "learning_rate": 4.532224641189547e-05, + "loss": 4.2942, + "step": 285696 + }, + { + "epoch": 0.02, + "learning_rate": 4.531386046438495e-05, + "loss": 4.2948, + "step": 286208 + }, + { + "epoch": 0.02, + "learning_rate": 4.530547451687443e-05, + "loss": 4.3008, + "step": 286720 + }, + { + "epoch": 0.02, + "learning_rate": 4.529708856936391e-05, + "loss": 4.3112, + "step": 287232 + }, + { + "epoch": 0.02, + "learning_rate": 4.528870262185339e-05, + "loss": 4.3074, + "step": 287744 + }, + { + "epoch": 0.02, + "learning_rate": 4.528031667434287e-05, + "loss": 4.3069, + "step": 288256 + }, + { + "epoch": 0.02, + "learning_rate": 4.527193072683234e-05, + "loss": 4.2959, + "step": 288768 + }, + { + "epoch": 0.02, + "learning_rate": 4.526354477932182e-05, + "loss": 4.2976, + "step": 289280 + }, + { + "epoch": 0.02, + "learning_rate": 4.525517521061504e-05, + "loss": 4.3112, + "step": 289792 + }, + { + "epoch": 0.02, + "learning_rate": 4.5246805641908255e-05, + "loss": 4.2964, + "step": 290304 + }, + { + "epoch": 0.02, + "learning_rate": 4.5238419694397735e-05, + "loss": 4.2952, + "step": 290816 + }, + { + "epoch": 0.02, + "learning_rate": 4.5230033746887215e-05, + "loss": 4.2996, + "step": 291328 + }, + { + "epoch": 0.02, + "learning_rate": 4.5221647799376694e-05, + "loss": 4.2857, + "step": 291840 + }, + { + "epoch": 0.02, + "learning_rate": 4.521326185186617e-05, + "loss": 4.2995, + "step": 292352 + }, + { + "epoch": 0.02, + "learning_rate": 4.5204892283159384e-05, + "loss": 4.2975, + "step": 292864 + }, + { + "epoch": 0.02, + "learning_rate": 4.5196506335648863e-05, + "loss": 4.308, + "step": 293376 + }, + { + "epoch": 0.02, + "learning_rate": 4.5188120388138343e-05, + "loss": 4.2858, + "step": 293888 + }, + { + "epoch": 0.02, + "learning_rate": 4.5179734440627817e-05, + "loss": 4.2902, + "step": 294400 + }, + { + "epoch": 0.02, + "learning_rate": 4.5171348493117297e-05, + "loss": 4.3105, + "step": 294912 + }, + { + "epoch": 0.02, + "learning_rate": 4.516297892441051e-05, + "loss": 4.2899, + "step": 295424 + }, + { + "epoch": 0.02, + "learning_rate": 4.515459297689999e-05, + "loss": 4.301, + "step": 295936 + }, + { + "epoch": 0.02, + "learning_rate": 4.514620702938947e-05, + "loss": 4.2964, + "step": 296448 + }, + { + "epoch": 0.02, + "learning_rate": 4.513782108187895e-05, + "loss": 4.3076, + "step": 296960 + }, + { + "epoch": 0.02, + "learning_rate": 4.512943513436843e-05, + "loss": 4.2978, + "step": 297472 + }, + { + "epoch": 0.02, + "learning_rate": 4.512106556566164e-05, + "loss": 4.2899, + "step": 297984 + }, + { + "epoch": 0.02, + "learning_rate": 4.511267961815112e-05, + "loss": 4.2849, + "step": 298496 + }, + { + "epoch": 0.02, + "learning_rate": 4.51042936706406e-05, + "loss": 4.2817, + "step": 299008 + }, + { + "epoch": 0.02, + "learning_rate": 4.509590772313008e-05, + "loss": 4.2937, + "step": 299520 + }, + { + "epoch": 0.02, + "learning_rate": 4.508752177561956e-05, + "loss": 4.3045, + "step": 300032 + }, + { + "epoch": 0.02, + "learning_rate": 4.507915220691277e-05, + "loss": 4.2951, + "step": 300544 + }, + { + "epoch": 0.02, + "learning_rate": 4.507076625940225e-05, + "loss": 4.2965, + "step": 301056 + }, + { + "epoch": 0.02, + "learning_rate": 4.506238031189173e-05, + "loss": 4.2861, + "step": 301568 + }, + { + "epoch": 0.02, + "learning_rate": 4.505399436438121e-05, + "loss": 4.2868, + "step": 302080 + }, + { + "epoch": 0.02, + "learning_rate": 4.50456084168707e-05, + "loss": 4.2778, + "step": 302592 + }, + { + "epoch": 0.02, + "learning_rate": 4.503722246936018e-05, + "loss": 4.2948, + "step": 303104 + }, + { + "epoch": 0.02, + "learning_rate": 4.5028852900653386e-05, + "loss": 4.2961, + "step": 303616 + }, + { + "epoch": 0.02, + "learning_rate": 4.5020466953142866e-05, + "loss": 4.2997, + "step": 304128 + }, + { + "epoch": 0.02, + "learning_rate": 4.5012081005632346e-05, + "loss": 4.2811, + "step": 304640 + }, + { + "epoch": 0.02, + "learning_rate": 4.5003695058121826e-05, + "loss": 4.2801, + "step": 305152 + }, + { + "epoch": 0.03, + "eval_loss": 4.2668843269348145, + "eval_runtime": 552.3769, + "eval_samples_per_second": 690.816, + "eval_steps_per_second": 21.589, + "step": 305276 + }, + { + "epoch": 1.0, + "learning_rate": 4.4995309110611306e-05, + "loss": 4.2939, + "step": 305664 + }, + { + "epoch": 1.0, + "learning_rate": 4.4986939541904515e-05, + "loss": 4.2912, + "step": 306176 + }, + { + "epoch": 1.0, + "learning_rate": 4.4978553594393995e-05, + "loss": 4.2805, + "step": 306688 + }, + { + "epoch": 1.0, + "learning_rate": 4.4970167646883475e-05, + "loss": 4.2807, + "step": 307200 + }, + { + "epoch": 1.0, + "learning_rate": 4.4961781699372955e-05, + "loss": 4.2817, + "step": 307712 + }, + { + "epoch": 1.0, + "learning_rate": 4.4953395751862435e-05, + "loss": 4.2675, + "step": 308224 + }, + { + "epoch": 1.0, + "learning_rate": 4.4945009804351915e-05, + "loss": 4.2752, + "step": 308736 + }, + { + "epoch": 1.0, + "learning_rate": 4.4936623856841395e-05, + "loss": 4.2789, + "step": 309248 + }, + { + "epoch": 1.0, + "learning_rate": 4.492823790933088e-05, + "loss": 4.2784, + "step": 309760 + }, + { + "epoch": 1.0, + "learning_rate": 4.491988471942782e-05, + "loss": 4.2846, + "step": 310272 + }, + { + "epoch": 1.0, + "learning_rate": 4.49114987719173e-05, + "loss": 4.2869, + "step": 310784 + }, + { + "epoch": 1.0, + "learning_rate": 4.490311282440678e-05, + "loss": 4.2808, + "step": 311296 + }, + { + "epoch": 1.0, + "learning_rate": 4.489472687689626e-05, + "loss": 4.2796, + "step": 311808 + }, + { + "epoch": 1.0, + "learning_rate": 4.488635730818947e-05, + "loss": 4.2831, + "step": 312320 + }, + { + "epoch": 1.0, + "learning_rate": 4.487797136067895e-05, + "loss": 4.2765, + "step": 312832 + }, + { + "epoch": 1.0, + "learning_rate": 4.486958541316843e-05, + "loss": 4.2713, + "step": 313344 + }, + { + "epoch": 1.0, + "learning_rate": 4.486119946565791e-05, + "loss": 4.2683, + "step": 313856 + }, + { + "epoch": 1.0, + "learning_rate": 4.485281351814739e-05, + "loss": 4.2802, + "step": 314368 + }, + { + "epoch": 1.0, + "learning_rate": 4.484442757063687e-05, + "loss": 4.2767, + "step": 314880 + }, + { + "epoch": 1.0, + "learning_rate": 4.483604162312635e-05, + "loss": 4.287, + "step": 315392 + }, + { + "epoch": 1.0, + "learning_rate": 4.482765567561583e-05, + "loss": 4.2717, + "step": 315904 + }, + { + "epoch": 1.0, + "learning_rate": 4.481926972810531e-05, + "loss": 4.2833, + "step": 316416 + }, + { + "epoch": 1.0, + "learning_rate": 4.4810900159398524e-05, + "loss": 4.2768, + "step": 316928 + }, + { + "epoch": 1.0, + "learning_rate": 4.4802514211888004e-05, + "loss": 4.2754, + "step": 317440 + }, + { + "epoch": 1.0, + "learning_rate": 4.479412826437748e-05, + "loss": 4.2737, + "step": 317952 + }, + { + "epoch": 1.0, + "learning_rate": 4.478574231686696e-05, + "loss": 4.2717, + "step": 318464 + }, + { + "epoch": 1.0, + "learning_rate": 4.477735636935644e-05, + "loss": 4.2797, + "step": 318976 + }, + { + "epoch": 1.0, + "learning_rate": 4.476897042184592e-05, + "loss": 4.2626, + "step": 319488 + }, + { + "epoch": 1.0, + "learning_rate": 4.47605844743354e-05, + "loss": 4.2796, + "step": 320000 + }, + { + "epoch": 1.0, + "learning_rate": 4.475219852682488e-05, + "loss": 4.266, + "step": 320512 + }, + { + "epoch": 1.01, + "learning_rate": 4.4743828958118086e-05, + "loss": 4.2644, + "step": 321024 + }, + { + "epoch": 1.01, + "learning_rate": 4.473544301060757e-05, + "loss": 4.2728, + "step": 321536 + }, + { + "epoch": 1.01, + "learning_rate": 4.472705706309705e-05, + "loss": 4.2765, + "step": 322048 + }, + { + "epoch": 1.01, + "learning_rate": 4.471867111558653e-05, + "loss": 4.2683, + "step": 322560 + }, + { + "epoch": 1.01, + "learning_rate": 4.471030154687974e-05, + "loss": 4.2648, + "step": 323072 + }, + { + "epoch": 1.01, + "learning_rate": 4.470193197817295e-05, + "loss": 4.2694, + "step": 323584 + }, + { + "epoch": 1.01, + "learning_rate": 4.469354603066243e-05, + "loss": 4.2718, + "step": 324096 + }, + { + "epoch": 1.01, + "learning_rate": 4.468516008315191e-05, + "loss": 4.2832, + "step": 324608 + }, + { + "epoch": 1.01, + "learning_rate": 4.467677413564139e-05, + "loss": 4.267, + "step": 325120 + }, + { + "epoch": 1.01, + "learning_rate": 4.466838818813087e-05, + "loss": 4.2587, + "step": 325632 + }, + { + "epoch": 1.01, + "learning_rate": 4.466000224062035e-05, + "loss": 4.2575, + "step": 326144 + }, + { + "epoch": 1.01, + "learning_rate": 4.465161629310983e-05, + "loss": 4.2557, + "step": 326656 + }, + { + "epoch": 1.01, + "learning_rate": 4.464323034559931e-05, + "loss": 4.2711, + "step": 327168 + }, + { + "epoch": 1.01, + "learning_rate": 4.4634860776892526e-05, + "loss": 4.2594, + "step": 327680 + }, + { + "epoch": 1.01, + "learning_rate": 4.4626474829382006e-05, + "loss": 4.2705, + "step": 328192 + }, + { + "epoch": 1.01, + "learning_rate": 4.4618088881871486e-05, + "loss": 4.2665, + "step": 328704 + }, + { + "epoch": 1.01, + "learning_rate": 4.4609702934360966e-05, + "loss": 4.2618, + "step": 329216 + }, + { + "epoch": 1.01, + "learning_rate": 4.4601316986850446e-05, + "loss": 4.2723, + "step": 329728 + }, + { + "epoch": 1.01, + "learning_rate": 4.4592947418143655e-05, + "loss": 4.2515, + "step": 330240 + }, + { + "epoch": 1.01, + "learning_rate": 4.4584561470633135e-05, + "loss": 4.2455, + "step": 330752 + }, + { + "epoch": 1.01, + "learning_rate": 4.4576175523122615e-05, + "loss": 4.2568, + "step": 331264 + }, + { + "epoch": 1.01, + "learning_rate": 4.4567789575612095e-05, + "loss": 4.2652, + "step": 331776 + }, + { + "epoch": 1.01, + "learning_rate": 4.4559420006905304e-05, + "loss": 4.2446, + "step": 332288 + }, + { + "epoch": 1.01, + "learning_rate": 4.4551034059394784e-05, + "loss": 4.2693, + "step": 332800 + }, + { + "epoch": 1.01, + "learning_rate": 4.454266449068799e-05, + "loss": 4.2493, + "step": 333312 + }, + { + "epoch": 1.01, + "learning_rate": 4.453429492198121e-05, + "loss": 4.245, + "step": 333824 + }, + { + "epoch": 1.01, + "learning_rate": 4.452590897447069e-05, + "loss": 4.2511, + "step": 334336 + }, + { + "epoch": 1.01, + "learning_rate": 4.451752302696017e-05, + "loss": 4.2444, + "step": 334848 + }, + { + "epoch": 1.01, + "learning_rate": 4.450913707944965e-05, + "loss": 4.2635, + "step": 335360 + }, + { + "epoch": 1.01, + "learning_rate": 4.450075113193913e-05, + "loss": 4.2543, + "step": 335872 + }, + { + "epoch": 1.01, + "learning_rate": 4.449236518442861e-05, + "loss": 4.2376, + "step": 336384 + }, + { + "epoch": 1.01, + "learning_rate": 4.448397923691809e-05, + "loss": 4.2531, + "step": 336896 + }, + { + "epoch": 1.01, + "learning_rate": 4.447559328940757e-05, + "loss": 4.2463, + "step": 337408 + }, + { + "epoch": 1.01, + "learning_rate": 4.446720734189705e-05, + "loss": 4.2572, + "step": 337920 + }, + { + "epoch": 1.01, + "learning_rate": 4.445883777319026e-05, + "loss": 4.2415, + "step": 338432 + }, + { + "epoch": 1.01, + "learning_rate": 4.445045182567974e-05, + "loss": 4.2536, + "step": 338944 + }, + { + "epoch": 1.01, + "learning_rate": 4.444206587816922e-05, + "loss": 4.2358, + "step": 339456 + }, + { + "epoch": 1.01, + "learning_rate": 4.44336799306587e-05, + "loss": 4.2546, + "step": 339968 + }, + { + "epoch": 1.01, + "learning_rate": 4.442529398314818e-05, + "loss": 4.2435, + "step": 340480 + }, + { + "epoch": 1.01, + "learning_rate": 4.441690803563766e-05, + "loss": 4.2444, + "step": 340992 + }, + { + "epoch": 1.01, + "learning_rate": 4.440852208812714e-05, + "loss": 4.2534, + "step": 341504 + }, + { + "epoch": 1.01, + "learning_rate": 4.440013614061662e-05, + "loss": 4.2463, + "step": 342016 + }, + { + "epoch": 1.01, + "learning_rate": 4.4391766571909834e-05, + "loss": 4.2555, + "step": 342528 + }, + { + "epoch": 1.01, + "learning_rate": 4.4383380624399314e-05, + "loss": 4.2638, + "step": 343040 + }, + { + "epoch": 1.01, + "learning_rate": 4.437499467688879e-05, + "loss": 4.2626, + "step": 343552 + }, + { + "epoch": 1.01, + "learning_rate": 4.4366625108182e-05, + "loss": 4.2468, + "step": 344064 + }, + { + "epoch": 1.01, + "learning_rate": 4.435823916067148e-05, + "loss": 4.2424, + "step": 344576 + }, + { + "epoch": 1.01, + "learning_rate": 4.4349853213160956e-05, + "loss": 4.2357, + "step": 345088 + }, + { + "epoch": 1.01, + "learning_rate": 4.4341467265650436e-05, + "loss": 4.249, + "step": 345600 + }, + { + "epoch": 1.01, + "learning_rate": 4.4333081318139916e-05, + "loss": 4.2633, + "step": 346112 + }, + { + "epoch": 1.01, + "learning_rate": 4.432471174943313e-05, + "loss": 4.2518, + "step": 346624 + }, + { + "epoch": 1.01, + "learning_rate": 4.431632580192261e-05, + "loss": 4.2416, + "step": 347136 + }, + { + "epoch": 1.01, + "learning_rate": 4.430795623321583e-05, + "loss": 4.2285, + "step": 347648 + }, + { + "epoch": 1.01, + "learning_rate": 4.429957028570531e-05, + "loss": 4.2545, + "step": 348160 + }, + { + "epoch": 1.01, + "learning_rate": 4.429118433819479e-05, + "loss": 4.2301, + "step": 348672 + }, + { + "epoch": 1.01, + "learning_rate": 4.4282814769487996e-05, + "loss": 4.2406, + "step": 349184 + }, + { + "epoch": 1.01, + "learning_rate": 4.4274428821977476e-05, + "loss": 4.2422, + "step": 349696 + }, + { + "epoch": 1.01, + "learning_rate": 4.4266042874466956e-05, + "loss": 4.2467, + "step": 350208 + }, + { + "epoch": 1.01, + "learning_rate": 4.425765692695643e-05, + "loss": 4.2461, + "step": 350720 + }, + { + "epoch": 1.02, + "learning_rate": 4.424927097944591e-05, + "loss": 4.2505, + "step": 351232 + }, + { + "epoch": 1.02, + "learning_rate": 4.424088503193539e-05, + "loss": 4.2314, + "step": 351744 + }, + { + "epoch": 1.02, + "learning_rate": 4.423249908442487e-05, + "loss": 4.2441, + "step": 352256 + }, + { + "epoch": 1.02, + "learning_rate": 4.422411313691435e-05, + "loss": 4.2405, + "step": 352768 + }, + { + "epoch": 1.02, + "learning_rate": 4.4215727189403836e-05, + "loss": 4.2343, + "step": 353280 + }, + { + "epoch": 1.02, + "learning_rate": 4.4207341241893316e-05, + "loss": 4.2297, + "step": 353792 + }, + { + "epoch": 1.02, + "learning_rate": 4.4198955294382796e-05, + "loss": 4.2526, + "step": 354304 + }, + { + "epoch": 1.02, + "learning_rate": 4.4190569346872276e-05, + "loss": 4.2454, + "step": 354816 + }, + { + "epoch": 1.02, + "learning_rate": 4.4182183399361756e-05, + "loss": 4.244, + "step": 355328 + }, + { + "epoch": 1.02, + "learning_rate": 4.4173797451851236e-05, + "loss": 4.2359, + "step": 355840 + }, + { + "epoch": 1.02, + "learning_rate": 4.4165411504340716e-05, + "loss": 4.2424, + "step": 356352 + }, + { + "epoch": 1.02, + "learning_rate": 4.4157025556830196e-05, + "loss": 4.2304, + "step": 356864 + }, + { + "epoch": 1.02, + "learning_rate": 4.4148655988123405e-05, + "loss": 4.2452, + "step": 357376 + }, + { + "epoch": 1.02, + "learning_rate": 4.4140270040612885e-05, + "loss": 4.2448, + "step": 357888 + }, + { + "epoch": 1.02, + "learning_rate": 4.4131900471906094e-05, + "loss": 4.231, + "step": 358400 + }, + { + "epoch": 1.02, + "learning_rate": 4.4123514524395574e-05, + "loss": 4.2478, + "step": 358912 + }, + { + "epoch": 1.02, + "learning_rate": 4.4115128576885054e-05, + "loss": 4.2148, + "step": 359424 + }, + { + "epoch": 1.02, + "learning_rate": 4.4106742629374534e-05, + "loss": 4.2219, + "step": 359936 + }, + { + "epoch": 1.02, + "learning_rate": 4.409835668186402e-05, + "loss": 4.229, + "step": 360448 + }, + { + "epoch": 1.02, + "learning_rate": 4.40899707343535e-05, + "loss": 4.2327, + "step": 360960 + }, + { + "epoch": 1.02, + "learning_rate": 4.4081584786842974e-05, + "loss": 4.2422, + "step": 361472 + }, + { + "epoch": 1.02, + "learning_rate": 4.407321521813619e-05, + "loss": 4.2302, + "step": 361984 + }, + { + "epoch": 1.02, + "learning_rate": 4.406482927062567e-05, + "loss": 4.2193, + "step": 362496 + }, + { + "epoch": 1.02, + "learning_rate": 4.405644332311514e-05, + "loss": 4.2283, + "step": 363008 + }, + { + "epoch": 1.02, + "learning_rate": 4.404805737560462e-05, + "loss": 4.2396, + "step": 363520 + }, + { + "epoch": 1.02, + "learning_rate": 4.403968780689784e-05, + "loss": 4.2368, + "step": 364032 + }, + { + "epoch": 1.02, + "learning_rate": 4.403130185938732e-05, + "loss": 4.2402, + "step": 364544 + }, + { + "epoch": 1.02, + "learning_rate": 4.402291591187679e-05, + "loss": 4.2264, + "step": 365056 + }, + { + "epoch": 1.02, + "learning_rate": 4.401452996436627e-05, + "loss": 4.2252, + "step": 365568 + }, + { + "epoch": 1.02, + "learning_rate": 4.400614401685576e-05, + "loss": 4.2421, + "step": 366080 + }, + { + "epoch": 1.02, + "learning_rate": 4.399777444814897e-05, + "loss": 4.2293, + "step": 366592 + }, + { + "epoch": 1.02, + "learning_rate": 4.398938850063845e-05, + "loss": 4.2244, + "step": 367104 + }, + { + "epoch": 1.02, + "learning_rate": 4.398100255312793e-05, + "loss": 4.2292, + "step": 367616 + }, + { + "epoch": 1.02, + "learning_rate": 4.397261660561741e-05, + "loss": 4.2178, + "step": 368128 + }, + { + "epoch": 1.02, + "learning_rate": 4.396423065810689e-05, + "loss": 4.2304, + "step": 368640 + }, + { + "epoch": 1.02, + "learning_rate": 4.395584471059637e-05, + "loss": 4.2314, + "step": 369152 + }, + { + "epoch": 1.02, + "learning_rate": 4.394745876308585e-05, + "loss": 4.2375, + "step": 369664 + }, + { + "epoch": 1.02, + "learning_rate": 4.3939089194379056e-05, + "loss": 4.2181, + "step": 370176 + }, + { + "epoch": 1.02, + "learning_rate": 4.3930703246868536e-05, + "loss": 4.2235, + "step": 370688 + }, + { + "epoch": 1.02, + "learning_rate": 4.3922317299358016e-05, + "loss": 4.2384, + "step": 371200 + }, + { + "epoch": 1.02, + "learning_rate": 4.3913931351847496e-05, + "loss": 4.2273, + "step": 371712 + }, + { + "epoch": 1.02, + "learning_rate": 4.3905545404336976e-05, + "loss": 4.2315, + "step": 372224 + }, + { + "epoch": 1.02, + "learning_rate": 4.3897159456826456e-05, + "loss": 4.2322, + "step": 372736 + }, + { + "epoch": 1.02, + "learning_rate": 4.3888773509315936e-05, + "loss": 4.2368, + "step": 373248 + }, + { + "epoch": 1.02, + "learning_rate": 4.388038756180542e-05, + "loss": 4.235, + "step": 373760 + }, + { + "epoch": 1.02, + "learning_rate": 4.387201799309863e-05, + "loss": 4.2204, + "step": 374272 + }, + { + "epoch": 1.02, + "learning_rate": 4.386363204558811e-05, + "loss": 4.2184, + "step": 374784 + }, + { + "epoch": 1.02, + "learning_rate": 4.385524609807759e-05, + "loss": 4.2202, + "step": 375296 + }, + { + "epoch": 1.02, + "learning_rate": 4.384686015056707e-05, + "loss": 4.2283, + "step": 375808 + }, + { + "epoch": 1.02, + "learning_rate": 4.383847420305655e-05, + "loss": 4.2312, + "step": 376320 + }, + { + "epoch": 1.02, + "learning_rate": 4.383010463434976e-05, + "loss": 4.2327, + "step": 376832 + }, + { + "epoch": 1.02, + "learning_rate": 4.382173506564297e-05, + "loss": 4.2304, + "step": 377344 + }, + { + "epoch": 1.02, + "learning_rate": 4.381334911813245e-05, + "loss": 4.2221, + "step": 377856 + }, + { + "epoch": 1.02, + "learning_rate": 4.380496317062193e-05, + "loss": 4.2214, + "step": 378368 + }, + { + "epoch": 1.02, + "learning_rate": 4.379657722311141e-05, + "loss": 4.212, + "step": 378880 + }, + { + "epoch": 1.02, + "learning_rate": 4.378819127560089e-05, + "loss": 4.2287, + "step": 379392 + }, + { + "epoch": 1.02, + "learning_rate": 4.3779805328090376e-05, + "loss": 4.2309, + "step": 379904 + }, + { + "epoch": 1.02, + "learning_rate": 4.3771419380579856e-05, + "loss": 4.2346, + "step": 380416 + }, + { + "epoch": 1.02, + "learning_rate": 4.3763033433069336e-05, + "loss": 4.2136, + "step": 380928 + }, + { + "epoch": 1.02, + "learning_rate": 4.3754663864362545e-05, + "loss": 4.216, + "step": 381440 + }, + { + "epoch": 1.03, + "eval_loss": 4.209681034088135, + "eval_runtime": 546.9996, + "eval_samples_per_second": 697.607, + "eval_steps_per_second": 21.801, + "step": 381595 + }, + { + "epoch": 0.0, + "learning_rate": 4.3746277916852025e-05, + "loss": 4.2385, + "step": 381952 + }, + { + "epoch": 0.0, + "learning_rate": 4.3737891969341505e-05, + "loss": 4.223, + "step": 382464 + }, + { + "epoch": 0.0, + "learning_rate": 4.372950602183098e-05, + "loss": 4.2188, + "step": 382976 + }, + { + "epoch": 0.0, + "learning_rate": 4.372112007432046e-05, + "loss": 4.2132, + "step": 383488 + }, + { + "epoch": 0.0, + "learning_rate": 4.371273412680994e-05, + "loss": 4.2169, + "step": 384000 + }, + { + "epoch": 0.0, + "learning_rate": 4.370434817929942e-05, + "loss": 4.206, + "step": 384512 + }, + { + "epoch": 0.0, + "learning_rate": 4.36959622317889e-05, + "loss": 4.2118, + "step": 385024 + }, + { + "epoch": 0.0, + "learning_rate": 4.368757628427838e-05, + "loss": 4.21, + "step": 385536 + }, + { + "epoch": 0.0, + "learning_rate": 4.367919033676786e-05, + "loss": 4.2146, + "step": 386048 + }, + { + "epoch": 0.0, + "learning_rate": 4.3670804389257345e-05, + "loss": 4.2242, + "step": 386560 + }, + { + "epoch": 0.0, + "learning_rate": 4.3662418441746825e-05, + "loss": 4.2179, + "step": 387072 + }, + { + "epoch": 0.0, + "learning_rate": 4.3654032494236305e-05, + "loss": 4.2164, + "step": 387584 + }, + { + "epoch": 0.0, + "learning_rate": 4.3645646546725785e-05, + "loss": 4.2206, + "step": 388096 + }, + { + "epoch": 0.0, + "learning_rate": 4.3637260599215265e-05, + "loss": 4.2192, + "step": 388608 + }, + { + "epoch": 0.0, + "learning_rate": 4.3628874651704745e-05, + "loss": 4.2126, + "step": 389120 + }, + { + "epoch": 0.0, + "learning_rate": 4.3620488704194225e-05, + "loss": 4.2078, + "step": 389632 + }, + { + "epoch": 0.0, + "learning_rate": 4.3612119135487434e-05, + "loss": 4.2057, + "step": 390144 + }, + { + "epoch": 0.0, + "learning_rate": 4.3603733187976914e-05, + "loss": 4.2136, + "step": 390656 + }, + { + "epoch": 0.0, + "learning_rate": 4.3595347240466394e-05, + "loss": 4.2142, + "step": 391168 + }, + { + "epoch": 0.0, + "learning_rate": 4.358696129295587e-05, + "loss": 4.2238, + "step": 391680 + }, + { + "epoch": 0.0, + "learning_rate": 4.357857534544535e-05, + "loss": 4.2102, + "step": 392192 + }, + { + "epoch": 0.0, + "learning_rate": 4.357018939793483e-05, + "loss": 4.2208, + "step": 392704 + }, + { + "epoch": 0.0, + "learning_rate": 4.356180345042431e-05, + "loss": 4.2169, + "step": 393216 + }, + { + "epoch": 0.0, + "learning_rate": 4.355341750291379e-05, + "loss": 4.2107, + "step": 393728 + }, + { + "epoch": 0.0, + "learning_rate": 4.3545047934207e-05, + "loss": 4.2116, + "step": 394240 + }, + { + "epoch": 0.0, + "learning_rate": 4.353666198669648e-05, + "loss": 4.2096, + "step": 394752 + }, + { + "epoch": 0.0, + "learning_rate": 4.352827603918596e-05, + "loss": 4.2189, + "step": 395264 + }, + { + "epoch": 0.0, + "learning_rate": 4.351989009167544e-05, + "loss": 4.1993, + "step": 395776 + }, + { + "epoch": 0.0, + "learning_rate": 4.351152052296865e-05, + "loss": 4.2214, + "step": 396288 + }, + { + "epoch": 0.0, + "learning_rate": 4.350313457545813e-05, + "loss": 4.2033, + "step": 396800 + }, + { + "epoch": 0.01, + "learning_rate": 4.349474862794761e-05, + "loss": 4.1994, + "step": 397312 + }, + { + "epoch": 0.01, + "learning_rate": 4.348636268043709e-05, + "loss": 4.2146, + "step": 397824 + }, + { + "epoch": 0.01, + "learning_rate": 4.34779931117303e-05, + "loss": 4.2114, + "step": 398336 + }, + { + "epoch": 0.01, + "learning_rate": 4.3469623543023516e-05, + "loss": 4.2141, + "step": 398848 + }, + { + "epoch": 0.01, + "learning_rate": 4.3461237595512996e-05, + "loss": 4.2059, + "step": 399360 + }, + { + "epoch": 0.01, + "learning_rate": 4.3452851648002476e-05, + "loss": 4.2053, + "step": 399872 + }, + { + "epoch": 0.01, + "learning_rate": 4.344448207929569e-05, + "loss": 4.2109, + "step": 400384 + }, + { + "epoch": 0.01, + "learning_rate": 4.3436096131785165e-05, + "loss": 4.2248, + "step": 400896 + }, + { + "epoch": 0.01, + "learning_rate": 4.3427710184274645e-05, + "loss": 4.2069, + "step": 401408 + }, + { + "epoch": 0.01, + "learning_rate": 4.3419324236764125e-05, + "loss": 4.1988, + "step": 401920 + }, + { + "epoch": 0.01, + "learning_rate": 4.3410938289253605e-05, + "loss": 4.197, + "step": 402432 + }, + { + "epoch": 0.01, + "learning_rate": 4.3402552341743085e-05, + "loss": 4.1953, + "step": 402944 + }, + { + "epoch": 0.01, + "learning_rate": 4.3394166394232565e-05, + "loss": 4.2089, + "step": 403456 + }, + { + "epoch": 0.01, + "learning_rate": 4.3385780446722045e-05, + "loss": 4.2018, + "step": 403968 + }, + { + "epoch": 0.01, + "learning_rate": 4.3377394499211525e-05, + "loss": 4.2077, + "step": 404480 + }, + { + "epoch": 0.01, + "learning_rate": 4.3369008551701005e-05, + "loss": 4.2098, + "step": 404992 + }, + { + "epoch": 0.01, + "learning_rate": 4.3360622604190485e-05, + "loss": 4.2019, + "step": 405504 + }, + { + "epoch": 0.01, + "learning_rate": 4.33522530354837e-05, + "loss": 4.2146, + "step": 406016 + }, + { + "epoch": 0.01, + "learning_rate": 4.334386708797318e-05, + "loss": 4.1925, + "step": 406528 + }, + { + "epoch": 0.01, + "learning_rate": 4.333549751926639e-05, + "loss": 4.1841, + "step": 407040 + }, + { + "epoch": 0.01, + "learning_rate": 4.33271279505596e-05, + "loss": 4.2021, + "step": 407552 + }, + { + "epoch": 0.01, + "learning_rate": 4.331874200304908e-05, + "loss": 4.1995, + "step": 408064 + }, + { + "epoch": 0.01, + "learning_rate": 4.331035605553856e-05, + "loss": 4.191, + "step": 408576 + }, + { + "epoch": 0.01, + "learning_rate": 4.330197010802804e-05, + "loss": 4.2095, + "step": 409088 + }, + { + "epoch": 0.01, + "learning_rate": 4.329360053932125e-05, + "loss": 4.1891, + "step": 409600 + }, + { + "epoch": 0.01, + "learning_rate": 4.328521459181073e-05, + "loss": 4.1906, + "step": 410112 + }, + { + "epoch": 0.01, + "learning_rate": 4.327682864430021e-05, + "loss": 4.1929, + "step": 410624 + }, + { + "epoch": 0.01, + "learning_rate": 4.326844269678969e-05, + "loss": 4.1879, + "step": 411136 + }, + { + "epoch": 0.01, + "learning_rate": 4.326005674927917e-05, + "loss": 4.2034, + "step": 411648 + }, + { + "epoch": 0.01, + "learning_rate": 4.3251670801768654e-05, + "loss": 4.1946, + "step": 412160 + }, + { + "epoch": 0.01, + "learning_rate": 4.3243284854258134e-05, + "loss": 4.1888, + "step": 412672 + }, + { + "epoch": 0.01, + "learning_rate": 4.3234898906747614e-05, + "loss": 4.1914, + "step": 413184 + }, + { + "epoch": 0.01, + "learning_rate": 4.3226512959237094e-05, + "loss": 4.185, + "step": 413696 + }, + { + "epoch": 0.01, + "learning_rate": 4.3218127011726574e-05, + "loss": 4.2034, + "step": 414208 + }, + { + "epoch": 0.01, + "learning_rate": 4.3209741064216054e-05, + "loss": 4.187, + "step": 414720 + }, + { + "epoch": 0.01, + "learning_rate": 4.320135511670553e-05, + "loss": 4.201, + "step": 415232 + }, + { + "epoch": 0.01, + "learning_rate": 4.319298554799874e-05, + "loss": 4.1758, + "step": 415744 + }, + { + "epoch": 0.01, + "learning_rate": 4.318459960048822e-05, + "loss": 4.1942, + "step": 416256 + }, + { + "epoch": 0.01, + "learning_rate": 4.31762136529777e-05, + "loss": 4.1887, + "step": 416768 + }, + { + "epoch": 0.01, + "learning_rate": 4.3167827705467176e-05, + "loss": 4.1864, + "step": 417280 + }, + { + "epoch": 0.01, + "learning_rate": 4.315945813676039e-05, + "loss": 4.1974, + "step": 417792 + }, + { + "epoch": 0.01, + "learning_rate": 4.315108856805361e-05, + "loss": 4.1929, + "step": 418304 + }, + { + "epoch": 0.01, + "learning_rate": 4.314270262054309e-05, + "loss": 4.1956, + "step": 418816 + }, + { + "epoch": 0.01, + "learning_rate": 4.313431667303257e-05, + "loss": 4.2061, + "step": 419328 + }, + { + "epoch": 0.01, + "learning_rate": 4.312593072552205e-05, + "loss": 4.2069, + "step": 419840 + }, + { + "epoch": 0.01, + "learning_rate": 4.311756115681526e-05, + "loss": 4.1948, + "step": 420352 + }, + { + "epoch": 0.01, + "learning_rate": 4.310917520930474e-05, + "loss": 4.1879, + "step": 420864 + }, + { + "epoch": 0.01, + "learning_rate": 4.310078926179422e-05, + "loss": 4.1817, + "step": 421376 + }, + { + "epoch": 0.01, + "learning_rate": 4.30924033142837e-05, + "loss": 4.192, + "step": 421888 + }, + { + "epoch": 0.01, + "learning_rate": 4.308401736677318e-05, + "loss": 4.2048, + "step": 422400 + }, + { + "epoch": 0.01, + "learning_rate": 4.307563141926265e-05, + "loss": 4.196, + "step": 422912 + }, + { + "epoch": 0.01, + "learning_rate": 4.306724547175213e-05, + "loss": 4.1901, + "step": 423424 + }, + { + "epoch": 0.01, + "learning_rate": 4.305885952424161e-05, + "loss": 4.1738, + "step": 423936 + }, + { + "epoch": 0.01, + "learning_rate": 4.3050489955534826e-05, + "loss": 4.2003, + "step": 424448 + }, + { + "epoch": 0.01, + "learning_rate": 4.3042104008024306e-05, + "loss": 4.1731, + "step": 424960 + }, + { + "epoch": 0.01, + "learning_rate": 4.3033718060513786e-05, + "loss": 4.1871, + "step": 425472 + }, + { + "epoch": 0.01, + "learning_rate": 4.3025332113003266e-05, + "loss": 4.1884, + "step": 425984 + }, + { + "epoch": 0.01, + "learning_rate": 4.3016946165492746e-05, + "loss": 4.1923, + "step": 426496 + }, + { + "epoch": 0.01, + "learning_rate": 4.3008560217982226e-05, + "loss": 4.1904, + "step": 427008 + }, + { + "epoch": 0.02, + "learning_rate": 4.3000174270471705e-05, + "loss": 4.1993, + "step": 427520 + }, + { + "epoch": 0.02, + "learning_rate": 4.2991788322961185e-05, + "loss": 4.1745, + "step": 428032 + }, + { + "epoch": 0.02, + "learning_rate": 4.2983418754254395e-05, + "loss": 4.1861, + "step": 428544 + }, + { + "epoch": 0.02, + "learning_rate": 4.2975032806743874e-05, + "loss": 4.1902, + "step": 429056 + }, + { + "epoch": 0.02, + "learning_rate": 4.2966646859233354e-05, + "loss": 4.1805, + "step": 429568 + }, + { + "epoch": 0.02, + "learning_rate": 4.2958260911722834e-05, + "loss": 4.1762, + "step": 430080 + }, + { + "epoch": 0.02, + "learning_rate": 4.2949891343016043e-05, + "loss": 4.1959, + "step": 430592 + }, + { + "epoch": 0.02, + "learning_rate": 4.294152177430926e-05, + "loss": 4.19, + "step": 431104 + }, + { + "epoch": 0.02, + "learning_rate": 4.293313582679874e-05, + "loss": 4.197, + "step": 431616 + }, + { + "epoch": 0.02, + "learning_rate": 4.292474987928822e-05, + "loss": 4.1811, + "step": 432128 + }, + { + "epoch": 0.02, + "learning_rate": 4.29163639317777e-05, + "loss": 4.188, + "step": 432640 + }, + { + "epoch": 0.02, + "learning_rate": 4.290797798426718e-05, + "loss": 4.1771, + "step": 433152 + }, + { + "epoch": 0.02, + "learning_rate": 4.289960841556039e-05, + "loss": 4.1914, + "step": 433664 + }, + { + "epoch": 0.02, + "learning_rate": 4.289122246804987e-05, + "loss": 4.1946, + "step": 434176 + }, + { + "epoch": 0.02, + "learning_rate": 4.288283652053935e-05, + "loss": 4.178, + "step": 434688 + }, + { + "epoch": 0.02, + "learning_rate": 4.287445057302883e-05, + "loss": 4.1948, + "step": 435200 + }, + { + "epoch": 0.02, + "learning_rate": 4.286606462551831e-05, + "loss": 4.1623, + "step": 435712 + }, + { + "epoch": 0.02, + "learning_rate": 4.285767867800779e-05, + "loss": 4.1725, + "step": 436224 + }, + { + "epoch": 0.02, + "learning_rate": 4.284929273049727e-05, + "loss": 4.1719, + "step": 436736 + }, + { + "epoch": 0.02, + "learning_rate": 4.284090678298675e-05, + "loss": 4.1812, + "step": 437248 + }, + { + "epoch": 0.02, + "learning_rate": 4.283252083547623e-05, + "loss": 4.1905, + "step": 437760 + }, + { + "epoch": 0.02, + "learning_rate": 4.282413488796571e-05, + "loss": 4.1836, + "step": 438272 + }, + { + "epoch": 0.02, + "learning_rate": 4.281574894045519e-05, + "loss": 4.1593, + "step": 438784 + }, + { + "epoch": 0.02, + "learning_rate": 4.280736299294467e-05, + "loss": 4.1801, + "step": 439296 + }, + { + "epoch": 0.02, + "learning_rate": 4.2798993424237884e-05, + "loss": 4.1855, + "step": 439808 + }, + { + "epoch": 0.02, + "learning_rate": 4.2790607476727364e-05, + "loss": 4.1882, + "step": 440320 + }, + { + "epoch": 0.02, + "learning_rate": 4.278222152921684e-05, + "loss": 4.1846, + "step": 440832 + }, + { + "epoch": 0.02, + "learning_rate": 4.277383558170632e-05, + "loss": 4.1753, + "step": 441344 + }, + { + "epoch": 0.02, + "learning_rate": 4.276546601299953e-05, + "loss": 4.1739, + "step": 441856 + }, + { + "epoch": 0.02, + "learning_rate": 4.275709644429274e-05, + "loss": 4.1929, + "step": 442368 + }, + { + "epoch": 0.02, + "learning_rate": 4.274871049678222e-05, + "loss": 4.1775, + "step": 442880 + }, + { + "epoch": 0.02, + "learning_rate": 4.27403245492717e-05, + "loss": 4.1752, + "step": 443392 + }, + { + "epoch": 0.02, + "learning_rate": 4.273193860176118e-05, + "loss": 4.1727, + "step": 443904 + }, + { + "epoch": 0.02, + "learning_rate": 4.27235690330544e-05, + "loss": 4.1699, + "step": 444416 + }, + { + "epoch": 0.02, + "learning_rate": 4.271518308554388e-05, + "loss": 4.1783, + "step": 444928 + }, + { + "epoch": 0.02, + "learning_rate": 4.270679713803336e-05, + "loss": 4.1811, + "step": 445440 + }, + { + "epoch": 0.02, + "learning_rate": 4.269841119052284e-05, + "loss": 4.1865, + "step": 445952 + }, + { + "epoch": 0.02, + "learning_rate": 4.269002524301231e-05, + "loss": 4.1705, + "step": 446464 + }, + { + "epoch": 0.02, + "learning_rate": 4.268163929550179e-05, + "loss": 4.1706, + "step": 446976 + }, + { + "epoch": 0.02, + "learning_rate": 4.267325334799127e-05, + "loss": 4.1865, + "step": 447488 + }, + { + "epoch": 0.02, + "learning_rate": 4.266486740048075e-05, + "loss": 4.1726, + "step": 448000 + }, + { + "epoch": 0.02, + "learning_rate": 4.265649783177396e-05, + "loss": 4.1804, + "step": 448512 + }, + { + "epoch": 0.02, + "learning_rate": 4.264811188426344e-05, + "loss": 4.1829, + "step": 449024 + }, + { + "epoch": 0.02, + "learning_rate": 4.263972593675292e-05, + "loss": 4.1881, + "step": 449536 + }, + { + "epoch": 0.02, + "learning_rate": 4.26313399892424e-05, + "loss": 4.1844, + "step": 450048 + }, + { + "epoch": 0.02, + "learning_rate": 4.2622970420535615e-05, + "loss": 4.1725, + "step": 450560 + }, + { + "epoch": 0.02, + "learning_rate": 4.2614584473025095e-05, + "loss": 4.1635, + "step": 451072 + }, + { + "epoch": 0.02, + "learning_rate": 4.2606198525514575e-05, + "loss": 4.1709, + "step": 451584 + }, + { + "epoch": 0.02, + "learning_rate": 4.2597812578004055e-05, + "loss": 4.1769, + "step": 452096 + }, + { + "epoch": 0.02, + "learning_rate": 4.2589426630493535e-05, + "loss": 4.1859, + "step": 452608 + }, + { + "epoch": 0.02, + "learning_rate": 4.2581040682983015e-05, + "loss": 4.1807, + "step": 453120 + }, + { + "epoch": 0.02, + "learning_rate": 4.2572654735472495e-05, + "loss": 4.1762, + "step": 453632 + }, + { + "epoch": 0.02, + "learning_rate": 4.2564268787961975e-05, + "loss": 4.1764, + "step": 454144 + }, + { + "epoch": 0.02, + "learning_rate": 4.2555899219255184e-05, + "loss": 4.1747, + "step": 454656 + }, + { + "epoch": 0.02, + "learning_rate": 4.2547513271744664e-05, + "loss": 4.1639, + "step": 455168 + }, + { + "epoch": 0.02, + "learning_rate": 4.253914370303787e-05, + "loss": 4.1714, + "step": 455680 + }, + { + "epoch": 0.02, + "learning_rate": 4.253075775552735e-05, + "loss": 4.1847, + "step": 456192 + }, + { + "epoch": 0.02, + "learning_rate": 4.252237180801684e-05, + "loss": 4.1864, + "step": 456704 + }, + { + "epoch": 0.02, + "learning_rate": 4.251398586050632e-05, + "loss": 4.1653, + "step": 457216 + }, + { + "epoch": 0.02, + "learning_rate": 4.25055999129958e-05, + "loss": 4.1643, + "step": 457728 + }, + { + "epoch": 0.03, + "eval_loss": 4.168251037597656, + "eval_runtime": 545.9187, + "eval_samples_per_second": 698.989, + "eval_steps_per_second": 21.844, + "step": 457914 + }, + { + "epoch": 0.0, + "learning_rate": 4.249721396548528e-05, + "loss": 4.1915, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248882801797476e-05, + "loss": 4.1737, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248044207046424e-05, + "loss": 4.1656, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247205612295372e-05, + "loss": 4.1677, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.24636701754432e-05, + "loss": 4.1644, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245528422793267e-05, + "loss": 4.1587, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.244689828042215e-05, + "loss": 4.16, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243851233291163e-05, + "loss": 4.1653, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243012638540111e-05, + "loss": 4.1674, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.242174043789059e-05, + "loss": 4.1727, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241335449038007e-05, + "loss": 4.1712, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240496854286955e-05, + "loss": 4.1637, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239658259535903e-05, + "loss": 4.1774, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238819664784852e-05, + "loss": 4.1672, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.2379810700338e-05, + "loss": 4.1677, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237142475282748e-05, + "loss": 4.1555, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236303880531696e-05, + "loss": 4.1545, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.235465285780644e-05, + "loss": 4.1692, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.234626691029591e-05, + "loss": 4.1657, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233789734158913e-05, + "loss": 4.1758, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.232952777288234e-05, + "loss": 4.1636, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232114182537182e-05, + "loss": 4.1726, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.23127558778613e-05, + "loss": 4.1683, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230436993035078e-05, + "loss": 4.1659, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.229598398284026e-05, + "loss": 4.1632, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.228759803532974e-05, + "loss": 4.1617, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227921208781922e-05, + "loss": 4.1717, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.22708261403087e-05, + "loss": 4.1529, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226245657160191e-05, + "loss": 4.1723, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.2254070624091386e-05, + "loss": 4.1603, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.2245684676580866e-05, + "loss": 4.1518, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.2237298729070346e-05, + "loss": 4.164, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.222894553916729e-05, + "loss": 4.166, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222055959165677e-05, + "loss": 4.1698, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221217364414625e-05, + "loss": 4.157, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.220378769663573e-05, + "loss": 4.1624, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219540174912521e-05, + "loss": 4.1648, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.2187032180418426e-05, + "loss": 4.1749, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.2178646232907906e-05, + "loss": 4.1629, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.2170260285397386e-05, + "loss": 4.1525, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.2161890716690595e-05, + "loss": 4.1505, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.2153504769180075e-05, + "loss": 4.1471, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.2145118821669555e-05, + "loss": 4.1671, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.2136732874159035e-05, + "loss": 4.1578, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.212834692664851e-05, + "loss": 4.1582, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.211996097913799e-05, + "loss": 4.1688, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.211157503162747e-05, + "loss": 4.1538, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210318908411695e-05, + "loss": 4.1678, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209480313660643e-05, + "loss": 4.1497, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208641718909591e-05, + "loss": 4.1434, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.2078031241585395e-05, + "loss": 4.1556, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.2069661672878604e-05, + "loss": 4.1511, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.2061275725368084e-05, + "loss": 4.1497, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.2052889777857564e-05, + "loss": 4.1591, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.2044503830347044e-05, + "loss": 4.1508, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.2036117882836524e-05, + "loss": 4.1447, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.2027731935326004e-05, + "loss": 4.1453, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.2019345987815484e-05, + "loss": 4.145, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.2010960040304964e-05, + "loss": 4.158, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200259047159817e-05, + "loss": 4.1492, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199420452408765e-05, + "loss": 4.1435, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.198583495538086e-05, + "loss": 4.1475, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197744900787035e-05, + "loss": 4.1347, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196906306035983e-05, + "loss": 4.163, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.196067711284931e-05, + "loss": 4.1447, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195229116533879e-05, + "loss": 4.1518, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194390521782827e-05, + "loss": 4.1387, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193551927031775e-05, + "loss": 4.1444, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192713332280722e-05, + "loss": 4.1473, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.191876375410044e-05, + "loss": 4.1427, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191037780658992e-05, + "loss": 4.1548, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.19019918590794e-05, + "loss": 4.1472, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189360591156887e-05, + "loss": 4.1538, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.1885236342862086e-05, + "loss": 4.1619, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.18768667741553e-05, + "loss": 4.1607, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186848082664478e-05, + "loss": 4.1534, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.186009487913426e-05, + "loss": 4.1463, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185170893162374e-05, + "loss": 4.1398, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184332298411322e-05, + "loss": 4.1479, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183495341540643e-05, + "loss": 4.1587, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182656746789591e-05, + "loss": 4.1544, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181818152038539e-05, + "loss": 4.1462, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.180979557287487e-05, + "loss": 4.1299, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.1801409625364344e-05, + "loss": 4.1584, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.1793023677853824e-05, + "loss": 4.1272, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.1784637730343304e-05, + "loss": 4.1449, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.177626816163652e-05, + "loss": 4.1471, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.1767882214126e-05, + "loss": 4.1442, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.175949626661548e-05, + "loss": 4.1502, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175111031910496e-05, + "loss": 4.1562, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.174272437159444e-05, + "loss": 4.13, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173433842408392e-05, + "loss": 4.145, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.17259524765734e-05, + "loss": 4.1482, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171758290786661e-05, + "loss": 4.1383, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170919696035609e-05, + "loss": 4.1326, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170081101284557e-05, + "loss": 4.155, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169242506533505e-05, + "loss": 4.149, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.168403911782453e-05, + "loss": 4.1573, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167565317031401e-05, + "loss": 4.1382, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166726722280349e-05, + "loss": 4.1469, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165888127529297e-05, + "loss": 4.1337, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.1650511706586184e-05, + "loss": 4.1492, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.1642142137879393e-05, + "loss": 4.1519, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.1633756190368873e-05, + "loss": 4.1422, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.1625370242858353e-05, + "loss": 4.1495, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.161698429534783e-05, + "loss": 4.1246, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.160861472664104e-05, + "loss": 4.1272, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160022877913052e-05, + "loss": 4.1262, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159184283162e-05, + "loss": 4.1401, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158345688410948e-05, + "loss": 4.1492, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157507093659896e-05, + "loss": 4.1468, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156668498908844e-05, + "loss": 4.1191, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155829904157792e-05, + "loss": 4.1368, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.154992947287114e-05, + "loss": 4.1454, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154154352536062e-05, + "loss": 4.1482, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.15331575778501e-05, + "loss": 4.1443, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152477163033958e-05, + "loss": 4.1359, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151638568282906e-05, + "loss": 4.1354, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150801611412227e-05, + "loss": 4.1453, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.149963016661175e-05, + "loss": 4.1396, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149124421910123e-05, + "loss": 4.1349, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.14828582715907e-05, + "loss": 4.1299, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147447232408018e-05, + "loss": 4.1271, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.1466102755373396e-05, + "loss": 4.141, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.1457716807862876e-05, + "loss": 4.1404, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.1449330860352356e-05, + "loss": 4.1429, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.1440944912841836e-05, + "loss": 4.1325, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.1432558965331316e-05, + "loss": 4.1293, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.1424173017820796e-05, + "loss": 4.1472, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.1415787070310276e-05, + "loss": 4.1295, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.1407401122799756e-05, + "loss": 4.1422, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.13990479328967e-05, + "loss": 4.1462, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.1390661985386174e-05, + "loss": 4.1444, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.1382276037875654e-05, + "loss": 4.146, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.1373890090365134e-05, + "loss": 4.136, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.1365504142854614e-05, + "loss": 4.1223, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.1357118195344094e-05, + "loss": 4.1308, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.134873224783358e-05, + "loss": 4.135, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.134034630032306e-05, + "loss": 4.1491, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133197673161627e-05, + "loss": 4.1376, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132359078410575e-05, + "loss": 4.1429, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131520483659523e-05, + "loss": 4.1342, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.130683526788844e-05, + "loss": 4.135, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.129844932037792e-05, + "loss": 4.1232, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.12900633728674e-05, + "loss": 4.133, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128167742535688e-05, + "loss": 4.1456, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127329147784636e-05, + "loss": 4.1475, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126490553033584e-05, + "loss": 4.1225, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125651958282532e-05, + "loss": 4.1289, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 4.136957168579102, + "eval_runtime": 548.4137, + "eval_samples_per_second": 695.809, + "eval_steps_per_second": 21.745, + "step": 534233 + }, + { + "epoch": 0.0, + "learning_rate": 4.12481336353148e-05, + "loss": 4.1533, + "step": 534528 + }, + { + "epoch": 0.0, + "learning_rate": 4.123974768780428e-05, + "loss": 4.1362, + "step": 535040 + }, + { + "epoch": 0.0, + "learning_rate": 4.123136174029376e-05, + "loss": 4.1283, + "step": 535552 + }, + { + "epoch": 0.0, + "learning_rate": 4.1222975792783245e-05, + "loss": 4.1313, + "step": 536064 + }, + { + "epoch": 0.0, + "learning_rate": 4.121458984527272e-05, + "loss": 4.1234, + "step": 536576 + }, + { + "epoch": 0.0, + "learning_rate": 4.12062038977622e-05, + "loss": 4.1248, + "step": 537088 + }, + { + "epoch": 0.0, + "learning_rate": 4.119781795025168e-05, + "loss": 4.1154, + "step": 537600 + }, + { + "epoch": 0.0, + "learning_rate": 4.118943200274116e-05, + "loss": 4.1302, + "step": 538112 + }, + { + "epoch": 0.0, + "learning_rate": 4.118104605523064e-05, + "loss": 4.1264, + "step": 538624 + }, + { + "epoch": 0.0, + "learning_rate": 4.117266010772012e-05, + "loss": 4.1354, + "step": 539136 + }, + { + "epoch": 0.0, + "learning_rate": 4.11642741602096e-05, + "loss": 4.1317, + "step": 539648 + }, + { + "epoch": 0.0, + "learning_rate": 4.115588821269908e-05, + "loss": 4.128, + "step": 540160 + }, + { + "epoch": 0.0, + "learning_rate": 4.114750226518856e-05, + "loss": 4.1389, + "step": 540672 + }, + { + "epoch": 0.0, + "learning_rate": 4.113911631767804e-05, + "loss": 4.1253, + "step": 541184 + }, + { + "epoch": 0.0, + "learning_rate": 4.113073037016752e-05, + "loss": 4.136, + "step": 541696 + }, + { + "epoch": 0.0, + "learning_rate": 4.1122344422657e-05, + "loss": 4.1154, + "step": 542208 + }, + { + "epoch": 0.0, + "learning_rate": 4.111395847514648e-05, + "loss": 4.1198, + "step": 542720 + }, + { + "epoch": 0.0, + "learning_rate": 4.110557252763596e-05, + "loss": 4.1309, + "step": 543232 + }, + { + "epoch": 0.0, + "learning_rate": 4.109718658012544e-05, + "loss": 4.1252, + "step": 543744 + }, + { + "epoch": 0.0, + "learning_rate": 4.108881701141865e-05, + "loss": 4.1379, + "step": 544256 + }, + { + "epoch": 0.0, + "learning_rate": 4.108043106390813e-05, + "loss": 4.1272, + "step": 544768 + }, + { + "epoch": 0.0, + "learning_rate": 4.1072045116397606e-05, + "loss": 4.1326, + "step": 545280 + }, + { + "epoch": 0.0, + "learning_rate": 4.1063659168887086e-05, + "loss": 4.1322, + "step": 545792 + }, + { + "epoch": 0.0, + "learning_rate": 4.1055273221376566e-05, + "loss": 4.1234, + "step": 546304 + }, + { + "epoch": 0.0, + "learning_rate": 4.1046887273866046e-05, + "loss": 4.1314, + "step": 546816 + }, + { + "epoch": 0.0, + "learning_rate": 4.1038517705159255e-05, + "loss": 4.1192, + "step": 547328 + }, + { + "epoch": 0.0, + "learning_rate": 4.1030131757648735e-05, + "loss": 4.1348, + "step": 547840 + }, + { + "epoch": 0.0, + "learning_rate": 4.1021745810138215e-05, + "loss": 4.1219, + "step": 548352 + }, + { + "epoch": 0.0, + "learning_rate": 4.1013359862627695e-05, + "loss": 4.1323, + "step": 548864 + }, + { + "epoch": 0.0, + "learning_rate": 4.100499029392091e-05, + "loss": 4.1184, + "step": 549376 + }, + { + "epoch": 0.01, + "learning_rate": 4.099660434641039e-05, + "loss": 4.1179, + "step": 549888 + }, + { + "epoch": 0.01, + "learning_rate": 4.098821839889987e-05, + "loss": 4.1276, + "step": 550400 + }, + { + "epoch": 0.01, + "learning_rate": 4.097983245138935e-05, + "loss": 4.1268, + "step": 550912 + }, + { + "epoch": 0.01, + "learning_rate": 4.097144650387883e-05, + "loss": 4.1305, + "step": 551424 + }, + { + "epoch": 0.01, + "learning_rate": 4.096306055636831e-05, + "loss": 4.1263, + "step": 551936 + }, + { + "epoch": 0.01, + "learning_rate": 4.095469098766152e-05, + "loss": 4.1209, + "step": 552448 + }, + { + "epoch": 0.01, + "learning_rate": 4.0946305040151e-05, + "loss": 4.1302, + "step": 552960 + }, + { + "epoch": 0.01, + "learning_rate": 4.093791909264048e-05, + "loss": 4.1349, + "step": 553472 + }, + { + "epoch": 0.01, + "learning_rate": 4.092953314512996e-05, + "loss": 4.1262, + "step": 553984 + }, + { + "epoch": 0.01, + "learning_rate": 4.092114719761944e-05, + "loss": 4.117, + "step": 554496 + }, + { + "epoch": 0.01, + "learning_rate": 4.091276125010892e-05, + "loss": 4.1124, + "step": 555008 + }, + { + "epoch": 0.01, + "learning_rate": 4.09043753025984e-05, + "loss": 4.1139, + "step": 555520 + }, + { + "epoch": 0.01, + "learning_rate": 4.089598935508788e-05, + "loss": 4.1296, + "step": 556032 + }, + { + "epoch": 0.01, + "learning_rate": 4.0887619786381095e-05, + "loss": 4.1217, + "step": 556544 + }, + { + "epoch": 0.01, + "learning_rate": 4.0879233838870575e-05, + "loss": 4.1165, + "step": 557056 + }, + { + "epoch": 0.01, + "learning_rate": 4.0870847891360055e-05, + "loss": 4.1354, + "step": 557568 + }, + { + "epoch": 0.01, + "learning_rate": 4.0862478322653264e-05, + "loss": 4.1159, + "step": 558080 + }, + { + "epoch": 0.01, + "learning_rate": 4.0854092375142744e-05, + "loss": 4.1307, + "step": 558592 + }, + { + "epoch": 0.01, + "learning_rate": 4.0845706427632224e-05, + "loss": 4.114, + "step": 559104 + }, + { + "epoch": 0.01, + "learning_rate": 4.0837336858925433e-05, + "loss": 4.1062, + "step": 559616 + }, + { + "epoch": 0.01, + "learning_rate": 4.0828950911414913e-05, + "loss": 4.1169, + "step": 560128 + }, + { + "epoch": 0.01, + "learning_rate": 4.082056496390439e-05, + "loss": 4.1202, + "step": 560640 + }, + { + "epoch": 0.01, + "learning_rate": 4.081217901639387e-05, + "loss": 4.1107, + "step": 561152 + }, + { + "epoch": 0.01, + "learning_rate": 4.080379306888335e-05, + "loss": 4.1247, + "step": 561664 + }, + { + "epoch": 0.01, + "learning_rate": 4.079540712137283e-05, + "loss": 4.1162, + "step": 562176 + }, + { + "epoch": 0.01, + "learning_rate": 4.078702117386231e-05, + "loss": 4.1045, + "step": 562688 + }, + { + "epoch": 0.01, + "learning_rate": 4.077863522635179e-05, + "loss": 4.1161, + "step": 563200 + }, + { + "epoch": 0.01, + "learning_rate": 4.077024927884127e-05, + "loss": 4.104, + "step": 563712 + }, + { + "epoch": 0.01, + "learning_rate": 4.076186333133075e-05, + "loss": 4.1203, + "step": 564224 + }, + { + "epoch": 0.01, + "learning_rate": 4.075349376262397e-05, + "loss": 4.1137, + "step": 564736 + }, + { + "epoch": 0.01, + "learning_rate": 4.074510781511344e-05, + "loss": 4.1112, + "step": 565248 + }, + { + "epoch": 0.01, + "learning_rate": 4.073672186760292e-05, + "loss": 4.1097, + "step": 565760 + }, + { + "epoch": 0.01, + "learning_rate": 4.07283359200924e-05, + "loss": 4.1013, + "step": 566272 + }, + { + "epoch": 0.01, + "learning_rate": 4.071996635138561e-05, + "loss": 4.1239, + "step": 566784 + }, + { + "epoch": 0.01, + "learning_rate": 4.071158040387509e-05, + "loss": 4.1065, + "step": 567296 + }, + { + "epoch": 0.01, + "learning_rate": 4.070319445636457e-05, + "loss": 4.118, + "step": 567808 + }, + { + "epoch": 0.01, + "learning_rate": 4.069480850885405e-05, + "loss": 4.1043, + "step": 568320 + }, + { + "epoch": 0.01, + "learning_rate": 4.068642256134354e-05, + "loss": 4.1104, + "step": 568832 + }, + { + "epoch": 0.01, + "learning_rate": 4.067803661383302e-05, + "loss": 4.1085, + "step": 569344 + }, + { + "epoch": 0.01, + "learning_rate": 4.06696506663225e-05, + "loss": 4.1104, + "step": 569856 + }, + { + "epoch": 0.01, + "learning_rate": 4.066126471881198e-05, + "loss": 4.1143, + "step": 570368 + }, + { + "epoch": 0.01, + "learning_rate": 4.065289515010519e-05, + "loss": 4.1114, + "step": 570880 + }, + { + "epoch": 0.01, + "learning_rate": 4.064450920259467e-05, + "loss": 4.1176, + "step": 571392 + }, + { + "epoch": 0.01, + "learning_rate": 4.0636123255084147e-05, + "loss": 4.1266, + "step": 571904 + }, + { + "epoch": 0.01, + "learning_rate": 4.0627737307573627e-05, + "loss": 4.1268, + "step": 572416 + }, + { + "epoch": 0.01, + "learning_rate": 4.0619351360063106e-05, + "loss": 4.1157, + "step": 572928 + }, + { + "epoch": 0.01, + "learning_rate": 4.0610965412552586e-05, + "loss": 4.1157, + "step": 573440 + }, + { + "epoch": 0.01, + "learning_rate": 4.0602579465042066e-05, + "loss": 4.0978, + "step": 573952 + }, + { + "epoch": 0.01, + "learning_rate": 4.0594209896335276e-05, + "loss": 4.1137, + "step": 574464 + }, + { + "epoch": 0.01, + "learning_rate": 4.0585823948824755e-05, + "loss": 4.1259, + "step": 574976 + }, + { + "epoch": 0.01, + "learning_rate": 4.0577438001314235e-05, + "loss": 4.1185, + "step": 575488 + }, + { + "epoch": 0.01, + "learning_rate": 4.056905205380372e-05, + "loss": 4.1155, + "step": 576000 + }, + { + "epoch": 0.01, + "learning_rate": 4.056068248509693e-05, + "loss": 4.0954, + "step": 576512 + }, + { + "epoch": 0.01, + "learning_rate": 4.055229653758641e-05, + "loss": 4.1194, + "step": 577024 + }, + { + "epoch": 0.01, + "learning_rate": 4.054391059007589e-05, + "loss": 4.0984, + "step": 577536 + }, + { + "epoch": 0.01, + "learning_rate": 4.053552464256537e-05, + "loss": 4.1091, + "step": 578048 + }, + { + "epoch": 0.01, + "learning_rate": 4.052713869505485e-05, + "loss": 4.1077, + "step": 578560 + }, + { + "epoch": 0.01, + "learning_rate": 4.0518752747544324e-05, + "loss": 4.1133, + "step": 579072 + }, + { + "epoch": 0.01, + "learning_rate": 4.0510366800033804e-05, + "loss": 4.1158, + "step": 579584 + }, + { + "epoch": 0.02, + "learning_rate": 4.0501980852523284e-05, + "loss": 4.1173, + "step": 580096 + }, + { + "epoch": 0.02, + "learning_rate": 4.04936112838165e-05, + "loss": 4.0997, + "step": 580608 + }, + { + "epoch": 0.02, + "learning_rate": 4.048522533630597e-05, + "loss": 4.1155, + "step": 581120 + }, + { + "epoch": 0.02, + "learning_rate": 4.047685576759919e-05, + "loss": 4.1084, + "step": 581632 + }, + { + "epoch": 0.02, + "learning_rate": 4.0468469820088676e-05, + "loss": 4.1056, + "step": 582144 + }, + { + "epoch": 0.02, + "learning_rate": 4.0460083872578156e-05, + "loss": 4.0968, + "step": 582656 + }, + { + "epoch": 0.02, + "learning_rate": 4.045169792506763e-05, + "loss": 4.1184, + "step": 583168 + }, + { + "epoch": 0.02, + "learning_rate": 4.044331197755711e-05, + "loss": 4.1134, + "step": 583680 + }, + { + "epoch": 0.02, + "learning_rate": 4.043492603004659e-05, + "loss": 4.1208, + "step": 584192 + }, + { + "epoch": 0.02, + "learning_rate": 4.04265564613398e-05, + "loss": 4.1092, + "step": 584704 + }, + { + "epoch": 0.02, + "learning_rate": 4.041817051382928e-05, + "loss": 4.1128, + "step": 585216 + }, + { + "epoch": 0.02, + "learning_rate": 4.040978456631876e-05, + "loss": 4.0978, + "step": 585728 + }, + { + "epoch": 0.02, + "learning_rate": 4.040139861880824e-05, + "loss": 4.1173, + "step": 586240 + }, + { + "epoch": 0.02, + "learning_rate": 4.039302905010145e-05, + "loss": 4.1139, + "step": 586752 + }, + { + "epoch": 0.02, + "learning_rate": 4.038464310259093e-05, + "loss": 4.1101, + "step": 587264 + }, + { + "epoch": 0.02, + "learning_rate": 4.0376257155080414e-05, + "loss": 4.1123, + "step": 587776 + }, + { + "epoch": 0.02, + "learning_rate": 4.0367871207569894e-05, + "loss": 4.0936, + "step": 588288 + }, + { + "epoch": 0.02, + "learning_rate": 4.0359485260059374e-05, + "loss": 4.0907, + "step": 588800 + }, + { + "epoch": 0.02, + "learning_rate": 4.0351099312548853e-05, + "loss": 4.0955, + "step": 589312 + }, + { + "epoch": 0.02, + "learning_rate": 4.0342713365038333e-05, + "loss": 4.1042, + "step": 589824 + }, + { + "epoch": 0.02, + "learning_rate": 4.033432741752781e-05, + "loss": 4.1173, + "step": 590336 + }, + { + "epoch": 0.02, + "learning_rate": 4.032594147001729e-05, + "loss": 4.1106, + "step": 590848 + }, + { + "epoch": 0.02, + "learning_rate": 4.031755552250677e-05, + "loss": 4.0811, + "step": 591360 + }, + { + "epoch": 0.02, + "learning_rate": 4.030918595379998e-05, + "loss": 4.1085, + "step": 591872 + }, + { + "epoch": 0.02, + "learning_rate": 4.030080000628946e-05, + "loss": 4.1135, + "step": 592384 + }, + { + "epoch": 0.02, + "learning_rate": 4.029241405877894e-05, + "loss": 4.1098, + "step": 592896 + }, + { + "epoch": 0.02, + "learning_rate": 4.028402811126842e-05, + "loss": 4.1109, + "step": 593408 + }, + { + "epoch": 0.02, + "learning_rate": 4.02756421637579e-05, + "loss": 4.1061, + "step": 593920 + }, + { + "epoch": 0.02, + "learning_rate": 4.026725621624738e-05, + "loss": 4.0973, + "step": 594432 + }, + { + "epoch": 0.02, + "learning_rate": 4.025888664754059e-05, + "loss": 4.1116, + "step": 594944 + }, + { + "epoch": 0.02, + "learning_rate": 4.025050070003008e-05, + "loss": 4.1068, + "step": 595456 + }, + { + "epoch": 0.02, + "learning_rate": 4.024211475251956e-05, + "loss": 4.1014, + "step": 595968 + }, + { + "epoch": 0.02, + "learning_rate": 4.023372880500904e-05, + "loss": 4.0942, + "step": 596480 + }, + { + "epoch": 0.02, + "learning_rate": 4.022534285749852e-05, + "loss": 4.0982, + "step": 596992 + }, + { + "epoch": 0.02, + "learning_rate": 4.021695690998799e-05, + "loss": 4.1048, + "step": 597504 + }, + { + "epoch": 0.02, + "learning_rate": 4.020857096247747e-05, + "loss": 4.1052, + "step": 598016 + }, + { + "epoch": 0.02, + "learning_rate": 4.020018501496695e-05, + "loss": 4.1135, + "step": 598528 + }, + { + "epoch": 0.02, + "learning_rate": 4.019181544626016e-05, + "loss": 4.1002, + "step": 599040 + }, + { + "epoch": 0.02, + "learning_rate": 4.018342949874964e-05, + "loss": 4.0959, + "step": 599552 + }, + { + "epoch": 0.02, + "learning_rate": 4.0175059930042856e-05, + "loss": 4.1146, + "step": 600064 + }, + { + "epoch": 0.02, + "learning_rate": 4.0166673982532336e-05, + "loss": 4.0948, + "step": 600576 + }, + { + "epoch": 0.02, + "learning_rate": 4.0158288035021816e-05, + "loss": 4.1111, + "step": 601088 + }, + { + "epoch": 0.02, + "learning_rate": 4.0149902087511296e-05, + "loss": 4.1123, + "step": 601600 + }, + { + "epoch": 0.02, + "learning_rate": 4.014153251880451e-05, + "loss": 4.1092, + "step": 602112 + }, + { + "epoch": 0.02, + "learning_rate": 4.013316295009772e-05, + "loss": 4.1139, + "step": 602624 + }, + { + "epoch": 0.02, + "learning_rate": 4.01247770025872e-05, + "loss": 4.1025, + "step": 603136 + }, + { + "epoch": 0.02, + "learning_rate": 4.011639105507668e-05, + "loss": 4.0933, + "step": 603648 + }, + { + "epoch": 0.02, + "learning_rate": 4.010800510756616e-05, + "loss": 4.0973, + "step": 604160 + }, + { + "epoch": 0.02, + "learning_rate": 4.0099619160055634e-05, + "loss": 4.106, + "step": 604672 + }, + { + "epoch": 0.02, + "learning_rate": 4.0091233212545114e-05, + "loss": 4.1108, + "step": 605184 + }, + { + "epoch": 0.02, + "learning_rate": 4.0082847265034594e-05, + "loss": 4.1101, + "step": 605696 + }, + { + "epoch": 0.02, + "learning_rate": 4.0074461317524074e-05, + "loss": 4.1053, + "step": 606208 + }, + { + "epoch": 0.02, + "learning_rate": 4.0066075370013554e-05, + "loss": 4.099, + "step": 606720 + }, + { + "epoch": 0.02, + "learning_rate": 4.0057689422503034e-05, + "loss": 4.1034, + "step": 607232 + }, + { + "epoch": 0.02, + "learning_rate": 4.0049303474992513e-05, + "loss": 4.089, + "step": 607744 + }, + { + "epoch": 0.02, + "learning_rate": 4.0040917527482e-05, + "loss": 4.103, + "step": 608256 + }, + { + "epoch": 0.02, + "learning_rate": 4.003254795877521e-05, + "loss": 4.1111, + "step": 608768 + }, + { + "epoch": 0.02, + "learning_rate": 4.002417839006842e-05, + "loss": 4.1156, + "step": 609280 + }, + { + "epoch": 0.02, + "learning_rate": 4.00157924425579e-05, + "loss": 4.0885, + "step": 609792 + }, + { + "epoch": 0.02, + "learning_rate": 4.000740649504738e-05, + "loss": 4.1016, + "step": 610304 + }, + { + "epoch": 0.03, + "eval_loss": 4.111624240875244, + "eval_runtime": 536.8692, + "eval_samples_per_second": 710.771, + "eval_steps_per_second": 22.212, + "step": 610552 + }, + { + "epoch": 1.0, + "learning_rate": 3.999902054753686e-05, + "loss": 4.1097, + "step": 610816 + }, + { + "epoch": 1.0, + "learning_rate": 3.999063460002634e-05, + "loss": 4.1067, + "step": 611328 + }, + { + "epoch": 1.0, + "learning_rate": 3.998224865251582e-05, + "loss": 4.0956, + "step": 611840 + }, + { + "epoch": 1.0, + "learning_rate": 3.99738627050053e-05, + "loss": 4.0985, + "step": 612352 + }, + { + "epoch": 1.0, + "learning_rate": 3.996549313629851e-05, + "loss": 4.0892, + "step": 612864 + }, + { + "epoch": 1.0, + "learning_rate": 3.995710718878799e-05, + "loss": 4.0916, + "step": 613376 + }, + { + "epoch": 1.0, + "learning_rate": 3.994872124127747e-05, + "loss": 4.0896, + "step": 613888 + }, + { + "epoch": 1.0, + "learning_rate": 3.9940335293766954e-05, + "loss": 4.0925, + "step": 614400 + }, + { + "epoch": 1.0, + "learning_rate": 3.9931949346256434e-05, + "loss": 4.0916, + "step": 614912 + }, + { + "epoch": 1.0, + "learning_rate": 3.9923563398745914e-05, + "loss": 4.1031, + "step": 615424 + }, + { + "epoch": 1.0, + "learning_rate": 3.991519383003912e-05, + "loss": 4.0972, + "step": 615936 + }, + { + "epoch": 1.0, + "learning_rate": 3.99068078825286e-05, + "loss": 4.0973, + "step": 616448 + }, + { + "epoch": 1.0, + "learning_rate": 3.989842193501808e-05, + "loss": 4.1078, + "step": 616960 + }, + { + "epoch": 1.0, + "learning_rate": 3.989003598750756e-05, + "loss": 4.0902, + "step": 617472 + }, + { + "epoch": 1.0, + "learning_rate": 3.988165003999704e-05, + "loss": 4.1057, + "step": 617984 + }, + { + "epoch": 1.0, + "learning_rate": 3.987326409248652e-05, + "loss": 4.083, + "step": 618496 + }, + { + "epoch": 1.0, + "learning_rate": 3.986489452377973e-05, + "loss": 4.0871, + "step": 619008 + }, + { + "epoch": 1.0, + "learning_rate": 3.985650857626921e-05, + "loss": 4.0981, + "step": 619520 + }, + { + "epoch": 1.0, + "learning_rate": 3.984812262875869e-05, + "loss": 4.0956, + "step": 620032 + }, + { + "epoch": 1.0, + "learning_rate": 3.983973668124817e-05, + "loss": 4.1059, + "step": 620544 + }, + { + "epoch": 1.0, + "learning_rate": 3.983135073373765e-05, + "loss": 4.0965, + "step": 621056 + }, + { + "epoch": 1.0, + "learning_rate": 3.982296478622713e-05, + "loss": 4.099, + "step": 621568 + }, + { + "epoch": 1.0, + "learning_rate": 3.981459521752035e-05, + "loss": 4.1022, + "step": 622080 + }, + { + "epoch": 1.0, + "learning_rate": 3.980620927000982e-05, + "loss": 4.0918, + "step": 622592 + }, + { + "epoch": 1.0, + "learning_rate": 3.97978233224993e-05, + "loss": 4.1019, + "step": 623104 + }, + { + "epoch": 1.0, + "learning_rate": 3.978943737498878e-05, + "loss": 4.0878, + "step": 623616 + }, + { + "epoch": 1.0, + "learning_rate": 3.978105142747826e-05, + "loss": 4.1013, + "step": 624128 + }, + { + "epoch": 1.0, + "learning_rate": 3.977266547996774e-05, + "loss": 4.0883, + "step": 624640 + }, + { + "epoch": 1.0, + "learning_rate": 3.976427953245722e-05, + "loss": 4.1041, + "step": 625152 + }, + { + "epoch": 1.0, + "learning_rate": 3.97558935849467e-05, + "loss": 4.0877, + "step": 625664 + }, + { + "epoch": 1.01, + "learning_rate": 3.974752401623991e-05, + "loss": 4.0863, + "step": 626176 + }, + { + "epoch": 1.01, + "learning_rate": 3.973913806872939e-05, + "loss": 4.098, + "step": 626688 + }, + { + "epoch": 1.01, + "learning_rate": 3.973075212121887e-05, + "loss": 4.0954, + "step": 627200 + }, + { + "epoch": 1.01, + "learning_rate": 3.9722382552512085e-05, + "loss": 4.0999, + "step": 627712 + }, + { + "epoch": 1.01, + "learning_rate": 3.9713996605001565e-05, + "loss": 4.0923, + "step": 628224 + }, + { + "epoch": 1.01, + "learning_rate": 3.9705610657491045e-05, + "loss": 4.0942, + "step": 628736 + }, + { + "epoch": 1.01, + "learning_rate": 3.9697241088784254e-05, + "loss": 4.0954, + "step": 629248 + }, + { + "epoch": 1.01, + "learning_rate": 3.9688855141273734e-05, + "loss": 4.1029, + "step": 629760 + }, + { + "epoch": 1.01, + "learning_rate": 3.9680469193763214e-05, + "loss": 4.0977, + "step": 630272 + }, + { + "epoch": 1.01, + "learning_rate": 3.9672083246252694e-05, + "loss": 4.0833, + "step": 630784 + }, + { + "epoch": 1.01, + "learning_rate": 3.9663697298742174e-05, + "loss": 4.0822, + "step": 631296 + }, + { + "epoch": 1.01, + "learning_rate": 3.9655311351231654e-05, + "loss": 4.081, + "step": 631808 + }, + { + "epoch": 1.01, + "learning_rate": 3.9646925403721134e-05, + "loss": 4.0979, + "step": 632320 + }, + { + "epoch": 1.01, + "learning_rate": 3.9638539456210614e-05, + "loss": 4.0933, + "step": 632832 + }, + { + "epoch": 1.01, + "learning_rate": 3.9630153508700094e-05, + "loss": 4.0817, + "step": 633344 + }, + { + "epoch": 1.01, + "learning_rate": 3.962178393999331e-05, + "loss": 4.1058, + "step": 633856 + }, + { + "epoch": 1.01, + "learning_rate": 3.961341437128652e-05, + "loss": 4.0854, + "step": 634368 + }, + { + "epoch": 1.01, + "learning_rate": 3.9605028423776e-05, + "loss": 4.0983, + "step": 634880 + }, + { + "epoch": 1.01, + "learning_rate": 3.959664247626548e-05, + "loss": 4.0858, + "step": 635392 + }, + { + "epoch": 1.01, + "learning_rate": 3.958825652875496e-05, + "loss": 4.0772, + "step": 635904 + }, + { + "epoch": 1.01, + "learning_rate": 3.957987058124444e-05, + "loss": 4.0853, + "step": 636416 + }, + { + "epoch": 1.01, + "learning_rate": 3.957148463373392e-05, + "loss": 4.0849, + "step": 636928 + }, + { + "epoch": 1.01, + "learning_rate": 3.95630986862234e-05, + "loss": 4.0888, + "step": 637440 + }, + { + "epoch": 1.01, + "learning_rate": 3.955471273871288e-05, + "loss": 4.0875, + "step": 637952 + }, + { + "epoch": 1.01, + "learning_rate": 3.954632679120236e-05, + "loss": 4.088, + "step": 638464 + }, + { + "epoch": 1.01, + "learning_rate": 3.953795722249557e-05, + "loss": 4.0737, + "step": 638976 + }, + { + "epoch": 1.01, + "learning_rate": 3.952957127498505e-05, + "loss": 4.0855, + "step": 639488 + }, + { + "epoch": 1.01, + "learning_rate": 3.952118532747453e-05, + "loss": 4.075, + "step": 640000 + }, + { + "epoch": 1.01, + "learning_rate": 3.951279937996401e-05, + "loss": 4.0886, + "step": 640512 + }, + { + "epoch": 1.01, + "learning_rate": 3.950441343245349e-05, + "loss": 4.0784, + "step": 641024 + }, + { + "epoch": 1.01, + "learning_rate": 3.949602748494297e-05, + "loss": 4.0854, + "step": 641536 + }, + { + "epoch": 1.01, + "learning_rate": 3.948764153743245e-05, + "loss": 4.0814, + "step": 642048 + }, + { + "epoch": 1.01, + "learning_rate": 3.947925558992193e-05, + "loss": 4.0716, + "step": 642560 + }, + { + "epoch": 1.01, + "learning_rate": 3.9470886021215136e-05, + "loss": 4.0916, + "step": 643072 + }, + { + "epoch": 1.01, + "learning_rate": 3.9462500073704616e-05, + "loss": 4.0775, + "step": 643584 + }, + { + "epoch": 1.01, + "learning_rate": 3.9454114126194096e-05, + "loss": 4.0878, + "step": 644096 + }, + { + "epoch": 1.01, + "learning_rate": 3.9445728178683576e-05, + "loss": 4.0783, + "step": 644608 + }, + { + "epoch": 1.01, + "learning_rate": 3.9437358609976785e-05, + "loss": 4.0777, + "step": 645120 + }, + { + "epoch": 1.01, + "learning_rate": 3.9428972662466265e-05, + "loss": 4.0771, + "step": 645632 + }, + { + "epoch": 1.01, + "learning_rate": 3.9420586714955745e-05, + "loss": 4.0793, + "step": 646144 + }, + { + "epoch": 1.01, + "learning_rate": 3.941221714624896e-05, + "loss": 4.0842, + "step": 646656 + }, + { + "epoch": 1.01, + "learning_rate": 3.940383119873844e-05, + "loss": 4.0844, + "step": 647168 + }, + { + "epoch": 1.01, + "learning_rate": 3.939544525122792e-05, + "loss": 4.0853, + "step": 647680 + }, + { + "epoch": 1.01, + "learning_rate": 3.93870593037174e-05, + "loss": 4.1028, + "step": 648192 + }, + { + "epoch": 1.01, + "learning_rate": 3.937867335620688e-05, + "loss": 4.0935, + "step": 648704 + }, + { + "epoch": 1.01, + "learning_rate": 3.937028740869636e-05, + "loss": 4.0824, + "step": 649216 + }, + { + "epoch": 1.01, + "learning_rate": 3.936190146118584e-05, + "loss": 4.0855, + "step": 649728 + }, + { + "epoch": 1.01, + "learning_rate": 3.935353189247905e-05, + "loss": 4.0711, + "step": 650240 + }, + { + "epoch": 1.01, + "learning_rate": 3.934514594496853e-05, + "loss": 4.0804, + "step": 650752 + }, + { + "epoch": 1.01, + "learning_rate": 3.933675999745801e-05, + "loss": 4.0943, + "step": 651264 + }, + { + "epoch": 1.01, + "learning_rate": 3.932839042875122e-05, + "loss": 4.0927, + "step": 651776 + }, + { + "epoch": 1.01, + "learning_rate": 3.93200044812407e-05, + "loss": 4.083, + "step": 652288 + }, + { + "epoch": 1.01, + "learning_rate": 3.9311618533730186e-05, + "loss": 4.0682, + "step": 652800 + }, + { + "epoch": 1.01, + "learning_rate": 3.9303232586219666e-05, + "loss": 4.0874, + "step": 653312 + }, + { + "epoch": 1.01, + "learning_rate": 3.9294846638709146e-05, + "loss": 4.0651, + "step": 653824 + }, + { + "epoch": 1.01, + "learning_rate": 3.9286477070002355e-05, + "loss": 4.0812, + "step": 654336 + }, + { + "epoch": 1.01, + "learning_rate": 3.9278091122491835e-05, + "loss": 4.0807, + "step": 654848 + }, + { + "epoch": 1.01, + "learning_rate": 3.9269705174981315e-05, + "loss": 4.0804, + "step": 655360 + }, + { + "epoch": 1.01, + "learning_rate": 3.9261319227470795e-05, + "loss": 4.0896, + "step": 655872 + }, + { + "epoch": 1.02, + "learning_rate": 3.9252933279960274e-05, + "loss": 4.0889, + "step": 656384 + }, + { + "epoch": 1.02, + "learning_rate": 3.9244547332449754e-05, + "loss": 4.073, + "step": 656896 + }, + { + "epoch": 1.02, + "learning_rate": 3.9236161384939234e-05, + "loss": 4.0792, + "step": 657408 + }, + { + "epoch": 1.02, + "learning_rate": 3.9227775437428714e-05, + "loss": 4.0816, + "step": 657920 + }, + { + "epoch": 1.02, + "learning_rate": 3.9219405868721923e-05, + "loss": 4.0748, + "step": 658432 + }, + { + "epoch": 1.02, + "learning_rate": 3.9211019921211403e-05, + "loss": 4.0719, + "step": 658944 + }, + { + "epoch": 1.02, + "learning_rate": 3.920263397370088e-05, + "loss": 4.0848, + "step": 659456 + }, + { + "epoch": 1.02, + "learning_rate": 3.919424802619036e-05, + "loss": 4.0871, + "step": 659968 + }, + { + "epoch": 1.02, + "learning_rate": 3.918587845748358e-05, + "loss": 4.0957, + "step": 660480 + }, + { + "epoch": 1.02, + "learning_rate": 3.917749250997306e-05, + "loss": 4.0752, + "step": 660992 + }, + { + "epoch": 1.02, + "learning_rate": 3.916910656246254e-05, + "loss": 4.0836, + "step": 661504 + }, + { + "epoch": 1.02, + "learning_rate": 3.916072061495202e-05, + "loss": 4.0743, + "step": 662016 + }, + { + "epoch": 1.02, + "learning_rate": 3.915235104624523e-05, + "loss": 4.0827, + "step": 662528 + }, + { + "epoch": 1.02, + "learning_rate": 3.914396509873471e-05, + "loss": 4.0896, + "step": 663040 + }, + { + "epoch": 1.02, + "learning_rate": 3.913557915122419e-05, + "loss": 4.0822, + "step": 663552 + }, + { + "epoch": 1.02, + "learning_rate": 3.912719320371367e-05, + "loss": 4.0862, + "step": 664064 + }, + { + "epoch": 1.02, + "learning_rate": 3.911880725620314e-05, + "loss": 4.062, + "step": 664576 + }, + { + "epoch": 1.02, + "learning_rate": 3.911043768749636e-05, + "loss": 4.0655, + "step": 665088 + }, + { + "epoch": 1.02, + "learning_rate": 3.910205173998584e-05, + "loss": 4.069, + "step": 665600 + }, + { + "epoch": 1.02, + "learning_rate": 3.909366579247532e-05, + "loss": 4.0765, + "step": 666112 + }, + { + "epoch": 1.02, + "learning_rate": 3.90852798449648e-05, + "loss": 4.0827, + "step": 666624 + }, + { + "epoch": 1.02, + "learning_rate": 3.907689389745428e-05, + "loss": 4.0845, + "step": 667136 + }, + { + "epoch": 1.02, + "learning_rate": 3.906852432874749e-05, + "loss": 4.055, + "step": 667648 + }, + { + "epoch": 1.02, + "learning_rate": 3.9060138381236966e-05, + "loss": 4.0799, + "step": 668160 + }, + { + "epoch": 1.02, + "learning_rate": 3.905176881253018e-05, + "loss": 4.0863, + "step": 668672 + }, + { + "epoch": 1.02, + "learning_rate": 3.904338286501966e-05, + "loss": 4.0797, + "step": 669184 + }, + { + "epoch": 1.02, + "learning_rate": 3.903499691750914e-05, + "loss": 4.0829, + "step": 669696 + }, + { + "epoch": 1.02, + "learning_rate": 3.9026610969998615e-05, + "loss": 4.0808, + "step": 670208 + }, + { + "epoch": 1.02, + "learning_rate": 3.9018225022488095e-05, + "loss": 4.0671, + "step": 670720 + }, + { + "epoch": 1.02, + "learning_rate": 3.9009839074977575e-05, + "loss": 4.0833, + "step": 671232 + }, + { + "epoch": 1.02, + "learning_rate": 3.900146950627079e-05, + "loss": 4.0862, + "step": 671744 + }, + { + "epoch": 1.02, + "learning_rate": 3.899308355876027e-05, + "loss": 4.0699, + "step": 672256 + }, + { + "epoch": 1.02, + "learning_rate": 3.898469761124975e-05, + "loss": 4.0687, + "step": 672768 + }, + { + "epoch": 1.02, + "learning_rate": 3.897631166373923e-05, + "loss": 4.0708, + "step": 673280 + }, + { + "epoch": 1.02, + "learning_rate": 3.896792571622871e-05, + "loss": 4.0758, + "step": 673792 + }, + { + "epoch": 1.02, + "learning_rate": 3.895953976871819e-05, + "loss": 4.0749, + "step": 674304 + }, + { + "epoch": 1.02, + "learning_rate": 3.895115382120767e-05, + "loss": 4.0833, + "step": 674816 + }, + { + "epoch": 1.02, + "learning_rate": 3.894276787369715e-05, + "loss": 4.075, + "step": 675328 + }, + { + "epoch": 1.02, + "learning_rate": 3.893439830499036e-05, + "loss": 4.0652, + "step": 675840 + }, + { + "epoch": 1.02, + "learning_rate": 3.892601235747984e-05, + "loss": 4.0879, + "step": 676352 + }, + { + "epoch": 1.02, + "learning_rate": 3.891762640996932e-05, + "loss": 4.0664, + "step": 676864 + }, + { + "epoch": 1.02, + "learning_rate": 3.89092404624588e-05, + "loss": 4.0822, + "step": 677376 + }, + { + "epoch": 1.02, + "learning_rate": 3.890085451494828e-05, + "loss": 4.0867, + "step": 677888 + }, + { + "epoch": 1.02, + "learning_rate": 3.8892484946241495e-05, + "loss": 4.0832, + "step": 678400 + }, + { + "epoch": 1.02, + "learning_rate": 3.8884098998730975e-05, + "loss": 4.0862, + "step": 678912 + }, + { + "epoch": 1.02, + "learning_rate": 3.8875713051220455e-05, + "loss": 4.0757, + "step": 679424 + }, + { + "epoch": 1.02, + "learning_rate": 3.8867327103709935e-05, + "loss": 4.0651, + "step": 679936 + }, + { + "epoch": 1.02, + "learning_rate": 3.8858941156199415e-05, + "loss": 4.0711, + "step": 680448 + }, + { + "epoch": 1.02, + "learning_rate": 3.8850571587492624e-05, + "loss": 4.0735, + "step": 680960 + }, + { + "epoch": 1.02, + "learning_rate": 3.8842185639982104e-05, + "loss": 4.0878, + "step": 681472 + }, + { + "epoch": 1.02, + "learning_rate": 3.8833799692471584e-05, + "loss": 4.0806, + "step": 681984 + }, + { + "epoch": 1.02, + "learning_rate": 3.8825413744961064e-05, + "loss": 4.0757, + "step": 682496 + }, + { + "epoch": 1.02, + "learning_rate": 3.881704417625427e-05, + "loss": 4.0774, + "step": 683008 + }, + { + "epoch": 1.02, + "learning_rate": 3.880867460754748e-05, + "loss": 4.0722, + "step": 683520 + }, + { + "epoch": 1.02, + "learning_rate": 3.880028866003696e-05, + "loss": 4.0613, + "step": 684032 + }, + { + "epoch": 1.02, + "learning_rate": 3.879190271252645e-05, + "loss": 4.0758, + "step": 684544 + }, + { + "epoch": 1.02, + "learning_rate": 3.878351676501593e-05, + "loss": 4.0846, + "step": 685056 + }, + { + "epoch": 1.02, + "learning_rate": 3.877513081750541e-05, + "loss": 4.09, + "step": 685568 + }, + { + "epoch": 1.02, + "learning_rate": 3.876674486999489e-05, + "loss": 4.0665, + "step": 686080 + }, + { + "epoch": 1.02, + "learning_rate": 3.87583753012881e-05, + "loss": 4.0704, + "step": 686592 + }, + { + "epoch": 1.03, + "eval_loss": 4.091535568237305, + "eval_runtime": 535.9783, + "eval_samples_per_second": 711.952, + "eval_steps_per_second": 22.249, + "step": 686871 + }, + { + "epoch": 0.0, + "learning_rate": 3.874998935377758e-05, + "loss": 4.0927, + "step": 687104 + }, + { + "epoch": 0.0, + "learning_rate": 3.874160340626706e-05, + "loss": 4.0788, + "step": 687616 + }, + { + "epoch": 0.0, + "learning_rate": 3.873321745875654e-05, + "loss": 4.0732, + "step": 688128 + }, + { + "epoch": 0.0, + "learning_rate": 3.872483151124602e-05, + "loss": 4.0704, + "step": 688640 + }, + { + "epoch": 0.0, + "learning_rate": 3.87164455637355e-05, + "loss": 4.0668, + "step": 689152 + }, + { + "epoch": 0.0, + "learning_rate": 3.870805961622497e-05, + "loss": 4.0623, + "step": 689664 + }, + { + "epoch": 0.0, + "learning_rate": 3.869967366871445e-05, + "loss": 4.0624, + "step": 690176 + }, + { + "epoch": 0.0, + "learning_rate": 3.869128772120393e-05, + "loss": 4.0661, + "step": 690688 + }, + { + "epoch": 0.0, + "learning_rate": 3.868290177369342e-05, + "loss": 4.0645, + "step": 691200 + }, + { + "epoch": 0.0, + "learning_rate": 3.86745158261829e-05, + "loss": 4.0781, + "step": 691712 + }, + { + "epoch": 0.0, + "learning_rate": 3.866612987867238e-05, + "loss": 4.0697, + "step": 692224 + }, + { + "epoch": 0.0, + "learning_rate": 3.865774393116186e-05, + "loss": 4.0719, + "step": 692736 + }, + { + "epoch": 0.0, + "learning_rate": 3.864935798365134e-05, + "loss": 4.0824, + "step": 693248 + }, + { + "epoch": 0.0, + "learning_rate": 3.864097203614082e-05, + "loss": 4.0659, + "step": 693760 + }, + { + "epoch": 0.0, + "learning_rate": 3.86325860886303e-05, + "loss": 4.0762, + "step": 694272 + }, + { + "epoch": 0.0, + "learning_rate": 3.862420014111978e-05, + "loss": 4.0567, + "step": 694784 + }, + { + "epoch": 0.0, + "learning_rate": 3.861581419360926e-05, + "loss": 4.0599, + "step": 695296 + }, + { + "epoch": 0.0, + "learning_rate": 3.860742824609874e-05, + "loss": 4.0741, + "step": 695808 + }, + { + "epoch": 0.0, + "learning_rate": 3.859904229858822e-05, + "loss": 4.069, + "step": 696320 + }, + { + "epoch": 0.0, + "learning_rate": 3.859065635107769e-05, + "loss": 4.0823, + "step": 696832 + }, + { + "epoch": 0.0, + "learning_rate": 3.8582303161174635e-05, + "loss": 4.0653, + "step": 697344 + }, + { + "epoch": 0.0, + "learning_rate": 3.8573917213664115e-05, + "loss": 4.0809, + "step": 697856 + }, + { + "epoch": 0.0, + "learning_rate": 3.8565531266153595e-05, + "loss": 4.0677, + "step": 698368 + }, + { + "epoch": 0.0, + "learning_rate": 3.855714531864308e-05, + "loss": 4.0662, + "step": 698880 + }, + { + "epoch": 0.0, + "learning_rate": 3.854875937113256e-05, + "loss": 4.0728, + "step": 699392 + }, + { + "epoch": 0.0, + "learning_rate": 3.854037342362204e-05, + "loss": 4.0667, + "step": 699904 + }, + { + "epoch": 0.0, + "learning_rate": 3.8531987476111515e-05, + "loss": 4.0738, + "step": 700416 + }, + { + "epoch": 0.0, + "learning_rate": 3.8523601528600995e-05, + "loss": 4.062, + "step": 700928 + }, + { + "epoch": 0.0, + "learning_rate": 3.851523195989421e-05, + "loss": 4.079, + "step": 701440 + }, + { + "epoch": 0.0, + "learning_rate": 3.850686239118742e-05, + "loss": 4.0625, + "step": 701952 + }, + { + "epoch": 0.01, + "learning_rate": 3.84984764436769e-05, + "loss": 4.055, + "step": 702464 + }, + { + "epoch": 0.01, + "learning_rate": 3.849009049616638e-05, + "loss": 4.0748, + "step": 702976 + }, + { + "epoch": 0.01, + "learning_rate": 3.848170454865586e-05, + "loss": 4.0681, + "step": 703488 + }, + { + "epoch": 0.01, + "learning_rate": 3.847331860114533e-05, + "loss": 4.0741, + "step": 704000 + }, + { + "epoch": 0.01, + "learning_rate": 3.846494903243855e-05, + "loss": 4.0674, + "step": 704512 + }, + { + "epoch": 0.01, + "learning_rate": 3.8456563084928035e-05, + "loss": 4.0653, + "step": 705024 + }, + { + "epoch": 0.01, + "learning_rate": 3.8448193516221245e-05, + "loss": 4.0714, + "step": 705536 + }, + { + "epoch": 0.01, + "learning_rate": 3.8439807568710724e-05, + "loss": 4.0739, + "step": 706048 + }, + { + "epoch": 0.01, + "learning_rate": 3.8431421621200204e-05, + "loss": 4.077, + "step": 706560 + }, + { + "epoch": 0.01, + "learning_rate": 3.8423035673689684e-05, + "loss": 4.0566, + "step": 707072 + }, + { + "epoch": 0.01, + "learning_rate": 3.8414649726179164e-05, + "loss": 4.0621, + "step": 707584 + }, + { + "epoch": 0.01, + "learning_rate": 3.840626377866864e-05, + "loss": 4.058, + "step": 708096 + }, + { + "epoch": 0.01, + "learning_rate": 3.839787783115812e-05, + "loss": 4.0645, + "step": 708608 + }, + { + "epoch": 0.01, + "learning_rate": 3.83894918836476e-05, + "loss": 4.0724, + "step": 709120 + }, + { + "epoch": 0.01, + "learning_rate": 3.838110593613708e-05, + "loss": 4.0571, + "step": 709632 + }, + { + "epoch": 0.01, + "learning_rate": 3.837271998862656e-05, + "loss": 4.0786, + "step": 710144 + }, + { + "epoch": 0.01, + "learning_rate": 3.836433404111604e-05, + "loss": 4.0595, + "step": 710656 + }, + { + "epoch": 0.01, + "learning_rate": 3.835596447240925e-05, + "loss": 4.0758, + "step": 711168 + }, + { + "epoch": 0.01, + "learning_rate": 3.834757852489873e-05, + "loss": 4.0628, + "step": 711680 + }, + { + "epoch": 0.01, + "learning_rate": 3.833919257738821e-05, + "loss": 4.0538, + "step": 712192 + }, + { + "epoch": 0.01, + "learning_rate": 3.833080662987769e-05, + "loss": 4.0632, + "step": 712704 + }, + { + "epoch": 0.01, + "learning_rate": 3.83224370611709e-05, + "loss": 4.0547, + "step": 713216 + }, + { + "epoch": 0.01, + "learning_rate": 3.831405111366038e-05, + "loss": 4.0664, + "step": 713728 + }, + { + "epoch": 0.01, + "learning_rate": 3.830566516614986e-05, + "loss": 4.0589, + "step": 714240 + }, + { + "epoch": 0.01, + "learning_rate": 3.829727921863934e-05, + "loss": 4.066, + "step": 714752 + }, + { + "epoch": 0.01, + "learning_rate": 3.828889327112882e-05, + "loss": 4.0454, + "step": 715264 + }, + { + "epoch": 0.01, + "learning_rate": 3.828052370242203e-05, + "loss": 4.0619, + "step": 715776 + }, + { + "epoch": 0.01, + "learning_rate": 3.827213775491151e-05, + "loss": 4.0477, + "step": 716288 + }, + { + "epoch": 0.01, + "learning_rate": 3.826375180740099e-05, + "loss": 4.0673, + "step": 716800 + }, + { + "epoch": 0.01, + "learning_rate": 3.825536585989047e-05, + "loss": 4.0537, + "step": 717312 + }, + { + "epoch": 0.01, + "learning_rate": 3.824697991237996e-05, + "loss": 4.0596, + "step": 717824 + }, + { + "epoch": 0.01, + "learning_rate": 3.823859396486944e-05, + "loss": 4.0547, + "step": 718336 + }, + { + "epoch": 0.01, + "learning_rate": 3.823020801735892e-05, + "loss": 4.0469, + "step": 718848 + }, + { + "epoch": 0.01, + "learning_rate": 3.82218220698484e-05, + "loss": 4.0637, + "step": 719360 + }, + { + "epoch": 0.01, + "learning_rate": 3.821345250114161e-05, + "loss": 4.0548, + "step": 719872 + }, + { + "epoch": 0.01, + "learning_rate": 3.8205066553631087e-05, + "loss": 4.0671, + "step": 720384 + }, + { + "epoch": 0.01, + "learning_rate": 3.8196696984924296e-05, + "loss": 4.0481, + "step": 720896 + }, + { + "epoch": 0.01, + "learning_rate": 3.8188311037413776e-05, + "loss": 4.0558, + "step": 721408 + }, + { + "epoch": 0.01, + "learning_rate": 3.8179925089903256e-05, + "loss": 4.052, + "step": 721920 + }, + { + "epoch": 0.01, + "learning_rate": 3.8171539142392736e-05, + "loss": 4.0575, + "step": 722432 + }, + { + "epoch": 0.01, + "learning_rate": 3.8163153194882216e-05, + "loss": 4.0561, + "step": 722944 + }, + { + "epoch": 0.01, + "learning_rate": 3.8154767247371695e-05, + "loss": 4.0609, + "step": 723456 + }, + { + "epoch": 0.01, + "learning_rate": 3.8146381299861175e-05, + "loss": 4.0605, + "step": 723968 + }, + { + "epoch": 0.01, + "learning_rate": 3.8137995352350655e-05, + "loss": 4.079, + "step": 724480 + }, + { + "epoch": 0.01, + "learning_rate": 3.812962578364387e-05, + "loss": 4.0676, + "step": 724992 + }, + { + "epoch": 0.01, + "learning_rate": 3.812123983613335e-05, + "loss": 4.0628, + "step": 725504 + }, + { + "epoch": 0.01, + "learning_rate": 3.8112853888622824e-05, + "loss": 4.0616, + "step": 726016 + }, + { + "epoch": 0.01, + "learning_rate": 3.8104467941112304e-05, + "loss": 4.0495, + "step": 726528 + }, + { + "epoch": 0.01, + "learning_rate": 3.809609837240552e-05, + "loss": 4.0529, + "step": 727040 + }, + { + "epoch": 0.01, + "learning_rate": 3.8087712424894993e-05, + "loss": 4.0669, + "step": 727552 + }, + { + "epoch": 0.01, + "learning_rate": 3.807932647738447e-05, + "loss": 4.0715, + "step": 728064 + }, + { + "epoch": 0.01, + "learning_rate": 3.807094052987395e-05, + "loss": 4.0621, + "step": 728576 + }, + { + "epoch": 0.01, + "learning_rate": 3.806255458236343e-05, + "loss": 4.044, + "step": 729088 + }, + { + "epoch": 0.01, + "learning_rate": 3.805418501365665e-05, + "loss": 4.0581, + "step": 729600 + }, + { + "epoch": 0.01, + "learning_rate": 3.804579906614613e-05, + "loss": 4.0434, + "step": 730112 + }, + { + "epoch": 0.01, + "learning_rate": 3.803741311863561e-05, + "loss": 4.055, + "step": 730624 + }, + { + "epoch": 0.01, + "learning_rate": 3.802902717112509e-05, + "loss": 4.0567, + "step": 731136 + }, + { + "epoch": 0.01, + "learning_rate": 3.802064122361457e-05, + "loss": 4.0556, + "step": 731648 + }, + { + "epoch": 0.01, + "learning_rate": 3.801225527610405e-05, + "loss": 4.0636, + "step": 732160 + }, + { + "epoch": 0.02, + "learning_rate": 3.800386932859353e-05, + "loss": 4.0611, + "step": 732672 + }, + { + "epoch": 0.02, + "learning_rate": 3.799548338108301e-05, + "loss": 4.051, + "step": 733184 + }, + { + "epoch": 0.02, + "learning_rate": 3.798711381237622e-05, + "loss": 4.0565, + "step": 733696 + }, + { + "epoch": 0.02, + "learning_rate": 3.79787278648657e-05, + "loss": 4.0591, + "step": 734208 + }, + { + "epoch": 0.02, + "learning_rate": 3.797034191735518e-05, + "loss": 4.0474, + "step": 734720 + }, + { + "epoch": 0.02, + "learning_rate": 3.796195596984466e-05, + "loss": 4.0496, + "step": 735232 + }, + { + "epoch": 0.02, + "learning_rate": 3.795358640113787e-05, + "loss": 4.0603, + "step": 735744 + }, + { + "epoch": 0.02, + "learning_rate": 3.794521683243108e-05, + "loss": 4.0631, + "step": 736256 + }, + { + "epoch": 0.02, + "learning_rate": 3.793683088492056e-05, + "loss": 4.0692, + "step": 736768 + }, + { + "epoch": 0.02, + "learning_rate": 3.792844493741004e-05, + "loss": 4.0497, + "step": 737280 + }, + { + "epoch": 0.02, + "learning_rate": 3.792005898989952e-05, + "loss": 4.064, + "step": 737792 + }, + { + "epoch": 0.02, + "learning_rate": 3.7911673042389e-05, + "loss": 4.0512, + "step": 738304 + }, + { + "epoch": 0.02, + "learning_rate": 3.790328709487848e-05, + "loss": 4.0599, + "step": 738816 + }, + { + "epoch": 0.02, + "learning_rate": 3.789490114736796e-05, + "loss": 4.0592, + "step": 739328 + }, + { + "epoch": 0.02, + "learning_rate": 3.788651519985744e-05, + "loss": 4.0592, + "step": 739840 + }, + { + "epoch": 0.02, + "learning_rate": 3.787812925234692e-05, + "loss": 4.0641, + "step": 740352 + }, + { + "epoch": 0.02, + "learning_rate": 3.786975968364013e-05, + "loss": 4.0396, + "step": 740864 + }, + { + "epoch": 0.02, + "learning_rate": 3.786139011493334e-05, + "loss": 4.0434, + "step": 741376 + }, + { + "epoch": 0.02, + "learning_rate": 3.785300416742282e-05, + "loss": 4.043, + "step": 741888 + }, + { + "epoch": 0.02, + "learning_rate": 3.78446182199123e-05, + "loss": 4.0489, + "step": 742400 + }, + { + "epoch": 0.02, + "learning_rate": 3.783623227240178e-05, + "loss": 4.0584, + "step": 742912 + }, + { + "epoch": 0.02, + "learning_rate": 3.7827862703694996e-05, + "loss": 4.0583, + "step": 743424 + }, + { + "epoch": 0.02, + "learning_rate": 3.7819476756184476e-05, + "loss": 4.0367, + "step": 743936 + }, + { + "epoch": 0.02, + "learning_rate": 3.7811090808673956e-05, + "loss": 4.0536, + "step": 744448 + }, + { + "epoch": 0.02, + "learning_rate": 3.7802704861163436e-05, + "loss": 4.0628, + "step": 744960 + }, + { + "epoch": 0.02, + "learning_rate": 3.7794318913652916e-05, + "loss": 4.0581, + "step": 745472 + }, + { + "epoch": 0.02, + "learning_rate": 3.7785949344946125e-05, + "loss": 4.0605, + "step": 745984 + }, + { + "epoch": 0.02, + "learning_rate": 3.7777563397435605e-05, + "loss": 4.0543, + "step": 746496 + }, + { + "epoch": 0.02, + "learning_rate": 3.7769177449925085e-05, + "loss": 4.0466, + "step": 747008 + }, + { + "epoch": 0.02, + "learning_rate": 3.7760807881218294e-05, + "loss": 4.0548, + "step": 747520 + }, + { + "epoch": 0.02, + "learning_rate": 3.7752421933707774e-05, + "loss": 4.062, + "step": 748032 + }, + { + "epoch": 0.02, + "learning_rate": 3.7744035986197254e-05, + "loss": 4.0523, + "step": 748544 + }, + { + "epoch": 0.02, + "learning_rate": 3.7735650038686734e-05, + "loss": 4.0402, + "step": 749056 + }, + { + "epoch": 0.02, + "learning_rate": 3.772726409117622e-05, + "loss": 4.0498, + "step": 749568 + }, + { + "epoch": 0.02, + "learning_rate": 3.77188781436657e-05, + "loss": 4.0492, + "step": 750080 + }, + { + "epoch": 0.02, + "learning_rate": 3.771049219615518e-05, + "loss": 4.0571, + "step": 750592 + }, + { + "epoch": 0.02, + "learning_rate": 3.770210624864466e-05, + "loss": 4.0536, + "step": 751104 + }, + { + "epoch": 0.02, + "learning_rate": 3.7693720301134134e-05, + "loss": 4.0586, + "step": 751616 + }, + { + "epoch": 0.02, + "learning_rate": 3.768535073242735e-05, + "loss": 4.0427, + "step": 752128 + }, + { + "epoch": 0.02, + "learning_rate": 3.767696478491683e-05, + "loss": 4.063, + "step": 752640 + }, + { + "epoch": 0.02, + "learning_rate": 3.766859521621004e-05, + "loss": 4.0468, + "step": 753152 + }, + { + "epoch": 0.02, + "learning_rate": 3.766020926869952e-05, + "loss": 4.0584, + "step": 753664 + }, + { + "epoch": 0.02, + "learning_rate": 3.7651823321189e-05, + "loss": 4.0628, + "step": 754176 + }, + { + "epoch": 0.02, + "learning_rate": 3.764343737367848e-05, + "loss": 4.0579, + "step": 754688 + }, + { + "epoch": 0.02, + "learning_rate": 3.763506780497169e-05, + "loss": 4.0627, + "step": 755200 + }, + { + "epoch": 0.02, + "learning_rate": 3.7626681857461175e-05, + "loss": 4.0562, + "step": 755712 + }, + { + "epoch": 0.02, + "learning_rate": 3.7618295909950654e-05, + "loss": 4.0415, + "step": 756224 + }, + { + "epoch": 0.02, + "learning_rate": 3.760990996244013e-05, + "loss": 4.0486, + "step": 756736 + }, + { + "epoch": 0.02, + "learning_rate": 3.760152401492961e-05, + "loss": 4.0458, + "step": 757248 + }, + { + "epoch": 0.02, + "learning_rate": 3.759313806741909e-05, + "loss": 4.0651, + "step": 757760 + }, + { + "epoch": 0.02, + "learning_rate": 3.758475211990857e-05, + "loss": 4.059, + "step": 758272 + }, + { + "epoch": 0.02, + "learning_rate": 3.757636617239805e-05, + "loss": 4.0544, + "step": 758784 + }, + { + "epoch": 0.02, + "learning_rate": 3.756798022488753e-05, + "loss": 4.0567, + "step": 759296 + }, + { + "epoch": 0.02, + "learning_rate": 3.755959427737701e-05, + "loss": 4.0483, + "step": 759808 + }, + { + "epoch": 0.02, + "learning_rate": 3.7551224708670216e-05, + "loss": 4.0359, + "step": 760320 + }, + { + "epoch": 0.02, + "learning_rate": 3.7542838761159696e-05, + "loss": 4.0531, + "step": 760832 + }, + { + "epoch": 0.02, + "learning_rate": 3.7534452813649176e-05, + "loss": 4.064, + "step": 761344 + }, + { + "epoch": 0.02, + "learning_rate": 3.7526066866138656e-05, + "loss": 4.0634, + "step": 761856 + }, + { + "epoch": 0.02, + "learning_rate": 3.751768091862814e-05, + "loss": 4.0418, + "step": 762368 + }, + { + "epoch": 0.02, + "learning_rate": 3.750929497111762e-05, + "loss": 4.0474, + "step": 762880 + }, + { + "epoch": 0.03, + "eval_loss": 4.075624465942383, + "eval_runtime": 556.5679, + "eval_samples_per_second": 685.614, + "eval_steps_per_second": 21.426, + "step": 763190 + }, + { + "epoch": 1.0, + "learning_rate": 3.75009090236071e-05, + "loss": 4.0641, + "step": 763392 + }, + { + "epoch": 1.0, + "learning_rate": 3.749252307609658e-05, + "loss": 4.051, + "step": 763904 + }, + { + "epoch": 1.0, + "learning_rate": 3.748416988619352e-05, + "loss": 4.0522, + "step": 764416 + }, + { + "epoch": 1.0, + "learning_rate": 3.7475783938683e-05, + "loss": 4.0438, + "step": 764928 + }, + { + "epoch": 1.0, + "learning_rate": 3.746739799117248e-05, + "loss": 4.0509, + "step": 765440 + }, + { + "epoch": 1.0, + "learning_rate": 3.745901204366196e-05, + "loss": 4.0381, + "step": 765952 + }, + { + "epoch": 1.0, + "learning_rate": 3.745062609615144e-05, + "loss": 4.0415, + "step": 766464 + }, + { + "epoch": 1.0, + "learning_rate": 3.744224014864092e-05, + "loss": 4.0403, + "step": 766976 + }, + { + "epoch": 1.0, + "learning_rate": 3.74338542011304e-05, + "loss": 4.0441, + "step": 767488 + }, + { + "epoch": 1.0, + "learning_rate": 3.742546825361988e-05, + "loss": 4.0526, + "step": 768000 + }, + { + "epoch": 1.0, + "learning_rate": 3.741709868491309e-05, + "loss": 4.0513, + "step": 768512 + }, + { + "epoch": 1.0, + "learning_rate": 3.740871273740258e-05, + "loss": 4.0503, + "step": 769024 + }, + { + "epoch": 1.0, + "learning_rate": 3.740032678989206e-05, + "loss": 4.0568, + "step": 769536 + }, + { + "epoch": 1.0, + "learning_rate": 3.739194084238154e-05, + "loss": 4.0436, + "step": 770048 + }, + { + "epoch": 1.0, + "learning_rate": 3.7383554894871017e-05, + "loss": 4.0555, + "step": 770560 + }, + { + "epoch": 1.0, + "learning_rate": 3.737516894736049e-05, + "loss": 4.034, + "step": 771072 + }, + { + "epoch": 1.0, + "learning_rate": 3.736678299984997e-05, + "loss": 4.0344, + "step": 771584 + }, + { + "epoch": 1.0, + "learning_rate": 3.735839705233945e-05, + "loss": 4.0556, + "step": 772096 + }, + { + "epoch": 1.0, + "learning_rate": 3.7350027483632666e-05, + "loss": 4.0457, + "step": 772608 + }, + { + "epoch": 1.0, + "learning_rate": 3.7341657914925875e-05, + "loss": 4.0595, + "step": 773120 + }, + { + "epoch": 1.0, + "learning_rate": 3.7333271967415355e-05, + "loss": 4.0399, + "step": 773632 + }, + { + "epoch": 1.0, + "learning_rate": 3.7324886019904835e-05, + "loss": 4.0626, + "step": 774144 + }, + { + "epoch": 1.0, + "learning_rate": 3.7316500072394315e-05, + "loss": 4.048, + "step": 774656 + }, + { + "epoch": 1.0, + "learning_rate": 3.7308114124883794e-05, + "loss": 4.0453, + "step": 775168 + }, + { + "epoch": 1.0, + "learning_rate": 3.729974455617701e-05, + "loss": 4.0492, + "step": 775680 + }, + { + "epoch": 1.0, + "learning_rate": 3.729137498747022e-05, + "loss": 4.0458, + "step": 776192 + }, + { + "epoch": 1.0, + "learning_rate": 3.72829890399597e-05, + "loss": 4.0541, + "step": 776704 + }, + { + "epoch": 1.0, + "learning_rate": 3.727460309244918e-05, + "loss": 4.0372, + "step": 777216 + }, + { + "epoch": 1.0, + "learning_rate": 3.726621714493866e-05, + "loss": 4.0547, + "step": 777728 + }, + { + "epoch": 1.0, + "learning_rate": 3.725783119742814e-05, + "loss": 4.0459, + "step": 778240 + }, + { + "epoch": 1.01, + "learning_rate": 3.724944524991761e-05, + "loss": 4.032, + "step": 778752 + }, + { + "epoch": 1.01, + "learning_rate": 3.724105930240709e-05, + "loss": 4.0503, + "step": 779264 + }, + { + "epoch": 1.01, + "learning_rate": 3.723267335489657e-05, + "loss": 4.0471, + "step": 779776 + }, + { + "epoch": 1.01, + "learning_rate": 3.722428740738605e-05, + "loss": 4.0518, + "step": 780288 + }, + { + "epoch": 1.01, + "learning_rate": 3.721590145987553e-05, + "loss": 4.0434, + "step": 780800 + }, + { + "epoch": 1.01, + "learning_rate": 3.720751551236501e-05, + "loss": 4.0468, + "step": 781312 + }, + { + "epoch": 1.01, + "learning_rate": 3.719914594365823e-05, + "loss": 4.05, + "step": 781824 + }, + { + "epoch": 1.01, + "learning_rate": 3.719075999614771e-05, + "loss": 4.0504, + "step": 782336 + }, + { + "epoch": 1.01, + "learning_rate": 3.718239042744092e-05, + "loss": 4.0552, + "step": 782848 + }, + { + "epoch": 1.01, + "learning_rate": 3.71740044799304e-05, + "loss": 4.0344, + "step": 783360 + }, + { + "epoch": 1.01, + "learning_rate": 3.716561853241988e-05, + "loss": 4.04, + "step": 783872 + }, + { + "epoch": 1.01, + "learning_rate": 3.715723258490936e-05, + "loss": 4.0361, + "step": 784384 + }, + { + "epoch": 1.01, + "learning_rate": 3.714884663739884e-05, + "loss": 4.0444, + "step": 784896 + }, + { + "epoch": 1.01, + "learning_rate": 3.714046068988832e-05, + "loss": 4.0463, + "step": 785408 + }, + { + "epoch": 1.01, + "learning_rate": 3.71320747423778e-05, + "loss": 4.0359, + "step": 785920 + }, + { + "epoch": 1.01, + "learning_rate": 3.712368879486728e-05, + "loss": 4.0566, + "step": 786432 + }, + { + "epoch": 1.01, + "learning_rate": 3.711530284735676e-05, + "loss": 4.038, + "step": 786944 + }, + { + "epoch": 1.01, + "learning_rate": 3.710691689984624e-05, + "loss": 4.0528, + "step": 787456 + }, + { + "epoch": 1.01, + "learning_rate": 3.709853095233572e-05, + "loss": 4.0461, + "step": 787968 + }, + { + "epoch": 1.01, + "learning_rate": 3.70901450048252e-05, + "loss": 4.0275, + "step": 788480 + }, + { + "epoch": 1.01, + "learning_rate": 3.708177543611841e-05, + "loss": 4.0418, + "step": 788992 + }, + { + "epoch": 1.01, + "learning_rate": 3.707340586741162e-05, + "loss": 4.0337, + "step": 789504 + }, + { + "epoch": 1.01, + "learning_rate": 3.70650199199011e-05, + "loss": 4.0467, + "step": 790016 + }, + { + "epoch": 1.01, + "learning_rate": 3.705663397239058e-05, + "loss": 4.0391, + "step": 790528 + }, + { + "epoch": 1.01, + "learning_rate": 3.704824802488006e-05, + "loss": 4.0421, + "step": 791040 + }, + { + "epoch": 1.01, + "learning_rate": 3.703986207736954e-05, + "loss": 4.0239, + "step": 791552 + }, + { + "epoch": 1.01, + "learning_rate": 3.703147612985902e-05, + "loss": 4.0427, + "step": 792064 + }, + { + "epoch": 1.01, + "learning_rate": 3.70230901823485e-05, + "loss": 4.0269, + "step": 792576 + }, + { + "epoch": 1.01, + "learning_rate": 3.7014704234837975e-05, + "loss": 4.0453, + "step": 793088 + }, + { + "epoch": 1.01, + "learning_rate": 3.700633466613119e-05, + "loss": 4.0346, + "step": 793600 + }, + { + "epoch": 1.01, + "learning_rate": 3.699794871862067e-05, + "loss": 4.0359, + "step": 794112 + }, + { + "epoch": 1.01, + "learning_rate": 3.698956277111015e-05, + "loss": 4.0365, + "step": 794624 + }, + { + "epoch": 1.01, + "learning_rate": 3.698117682359963e-05, + "loss": 4.0222, + "step": 795136 + }, + { + "epoch": 1.01, + "learning_rate": 3.6972807254892846e-05, + "loss": 4.043, + "step": 795648 + }, + { + "epoch": 1.01, + "learning_rate": 3.6964421307382326e-05, + "loss": 4.035, + "step": 796160 + }, + { + "epoch": 1.01, + "learning_rate": 3.69560353598718e-05, + "loss": 4.047, + "step": 796672 + }, + { + "epoch": 1.01, + "learning_rate": 3.6947665791165015e-05, + "loss": 4.0291, + "step": 797184 + }, + { + "epoch": 1.01, + "learning_rate": 3.6939279843654495e-05, + "loss": 4.033, + "step": 797696 + }, + { + "epoch": 1.01, + "learning_rate": 3.6930893896143975e-05, + "loss": 4.0316, + "step": 798208 + }, + { + "epoch": 1.01, + "learning_rate": 3.692250794863345e-05, + "loss": 4.0372, + "step": 798720 + }, + { + "epoch": 1.01, + "learning_rate": 3.691412200112293e-05, + "loss": 4.0322, + "step": 799232 + }, + { + "epoch": 1.01, + "learning_rate": 3.690573605361241e-05, + "loss": 4.0403, + "step": 799744 + }, + { + "epoch": 1.01, + "learning_rate": 3.689735010610189e-05, + "loss": 4.0369, + "step": 800256 + }, + { + "epoch": 1.01, + "learning_rate": 3.688896415859137e-05, + "loss": 4.0584, + "step": 800768 + }, + { + "epoch": 1.01, + "learning_rate": 3.6880594589884584e-05, + "loss": 4.048, + "step": 801280 + }, + { + "epoch": 1.01, + "learning_rate": 3.6872208642374064e-05, + "loss": 4.0409, + "step": 801792 + }, + { + "epoch": 1.01, + "learning_rate": 3.6863822694863544e-05, + "loss": 4.0411, + "step": 802304 + }, + { + "epoch": 1.01, + "learning_rate": 3.6855436747353024e-05, + "loss": 4.0269, + "step": 802816 + }, + { + "epoch": 1.01, + "learning_rate": 3.684706717864623e-05, + "loss": 4.0371, + "step": 803328 + }, + { + "epoch": 1.01, + "learning_rate": 3.683868123113571e-05, + "loss": 4.0376, + "step": 803840 + }, + { + "epoch": 1.01, + "learning_rate": 3.683029528362519e-05, + "loss": 4.05, + "step": 804352 + }, + { + "epoch": 1.01, + "learning_rate": 3.682190933611467e-05, + "loss": 4.0433, + "step": 804864 + }, + { + "epoch": 1.01, + "learning_rate": 3.681352338860415e-05, + "loss": 4.026, + "step": 805376 + }, + { + "epoch": 1.01, + "learning_rate": 3.680515381989736e-05, + "loss": 4.0354, + "step": 805888 + }, + { + "epoch": 1.01, + "learning_rate": 3.679676787238684e-05, + "loss": 4.0247, + "step": 806400 + }, + { + "epoch": 1.01, + "learning_rate": 3.678838192487632e-05, + "loss": 4.0346, + "step": 806912 + }, + { + "epoch": 1.01, + "learning_rate": 3.677999597736581e-05, + "loss": 4.0331, + "step": 807424 + }, + { + "epoch": 1.01, + "learning_rate": 3.677161002985529e-05, + "loss": 4.0383, + "step": 807936 + }, + { + "epoch": 1.01, + "learning_rate": 3.676322408234477e-05, + "loss": 4.0447, + "step": 808448 + }, + { + "epoch": 1.01, + "learning_rate": 3.675483813483425e-05, + "loss": 4.0408, + "step": 808960 + }, + { + "epoch": 1.02, + "learning_rate": 3.674645218732373e-05, + "loss": 4.0281, + "step": 809472 + }, + { + "epoch": 1.02, + "learning_rate": 3.673808261861694e-05, + "loss": 4.0367, + "step": 809984 + }, + { + "epoch": 1.02, + "learning_rate": 3.672969667110642e-05, + "loss": 4.0376, + "step": 810496 + }, + { + "epoch": 1.02, + "learning_rate": 3.67213107235959e-05, + "loss": 4.0257, + "step": 811008 + }, + { + "epoch": 1.02, + "learning_rate": 3.671292477608538e-05, + "loss": 4.0278, + "step": 811520 + }, + { + "epoch": 1.02, + "learning_rate": 3.670453882857486e-05, + "loss": 4.0377, + "step": 812032 + }, + { + "epoch": 1.02, + "learning_rate": 3.6696169259868066e-05, + "loss": 4.0461, + "step": 812544 + }, + { + "epoch": 1.02, + "learning_rate": 3.6687783312357546e-05, + "loss": 4.0495, + "step": 813056 + }, + { + "epoch": 1.02, + "learning_rate": 3.6679397364847026e-05, + "loss": 4.034, + "step": 813568 + }, + { + "epoch": 1.02, + "learning_rate": 3.6671011417336506e-05, + "loss": 4.0422, + "step": 814080 + }, + { + "epoch": 1.02, + "learning_rate": 3.666264184862972e-05, + "loss": 4.0318, + "step": 814592 + }, + { + "epoch": 1.02, + "learning_rate": 3.665427227992293e-05, + "loss": 4.0396, + "step": 815104 + }, + { + "epoch": 1.02, + "learning_rate": 3.664588633241241e-05, + "loss": 4.0353, + "step": 815616 + }, + { + "epoch": 1.02, + "learning_rate": 3.663750038490189e-05, + "loss": 4.0451, + "step": 816128 + }, + { + "epoch": 1.02, + "learning_rate": 3.662911443739137e-05, + "loss": 4.039, + "step": 816640 + }, + { + "epoch": 1.02, + "learning_rate": 3.662072848988085e-05, + "loss": 4.0169, + "step": 817152 + }, + { + "epoch": 1.02, + "learning_rate": 3.661234254237033e-05, + "loss": 4.023, + "step": 817664 + }, + { + "epoch": 1.02, + "learning_rate": 3.660395659485981e-05, + "loss": 4.0242, + "step": 818176 + }, + { + "epoch": 1.02, + "learning_rate": 3.659558702615302e-05, + "loss": 4.0299, + "step": 818688 + }, + { + "epoch": 1.02, + "learning_rate": 3.65872010786425e-05, + "loss": 4.0366, + "step": 819200 + }, + { + "epoch": 1.02, + "learning_rate": 3.657881513113198e-05, + "loss": 4.0431, + "step": 819712 + }, + { + "epoch": 1.02, + "learning_rate": 3.657042918362146e-05, + "loss": 4.0167, + "step": 820224 + }, + { + "epoch": 1.02, + "learning_rate": 3.656204323611094e-05, + "loss": 4.0307, + "step": 820736 + }, + { + "epoch": 1.02, + "learning_rate": 3.655365728860042e-05, + "loss": 4.0424, + "step": 821248 + }, + { + "epoch": 1.02, + "learning_rate": 3.65452713410899e-05, + "loss": 4.0365, + "step": 821760 + }, + { + "epoch": 1.02, + "learning_rate": 3.653688539357938e-05, + "loss": 4.0407, + "step": 822272 + }, + { + "epoch": 1.02, + "learning_rate": 3.652851582487259e-05, + "loss": 4.0351, + "step": 822784 + }, + { + "epoch": 1.02, + "learning_rate": 3.652012987736207e-05, + "loss": 4.021, + "step": 823296 + }, + { + "epoch": 1.02, + "learning_rate": 3.651174392985155e-05, + "loss": 4.0354, + "step": 823808 + }, + { + "epoch": 1.02, + "learning_rate": 3.650335798234103e-05, + "loss": 4.045, + "step": 824320 + }, + { + "epoch": 1.02, + "learning_rate": 3.649498841363424e-05, + "loss": 4.0313, + "step": 824832 + }, + { + "epoch": 1.02, + "learning_rate": 3.648660246612372e-05, + "loss": 4.0203, + "step": 825344 + }, + { + "epoch": 1.02, + "learning_rate": 3.64782165186132e-05, + "loss": 4.0289, + "step": 825856 + }, + { + "epoch": 1.02, + "learning_rate": 3.6469830571102684e-05, + "loss": 4.0302, + "step": 826368 + }, + { + "epoch": 1.02, + "learning_rate": 3.6461461002395893e-05, + "loss": 4.0371, + "step": 826880 + }, + { + "epoch": 1.02, + "learning_rate": 3.6453075054885373e-05, + "loss": 4.0311, + "step": 827392 + }, + { + "epoch": 1.02, + "learning_rate": 3.644470548617858e-05, + "loss": 4.0398, + "step": 827904 + }, + { + "epoch": 1.02, + "learning_rate": 3.643631953866806e-05, + "loss": 4.0186, + "step": 828416 + }, + { + "epoch": 1.02, + "learning_rate": 3.642793359115754e-05, + "loss": 4.0427, + "step": 828928 + }, + { + "epoch": 1.02, + "learning_rate": 3.641954764364702e-05, + "loss": 4.0298, + "step": 829440 + }, + { + "epoch": 1.02, + "learning_rate": 3.64111616961365e-05, + "loss": 4.0398, + "step": 829952 + }, + { + "epoch": 1.02, + "learning_rate": 3.640277574862598e-05, + "loss": 4.0485, + "step": 830464 + }, + { + "epoch": 1.02, + "learning_rate": 3.639438980111546e-05, + "loss": 4.0331, + "step": 830976 + }, + { + "epoch": 1.02, + "learning_rate": 3.638602023240867e-05, + "loss": 4.0398, + "step": 831488 + }, + { + "epoch": 1.02, + "learning_rate": 3.637763428489815e-05, + "loss": 4.0382, + "step": 832000 + }, + { + "epoch": 1.02, + "learning_rate": 3.636924833738764e-05, + "loss": 4.0227, + "step": 832512 + }, + { + "epoch": 1.02, + "learning_rate": 3.636086238987712e-05, + "loss": 4.0258, + "step": 833024 + }, + { + "epoch": 1.02, + "learning_rate": 3.63524764423666e-05, + "loss": 4.0305, + "step": 833536 + }, + { + "epoch": 1.02, + "learning_rate": 3.634409049485608e-05, + "loss": 4.0411, + "step": 834048 + }, + { + "epoch": 1.02, + "learning_rate": 3.633572092614929e-05, + "loss": 4.0398, + "step": 834560 + }, + { + "epoch": 1.02, + "learning_rate": 3.632733497863877e-05, + "loss": 4.0372, + "step": 835072 + }, + { + "epoch": 1.02, + "learning_rate": 3.631894903112825e-05, + "loss": 4.0362, + "step": 835584 + }, + { + "epoch": 1.02, + "learning_rate": 3.631056308361773e-05, + "loss": 4.0288, + "step": 836096 + }, + { + "epoch": 1.02, + "learning_rate": 3.6302193514910936e-05, + "loss": 4.0191, + "step": 836608 + }, + { + "epoch": 1.02, + "learning_rate": 3.6293807567400416e-05, + "loss": 4.0344, + "step": 837120 + }, + { + "epoch": 1.02, + "learning_rate": 3.6285421619889896e-05, + "loss": 4.0416, + "step": 837632 + }, + { + "epoch": 1.02, + "learning_rate": 3.6277035672379376e-05, + "loss": 4.0423, + "step": 838144 + }, + { + "epoch": 1.02, + "learning_rate": 3.6268649724868856e-05, + "loss": 4.0258, + "step": 838656 + }, + { + "epoch": 1.02, + "learning_rate": 3.6260263777358336e-05, + "loss": 4.0289, + "step": 839168 + }, + { + "epoch": 1.03, + "eval_loss": 4.062594890594482, + "eval_runtime": 547.0062, + "eval_samples_per_second": 697.599, + "eval_steps_per_second": 21.8, + "step": 839509 + }, + { + "epoch": 0.0, + "learning_rate": 3.625189420865155e-05, + "loss": 4.058, + "step": 839680 + }, + { + "epoch": 0.0, + "learning_rate": 3.624350826114103e-05, + "loss": 4.0341, + "step": 840192 + }, + { + "epoch": 0.0, + "learning_rate": 3.623512231363051e-05, + "loss": 4.0291, + "step": 840704 + }, + { + "epoch": 0.0, + "learning_rate": 3.622673636611999e-05, + "loss": 4.0262, + "step": 841216 + }, + { + "epoch": 0.0, + "learning_rate": 3.621835041860947e-05, + "loss": 4.0317, + "step": 841728 + }, + { + "epoch": 0.0, + "learning_rate": 3.6209964471098945e-05, + "loss": 4.0205, + "step": 842240 + }, + { + "epoch": 0.0, + "learning_rate": 3.6201578523588425e-05, + "loss": 4.018, + "step": 842752 + }, + { + "epoch": 0.0, + "learning_rate": 3.6193192576077905e-05, + "loss": 4.0227, + "step": 843264 + }, + { + "epoch": 0.0, + "learning_rate": 3.6184806628567384e-05, + "loss": 4.0293, + "step": 843776 + }, + { + "epoch": 0.0, + "learning_rate": 3.6176420681056864e-05, + "loss": 4.03, + "step": 844288 + }, + { + "epoch": 0.0, + "learning_rate": 3.6168051112350074e-05, + "loss": 4.0264, + "step": 844800 + }, + { + "epoch": 0.0, + "learning_rate": 3.6159665164839553e-05, + "loss": 4.0316, + "step": 845312 + }, + { + "epoch": 0.0, + "learning_rate": 3.615127921732904e-05, + "loss": 4.0355, + "step": 845824 + }, + { + "epoch": 0.0, + "learning_rate": 3.614289326981852e-05, + "loss": 4.026, + "step": 846336 + }, + { + "epoch": 0.0, + "learning_rate": 3.6134507322308e-05, + "loss": 4.0375, + "step": 846848 + }, + { + "epoch": 0.0, + "learning_rate": 3.612612137479748e-05, + "loss": 4.0174, + "step": 847360 + }, + { + "epoch": 0.0, + "learning_rate": 3.611773542728696e-05, + "loss": 4.0138, + "step": 847872 + }, + { + "epoch": 0.0, + "learning_rate": 3.610934947977644e-05, + "loss": 4.0358, + "step": 848384 + }, + { + "epoch": 0.0, + "learning_rate": 3.610096353226592e-05, + "loss": 4.028, + "step": 848896 + }, + { + "epoch": 0.0, + "learning_rate": 3.60925775847554e-05, + "loss": 4.0353, + "step": 849408 + }, + { + "epoch": 0.0, + "learning_rate": 3.608419163724488e-05, + "loss": 4.0245, + "step": 849920 + }, + { + "epoch": 0.0, + "learning_rate": 3.607580568973436e-05, + "loss": 4.0386, + "step": 850432 + }, + { + "epoch": 0.0, + "learning_rate": 3.606741974222383e-05, + "loss": 4.0277, + "step": 850944 + }, + { + "epoch": 0.0, + "learning_rate": 3.605903379471331e-05, + "loss": 4.0282, + "step": 851456 + }, + { + "epoch": 0.0, + "learning_rate": 3.605064784720279e-05, + "loss": 4.0287, + "step": 851968 + }, + { + "epoch": 0.0, + "learning_rate": 3.604227827849601e-05, + "loss": 4.0283, + "step": 852480 + }, + { + "epoch": 0.0, + "learning_rate": 3.603389233098549e-05, + "loss": 4.031, + "step": 852992 + }, + { + "epoch": 0.0, + "learning_rate": 3.602550638347497e-05, + "loss": 4.019, + "step": 853504 + }, + { + "epoch": 0.0, + "learning_rate": 3.601712043596445e-05, + "loss": 4.0346, + "step": 854016 + }, + { + "epoch": 0.0, + "learning_rate": 3.600873448845393e-05, + "loss": 4.0261, + "step": 854528 + }, + { + "epoch": 0.01, + "learning_rate": 3.600034854094341e-05, + "loss": 4.0186, + "step": 855040 + }, + { + "epoch": 0.01, + "learning_rate": 3.599196259343289e-05, + "loss": 4.0284, + "step": 855552 + }, + { + "epoch": 0.01, + "learning_rate": 3.598357664592237e-05, + "loss": 4.027, + "step": 856064 + }, + { + "epoch": 0.01, + "learning_rate": 3.597520707721558e-05, + "loss": 4.035, + "step": 856576 + }, + { + "epoch": 0.01, + "learning_rate": 3.596682112970506e-05, + "loss": 4.0213, + "step": 857088 + }, + { + "epoch": 0.01, + "learning_rate": 3.595843518219454e-05, + "loss": 4.0292, + "step": 857600 + }, + { + "epoch": 0.01, + "learning_rate": 3.5950065613487747e-05, + "loss": 4.0319, + "step": 858112 + }, + { + "epoch": 0.01, + "learning_rate": 3.5941679665977227e-05, + "loss": 4.0296, + "step": 858624 + }, + { + "epoch": 0.01, + "learning_rate": 3.593331009727044e-05, + "loss": 4.0378, + "step": 859136 + }, + { + "epoch": 0.01, + "learning_rate": 3.592492414975992e-05, + "loss": 4.0164, + "step": 859648 + }, + { + "epoch": 0.01, + "learning_rate": 3.59165382022494e-05, + "loss": 4.0224, + "step": 860160 + }, + { + "epoch": 0.01, + "learning_rate": 3.590815225473888e-05, + "loss": 4.0171, + "step": 860672 + }, + { + "epoch": 0.01, + "learning_rate": 3.589976630722836e-05, + "loss": 4.0202, + "step": 861184 + }, + { + "epoch": 0.01, + "learning_rate": 3.589138035971784e-05, + "loss": 4.0291, + "step": 861696 + }, + { + "epoch": 0.01, + "learning_rate": 3.588299441220732e-05, + "loss": 4.0165, + "step": 862208 + }, + { + "epoch": 0.01, + "learning_rate": 3.58746084646968e-05, + "loss": 4.0339, + "step": 862720 + }, + { + "epoch": 0.01, + "learning_rate": 3.586622251718628e-05, + "loss": 4.0207, + "step": 863232 + }, + { + "epoch": 0.01, + "learning_rate": 3.585783656967576e-05, + "loss": 4.0352, + "step": 863744 + }, + { + "epoch": 0.01, + "learning_rate": 3.584945062216524e-05, + "loss": 4.0285, + "step": 864256 + }, + { + "epoch": 0.01, + "learning_rate": 3.5841064674654715e-05, + "loss": 4.0068, + "step": 864768 + }, + { + "epoch": 0.01, + "learning_rate": 3.583269510594793e-05, + "loss": 4.0187, + "step": 865280 + }, + { + "epoch": 0.01, + "learning_rate": 3.582432553724114e-05, + "loss": 4.0165, + "step": 865792 + }, + { + "epoch": 0.01, + "learning_rate": 3.581593958973063e-05, + "loss": 4.0245, + "step": 866304 + }, + { + "epoch": 0.01, + "learning_rate": 3.5807570021023836e-05, + "loss": 4.0207, + "step": 866816 + }, + { + "epoch": 0.01, + "learning_rate": 3.5799184073513316e-05, + "loss": 4.023, + "step": 867328 + }, + { + "epoch": 0.01, + "learning_rate": 3.5790798126002796e-05, + "loss": 4.007, + "step": 867840 + }, + { + "epoch": 0.01, + "learning_rate": 3.5782412178492276e-05, + "loss": 4.0234, + "step": 868352 + }, + { + "epoch": 0.01, + "learning_rate": 3.5774026230981756e-05, + "loss": 4.0129, + "step": 868864 + }, + { + "epoch": 0.01, + "learning_rate": 3.5765640283471236e-05, + "loss": 4.0262, + "step": 869376 + }, + { + "epoch": 0.01, + "learning_rate": 3.5757254335960716e-05, + "loss": 4.0099, + "step": 869888 + }, + { + "epoch": 0.01, + "learning_rate": 3.574886838845019e-05, + "loss": 4.0213, + "step": 870400 + }, + { + "epoch": 0.01, + "learning_rate": 3.574048244093967e-05, + "loss": 4.0138, + "step": 870912 + }, + { + "epoch": 0.01, + "learning_rate": 3.573209649342915e-05, + "loss": 4.0069, + "step": 871424 + }, + { + "epoch": 0.01, + "learning_rate": 3.5723726924722365e-05, + "loss": 4.0221, + "step": 871936 + }, + { + "epoch": 0.01, + "learning_rate": 3.5715340977211845e-05, + "loss": 4.0205, + "step": 872448 + }, + { + "epoch": 0.01, + "learning_rate": 3.5706955029701325e-05, + "loss": 4.0255, + "step": 872960 + }, + { + "epoch": 0.01, + "learning_rate": 3.5698569082190804e-05, + "loss": 4.009, + "step": 873472 + }, + { + "epoch": 0.01, + "learning_rate": 3.5690183134680284e-05, + "loss": 4.0184, + "step": 873984 + }, + { + "epoch": 0.01, + "learning_rate": 3.5681797187169764e-05, + "loss": 4.01, + "step": 874496 + }, + { + "epoch": 0.01, + "learning_rate": 3.5673427618462974e-05, + "loss": 4.0179, + "step": 875008 + }, + { + "epoch": 0.01, + "learning_rate": 3.5665041670952453e-05, + "loss": 4.0132, + "step": 875520 + }, + { + "epoch": 0.01, + "learning_rate": 3.5656655723441933e-05, + "loss": 4.0248, + "step": 876032 + }, + { + "epoch": 0.01, + "learning_rate": 3.564826977593141e-05, + "loss": 4.0153, + "step": 876544 + }, + { + "epoch": 0.01, + "learning_rate": 3.563988382842089e-05, + "loss": 4.0387, + "step": 877056 + }, + { + "epoch": 0.01, + "learning_rate": 3.563149788091037e-05, + "loss": 4.0316, + "step": 877568 + }, + { + "epoch": 0.01, + "learning_rate": 3.562312831220358e-05, + "loss": 4.0185, + "step": 878080 + }, + { + "epoch": 0.01, + "learning_rate": 3.561474236469306e-05, + "loss": 4.0184, + "step": 878592 + }, + { + "epoch": 0.01, + "learning_rate": 3.560635641718255e-05, + "loss": 4.0134, + "step": 879104 + }, + { + "epoch": 0.01, + "learning_rate": 3.559798684847576e-05, + "loss": 4.0149, + "step": 879616 + }, + { + "epoch": 0.01, + "learning_rate": 3.558960090096524e-05, + "loss": 4.0228, + "step": 880128 + }, + { + "epoch": 0.01, + "learning_rate": 3.558121495345472e-05, + "loss": 4.0281, + "step": 880640 + }, + { + "epoch": 0.01, + "learning_rate": 3.55728290059442e-05, + "loss": 4.0298, + "step": 881152 + }, + { + "epoch": 0.01, + "learning_rate": 3.556444305843368e-05, + "loss": 4.0085, + "step": 881664 + }, + { + "epoch": 0.01, + "learning_rate": 3.555605711092316e-05, + "loss": 4.0131, + "step": 882176 + }, + { + "epoch": 0.01, + "learning_rate": 3.554767116341264e-05, + "loss": 4.0054, + "step": 882688 + }, + { + "epoch": 0.01, + "learning_rate": 3.553930159470585e-05, + "loss": 4.0229, + "step": 883200 + }, + { + "epoch": 0.01, + "learning_rate": 3.553091564719533e-05, + "loss": 4.0127, + "step": 883712 + }, + { + "epoch": 0.01, + "learning_rate": 3.552252969968481e-05, + "loss": 4.02, + "step": 884224 + }, + { + "epoch": 0.01, + "learning_rate": 3.551414375217429e-05, + "loss": 4.0257, + "step": 884736 + }, + { + "epoch": 0.01, + "learning_rate": 3.550575780466377e-05, + "loss": 4.0248, + "step": 885248 + }, + { + "epoch": 0.02, + "learning_rate": 3.549737185715325e-05, + "loss": 4.0078, + "step": 885760 + }, + { + "epoch": 0.02, + "learning_rate": 3.5488985909642733e-05, + "loss": 4.0141, + "step": 886272 + }, + { + "epoch": 0.02, + "learning_rate": 3.548059996213221e-05, + "loss": 4.0221, + "step": 886784 + }, + { + "epoch": 0.02, + "learning_rate": 3.547221401462169e-05, + "loss": 4.0085, + "step": 887296 + }, + { + "epoch": 0.02, + "learning_rate": 3.5463828067111167e-05, + "loss": 4.0091, + "step": 887808 + }, + { + "epoch": 0.02, + "learning_rate": 3.5455442119600647e-05, + "loss": 4.0214, + "step": 888320 + }, + { + "epoch": 0.02, + "learning_rate": 3.5447056172090126e-05, + "loss": 4.0266, + "step": 888832 + }, + { + "epoch": 0.02, + "learning_rate": 3.5438686603383336e-05, + "loss": 4.031, + "step": 889344 + }, + { + "epoch": 0.02, + "learning_rate": 3.5430300655872816e-05, + "loss": 4.0189, + "step": 889856 + }, + { + "epoch": 0.02, + "learning_rate": 3.5421914708362296e-05, + "loss": 4.0219, + "step": 890368 + }, + { + "epoch": 0.02, + "learning_rate": 3.5413528760851775e-05, + "loss": 4.0113, + "step": 890880 + }, + { + "epoch": 0.02, + "learning_rate": 3.5405159192144985e-05, + "loss": 4.0232, + "step": 891392 + }, + { + "epoch": 0.02, + "learning_rate": 3.539677324463447e-05, + "loss": 4.0173, + "step": 891904 + }, + { + "epoch": 0.02, + "learning_rate": 3.538838729712395e-05, + "loss": 4.027, + "step": 892416 + }, + { + "epoch": 0.02, + "learning_rate": 3.538000134961343e-05, + "loss": 4.0181, + "step": 892928 + }, + { + "epoch": 0.02, + "learning_rate": 3.537163178090664e-05, + "loss": 4.0051, + "step": 893440 + }, + { + "epoch": 0.02, + "learning_rate": 3.5363262212199856e-05, + "loss": 4.006, + "step": 893952 + }, + { + "epoch": 0.02, + "learning_rate": 3.535487626468933e-05, + "loss": 3.9995, + "step": 894464 + }, + { + "epoch": 0.02, + "learning_rate": 3.534649031717881e-05, + "loss": 4.0148, + "step": 894976 + }, + { + "epoch": 0.02, + "learning_rate": 3.533810436966829e-05, + "loss": 4.0223, + "step": 895488 + }, + { + "epoch": 0.02, + "learning_rate": 3.532971842215777e-05, + "loss": 4.0199, + "step": 896000 + }, + { + "epoch": 0.02, + "learning_rate": 3.532133247464725e-05, + "loss": 4.003, + "step": 896512 + }, + { + "epoch": 0.02, + "learning_rate": 3.531294652713673e-05, + "loss": 4.0083, + "step": 897024 + }, + { + "epoch": 0.02, + "learning_rate": 3.530456057962621e-05, + "loss": 4.0222, + "step": 897536 + }, + { + "epoch": 0.02, + "learning_rate": 3.5296191010919425e-05, + "loss": 4.0226, + "step": 898048 + }, + { + "epoch": 0.02, + "learning_rate": 3.5287805063408905e-05, + "loss": 4.025, + "step": 898560 + }, + { + "epoch": 0.02, + "learning_rate": 3.5279419115898385e-05, + "loss": 4.0148, + "step": 899072 + }, + { + "epoch": 0.02, + "learning_rate": 3.5271033168387865e-05, + "loss": 4.0067, + "step": 899584 + }, + { + "epoch": 0.02, + "learning_rate": 3.5262647220877345e-05, + "loss": 4.0158, + "step": 900096 + }, + { + "epoch": 0.02, + "learning_rate": 3.5254277652170554e-05, + "loss": 4.0243, + "step": 900608 + }, + { + "epoch": 0.02, + "learning_rate": 3.524590808346376e-05, + "loss": 4.0141, + "step": 901120 + }, + { + "epoch": 0.02, + "learning_rate": 3.523752213595324e-05, + "loss": 4.0032, + "step": 901632 + }, + { + "epoch": 0.02, + "learning_rate": 3.522915256724645e-05, + "loss": 4.0089, + "step": 902144 + }, + { + "epoch": 0.02, + "learning_rate": 3.522076661973593e-05, + "loss": 4.012, + "step": 902656 + }, + { + "epoch": 0.02, + "learning_rate": 3.521239705102915e-05, + "loss": 4.0198, + "step": 903168 + }, + { + "epoch": 0.02, + "learning_rate": 3.520401110351863e-05, + "loss": 4.0133, + "step": 903680 + }, + { + "epoch": 0.02, + "learning_rate": 3.519562515600811e-05, + "loss": 4.0238, + "step": 904192 + }, + { + "epoch": 0.02, + "learning_rate": 3.518723920849759e-05, + "loss": 4.0022, + "step": 904704 + }, + { + "epoch": 0.02, + "learning_rate": 3.517885326098707e-05, + "loss": 4.0239, + "step": 905216 + }, + { + "epoch": 0.02, + "learning_rate": 3.517046731347655e-05, + "loss": 4.011, + "step": 905728 + }, + { + "epoch": 0.02, + "learning_rate": 3.516208136596603e-05, + "loss": 4.0209, + "step": 906240 + }, + { + "epoch": 0.02, + "learning_rate": 3.515369541845551e-05, + "loss": 4.0282, + "step": 906752 + }, + { + "epoch": 0.02, + "learning_rate": 3.514530947094499e-05, + "loss": 4.0202, + "step": 907264 + }, + { + "epoch": 0.02, + "learning_rate": 3.513692352343447e-05, + "loss": 4.0167, + "step": 907776 + }, + { + "epoch": 0.02, + "learning_rate": 3.512853757592395e-05, + "loss": 4.0222, + "step": 908288 + }, + { + "epoch": 0.02, + "learning_rate": 3.512015162841343e-05, + "loss": 4.0011, + "step": 908800 + }, + { + "epoch": 0.02, + "learning_rate": 3.511176568090291e-05, + "loss": 4.0104, + "step": 909312 + }, + { + "epoch": 0.02, + "learning_rate": 3.5103396112196116e-05, + "loss": 4.0107, + "step": 909824 + }, + { + "epoch": 0.02, + "learning_rate": 3.5095010164685596e-05, + "loss": 4.0268, + "step": 910336 + }, + { + "epoch": 0.02, + "learning_rate": 3.5086624217175076e-05, + "loss": 4.0207, + "step": 910848 + }, + { + "epoch": 0.02, + "learning_rate": 3.5078238269664556e-05, + "loss": 4.0231, + "step": 911360 + }, + { + "epoch": 0.02, + "learning_rate": 3.506985232215404e-05, + "loss": 4.017, + "step": 911872 + }, + { + "epoch": 0.02, + "learning_rate": 3.506148275344725e-05, + "loss": 4.0092, + "step": 912384 + }, + { + "epoch": 0.02, + "learning_rate": 3.505309680593673e-05, + "loss": 4.0019, + "step": 912896 + }, + { + "epoch": 0.02, + "learning_rate": 3.504471085842621e-05, + "loss": 4.0183, + "step": 913408 + }, + { + "epoch": 0.02, + "learning_rate": 3.5036324910915685e-05, + "loss": 4.0201, + "step": 913920 + }, + { + "epoch": 0.02, + "learning_rate": 3.50279553422089e-05, + "loss": 4.0287, + "step": 914432 + }, + { + "epoch": 0.02, + "learning_rate": 3.501956939469838e-05, + "loss": 4.0066, + "step": 914944 + }, + { + "epoch": 0.02, + "learning_rate": 3.501118344718786e-05, + "loss": 4.0114, + "step": 915456 + }, + { + "epoch": 0.03, + "eval_loss": 4.051225185394287, + "eval_runtime": 543.0432, + "eval_samples_per_second": 702.69, + "eval_steps_per_second": 21.96, + "step": 915828 + }, + { + "epoch": 1.0, + "learning_rate": 3.5002797499677334e-05, + "loss": 4.0184, + "step": 915968 + }, + { + "epoch": 1.0, + "learning_rate": 3.4994411552166814e-05, + "loss": 4.0164, + "step": 916480 + }, + { + "epoch": 1.0, + "learning_rate": 3.4986025604656294e-05, + "loss": 4.012, + "step": 916992 + }, + { + "epoch": 1.0, + "learning_rate": 3.497763965714578e-05, + "loss": 4.0096, + "step": 917504 + }, + { + "epoch": 1.0, + "learning_rate": 3.496927008843899e-05, + "loss": 4.0139, + "step": 918016 + }, + { + "epoch": 1.0, + "learning_rate": 3.496088414092847e-05, + "loss": 4.0032, + "step": 918528 + }, + { + "epoch": 1.0, + "learning_rate": 3.4952514572221686e-05, + "loss": 4.003, + "step": 919040 + }, + { + "epoch": 1.0, + "learning_rate": 3.494412862471116e-05, + "loss": 3.9992, + "step": 919552 + }, + { + "epoch": 1.0, + "learning_rate": 3.493574267720064e-05, + "loss": 4.018, + "step": 920064 + }, + { + "epoch": 1.0, + "learning_rate": 3.492735672969012e-05, + "loss": 4.008, + "step": 920576 + }, + { + "epoch": 1.0, + "learning_rate": 3.4918987160983335e-05, + "loss": 4.0109, + "step": 921088 + }, + { + "epoch": 1.0, + "learning_rate": 3.491060121347281e-05, + "loss": 4.0173, + "step": 921600 + }, + { + "epoch": 1.0, + "learning_rate": 3.490221526596229e-05, + "loss": 4.0149, + "step": 922112 + }, + { + "epoch": 1.0, + "learning_rate": 3.489382931845177e-05, + "loss": 4.0096, + "step": 922624 + }, + { + "epoch": 1.0, + "learning_rate": 3.488544337094125e-05, + "loss": 4.0183, + "step": 923136 + }, + { + "epoch": 1.0, + "learning_rate": 3.4877057423430734e-05, + "loss": 4.0019, + "step": 923648 + }, + { + "epoch": 1.0, + "learning_rate": 3.4868671475920214e-05, + "loss": 3.9954, + "step": 924160 + }, + { + "epoch": 1.0, + "learning_rate": 3.4860285528409694e-05, + "loss": 4.0164, + "step": 924672 + }, + { + "epoch": 1.0, + "learning_rate": 3.4851915959702903e-05, + "loss": 4.0102, + "step": 925184 + }, + { + "epoch": 1.0, + "learning_rate": 3.4843530012192383e-05, + "loss": 4.0205, + "step": 925696 + }, + { + "epoch": 1.0, + "learning_rate": 3.4835144064681863e-05, + "loss": 4.0052, + "step": 926208 + }, + { + "epoch": 1.0, + "learning_rate": 3.482675811717134e-05, + "loss": 4.0221, + "step": 926720 + }, + { + "epoch": 1.0, + "learning_rate": 3.481837216966082e-05, + "loss": 4.0118, + "step": 927232 + }, + { + "epoch": 1.0, + "learning_rate": 3.48099862221503e-05, + "loss": 4.008, + "step": 927744 + }, + { + "epoch": 1.0, + "learning_rate": 3.480161665344351e-05, + "loss": 4.0118, + "step": 928256 + }, + { + "epoch": 1.0, + "learning_rate": 3.479323070593299e-05, + "loss": 4.0093, + "step": 928768 + }, + { + "epoch": 1.0, + "learning_rate": 3.478484475842247e-05, + "loss": 4.0167, + "step": 929280 + }, + { + "epoch": 1.0, + "learning_rate": 3.477645881091195e-05, + "loss": 4.0041, + "step": 929792 + }, + { + "epoch": 1.0, + "learning_rate": 3.476807286340143e-05, + "loss": 4.0106, + "step": 930304 + }, + { + "epoch": 1.0, + "learning_rate": 3.475970329469465e-05, + "loss": 4.0159, + "step": 930816 + }, + { + "epoch": 1.01, + "learning_rate": 3.475131734718413e-05, + "loss": 3.9993, + "step": 931328 + }, + { + "epoch": 1.01, + "learning_rate": 3.474293139967361e-05, + "loss": 4.0075, + "step": 931840 + }, + { + "epoch": 1.01, + "learning_rate": 3.473454545216309e-05, + "loss": 4.0115, + "step": 932352 + }, + { + "epoch": 1.01, + "learning_rate": 3.472615950465257e-05, + "loss": 4.0199, + "step": 932864 + }, + { + "epoch": 1.01, + "learning_rate": 3.471777355714205e-05, + "loss": 4.0047, + "step": 933376 + }, + { + "epoch": 1.01, + "learning_rate": 3.470938760963152e-05, + "loss": 4.0092, + "step": 933888 + }, + { + "epoch": 1.01, + "learning_rate": 3.470101804092474e-05, + "loss": 4.0185, + "step": 934400 + }, + { + "epoch": 1.01, + "learning_rate": 3.469263209341422e-05, + "loss": 4.0089, + "step": 934912 + }, + { + "epoch": 1.01, + "learning_rate": 3.46842461459037e-05, + "loss": 4.0207, + "step": 935424 + }, + { + "epoch": 1.01, + "learning_rate": 3.467586019839317e-05, + "loss": 3.9985, + "step": 935936 + }, + { + "epoch": 1.01, + "learning_rate": 3.466747425088266e-05, + "loss": 4.0079, + "step": 936448 + }, + { + "epoch": 1.01, + "learning_rate": 3.465908830337214e-05, + "loss": 3.9982, + "step": 936960 + }, + { + "epoch": 1.01, + "learning_rate": 3.465070235586162e-05, + "loss": 4.0058, + "step": 937472 + }, + { + "epoch": 1.01, + "learning_rate": 3.4642316408351097e-05, + "loss": 4.0096, + "step": 937984 + }, + { + "epoch": 1.01, + "learning_rate": 3.4633946839644306e-05, + "loss": 4.0042, + "step": 938496 + }, + { + "epoch": 1.01, + "learning_rate": 3.4625560892133786e-05, + "loss": 4.015, + "step": 939008 + }, + { + "epoch": 1.01, + "learning_rate": 3.4617174944623266e-05, + "loss": 4.0067, + "step": 939520 + }, + { + "epoch": 1.01, + "learning_rate": 3.4608788997112746e-05, + "loss": 4.0192, + "step": 940032 + }, + { + "epoch": 1.01, + "learning_rate": 3.4600403049602225e-05, + "loss": 4.0106, + "step": 940544 + }, + { + "epoch": 1.01, + "learning_rate": 3.4592017102091705e-05, + "loss": 3.9856, + "step": 941056 + }, + { + "epoch": 1.01, + "learning_rate": 3.4583631154581185e-05, + "loss": 4.0034, + "step": 941568 + }, + { + "epoch": 1.01, + "learning_rate": 3.4575245207070665e-05, + "loss": 4.0002, + "step": 942080 + }, + { + "epoch": 1.01, + "learning_rate": 3.4566892017167604e-05, + "loss": 4.0105, + "step": 942592 + }, + { + "epoch": 1.01, + "learning_rate": 3.455850606965709e-05, + "loss": 4.0015, + "step": 943104 + }, + { + "epoch": 1.01, + "learning_rate": 3.455012012214657e-05, + "loss": 4.0069, + "step": 943616 + }, + { + "epoch": 1.01, + "learning_rate": 3.454173417463605e-05, + "loss": 3.9886, + "step": 944128 + }, + { + "epoch": 1.01, + "learning_rate": 3.453334822712553e-05, + "loss": 4.0076, + "step": 944640 + }, + { + "epoch": 1.01, + "learning_rate": 3.452496227961501e-05, + "loss": 3.9957, + "step": 945152 + }, + { + "epoch": 1.01, + "learning_rate": 3.451657633210449e-05, + "loss": 4.0102, + "step": 945664 + }, + { + "epoch": 1.01, + "learning_rate": 3.450819038459397e-05, + "loss": 3.9906, + "step": 946176 + }, + { + "epoch": 1.01, + "learning_rate": 3.449982081588718e-05, + "loss": 3.9988, + "step": 946688 + }, + { + "epoch": 1.01, + "learning_rate": 3.449143486837666e-05, + "loss": 4.0019, + "step": 947200 + }, + { + "epoch": 1.01, + "learning_rate": 3.448304892086614e-05, + "loss": 3.9951, + "step": 947712 + }, + { + "epoch": 1.01, + "learning_rate": 3.447467935215935e-05, + "loss": 4.0007, + "step": 948224 + }, + { + "epoch": 1.01, + "learning_rate": 3.446629340464883e-05, + "loss": 4.005, + "step": 948736 + }, + { + "epoch": 1.01, + "learning_rate": 3.445790745713831e-05, + "loss": 4.0086, + "step": 949248 + }, + { + "epoch": 1.01, + "learning_rate": 3.444952150962779e-05, + "loss": 3.9923, + "step": 949760 + }, + { + "epoch": 1.01, + "learning_rate": 3.4441135562117275e-05, + "loss": 3.9984, + "step": 950272 + }, + { + "epoch": 1.01, + "learning_rate": 3.4432749614606755e-05, + "loss": 3.9956, + "step": 950784 + }, + { + "epoch": 1.01, + "learning_rate": 3.4424363667096235e-05, + "loss": 3.9992, + "step": 951296 + }, + { + "epoch": 1.01, + "learning_rate": 3.441597771958571e-05, + "loss": 3.9962, + "step": 951808 + }, + { + "epoch": 1.01, + "learning_rate": 3.440762452968265e-05, + "loss": 4.0102, + "step": 952320 + }, + { + "epoch": 1.01, + "learning_rate": 3.439923858217213e-05, + "loss": 3.9987, + "step": 952832 + }, + { + "epoch": 1.01, + "learning_rate": 3.439085263466161e-05, + "loss": 4.0202, + "step": 953344 + }, + { + "epoch": 1.01, + "learning_rate": 3.438246668715109e-05, + "loss": 4.0147, + "step": 953856 + }, + { + "epoch": 1.01, + "learning_rate": 3.43740971184443e-05, + "loss": 4.0079, + "step": 954368 + }, + { + "epoch": 1.01, + "learning_rate": 3.436571117093378e-05, + "loss": 4.003, + "step": 954880 + }, + { + "epoch": 1.01, + "learning_rate": 3.435732522342326e-05, + "loss": 3.9965, + "step": 955392 + }, + { + "epoch": 1.01, + "learning_rate": 3.434893927591274e-05, + "loss": 3.9952, + "step": 955904 + }, + { + "epoch": 1.01, + "learning_rate": 3.434055332840223e-05, + "loss": 4.0077, + "step": 956416 + }, + { + "epoch": 1.01, + "learning_rate": 3.433216738089171e-05, + "loss": 4.0143, + "step": 956928 + }, + { + "epoch": 1.01, + "learning_rate": 3.432378143338118e-05, + "loss": 4.0088, + "step": 957440 + }, + { + "epoch": 1.01, + "learning_rate": 3.431539548587066e-05, + "loss": 3.9937, + "step": 957952 + }, + { + "epoch": 1.01, + "learning_rate": 3.430700953836014e-05, + "loss": 4.0015, + "step": 958464 + }, + { + "epoch": 1.01, + "learning_rate": 3.429863996965336e-05, + "loss": 3.9877, + "step": 958976 + }, + { + "epoch": 1.01, + "learning_rate": 3.4290270400946566e-05, + "loss": 4.0045, + "step": 959488 + }, + { + "epoch": 1.01, + "learning_rate": 3.4281884453436046e-05, + "loss": 3.9938, + "step": 960000 + }, + { + "epoch": 1.01, + "learning_rate": 3.4273498505925526e-05, + "loss": 4.0001, + "step": 960512 + }, + { + "epoch": 1.01, + "learning_rate": 3.4265112558415006e-05, + "loss": 4.0112, + "step": 961024 + }, + { + "epoch": 1.01, + "learning_rate": 3.425672661090448e-05, + "loss": 4.0055, + "step": 961536 + }, + { + "epoch": 1.02, + "learning_rate": 3.4248340663393966e-05, + "loss": 3.9932, + "step": 962048 + }, + { + "epoch": 1.02, + "learning_rate": 3.423997109468718e-05, + "loss": 4.0013, + "step": 962560 + }, + { + "epoch": 1.02, + "learning_rate": 3.4231585147176655e-05, + "loss": 4.0091, + "step": 963072 + }, + { + "epoch": 1.02, + "learning_rate": 3.4223199199666135e-05, + "loss": 3.9926, + "step": 963584 + }, + { + "epoch": 1.02, + "learning_rate": 3.4214813252155615e-05, + "loss": 3.9916, + "step": 964096 + }, + { + "epoch": 1.02, + "learning_rate": 3.420644368344883e-05, + "loss": 4.004, + "step": 964608 + }, + { + "epoch": 1.02, + "learning_rate": 3.4198057735938304e-05, + "loss": 4.0097, + "step": 965120 + }, + { + "epoch": 1.02, + "learning_rate": 3.4189671788427784e-05, + "loss": 4.0113, + "step": 965632 + }, + { + "epoch": 1.02, + "learning_rate": 3.4181285840917264e-05, + "loss": 4.0004, + "step": 966144 + }, + { + "epoch": 1.02, + "learning_rate": 3.4172899893406744e-05, + "loss": 4.009, + "step": 966656 + }, + { + "epoch": 1.02, + "learning_rate": 3.416453032469995e-05, + "loss": 3.9913, + "step": 967168 + }, + { + "epoch": 1.02, + "learning_rate": 3.415614437718943e-05, + "loss": 4.0048, + "step": 967680 + }, + { + "epoch": 1.02, + "learning_rate": 3.414775842967892e-05, + "loss": 4.0027, + "step": 968192 + }, + { + "epoch": 1.02, + "learning_rate": 3.41393724821684e-05, + "loss": 4.0143, + "step": 968704 + }, + { + "epoch": 1.02, + "learning_rate": 3.413100291346161e-05, + "loss": 3.9991, + "step": 969216 + }, + { + "epoch": 1.02, + "learning_rate": 3.412261696595109e-05, + "loss": 3.9962, + "step": 969728 + }, + { + "epoch": 1.02, + "learning_rate": 3.411423101844057e-05, + "loss": 3.9882, + "step": 970240 + }, + { + "epoch": 1.02, + "learning_rate": 3.410584507093005e-05, + "loss": 3.986, + "step": 970752 + }, + { + "epoch": 1.02, + "learning_rate": 3.409747550222326e-05, + "loss": 3.9938, + "step": 971264 + }, + { + "epoch": 1.02, + "learning_rate": 3.408908955471274e-05, + "loss": 4.007, + "step": 971776 + }, + { + "epoch": 1.02, + "learning_rate": 3.408070360720222e-05, + "loss": 4.0024, + "step": 972288 + }, + { + "epoch": 1.02, + "learning_rate": 3.40723176596917e-05, + "loss": 3.9877, + "step": 972800 + }, + { + "epoch": 1.02, + "learning_rate": 3.406393171218118e-05, + "loss": 3.9941, + "step": 973312 + }, + { + "epoch": 1.02, + "learning_rate": 3.405554576467066e-05, + "loss": 4.0055, + "step": 973824 + }, + { + "epoch": 1.02, + "learning_rate": 3.404715981716014e-05, + "loss": 4.0075, + "step": 974336 + }, + { + "epoch": 1.02, + "learning_rate": 3.403877386964962e-05, + "loss": 4.0066, + "step": 974848 + }, + { + "epoch": 1.02, + "learning_rate": 3.40303879221391e-05, + "loss": 3.9993, + "step": 975360 + }, + { + "epoch": 1.02, + "learning_rate": 3.4022018353432313e-05, + "loss": 3.9918, + "step": 975872 + }, + { + "epoch": 1.02, + "learning_rate": 3.401363240592179e-05, + "loss": 3.9988, + "step": 976384 + }, + { + "epoch": 1.02, + "learning_rate": 3.400524645841127e-05, + "loss": 4.009, + "step": 976896 + }, + { + "epoch": 1.02, + "learning_rate": 3.399686051090075e-05, + "loss": 3.9978, + "step": 977408 + }, + { + "epoch": 1.02, + "learning_rate": 3.398849094219396e-05, + "loss": 3.9869, + "step": 977920 + }, + { + "epoch": 1.02, + "learning_rate": 3.398010499468344e-05, + "loss": 3.9966, + "step": 978432 + }, + { + "epoch": 1.02, + "learning_rate": 3.397171904717292e-05, + "loss": 3.994, + "step": 978944 + }, + { + "epoch": 1.02, + "learning_rate": 3.396334947846613e-05, + "loss": 4.0035, + "step": 979456 + }, + { + "epoch": 1.02, + "learning_rate": 3.395496353095561e-05, + "loss": 3.9979, + "step": 979968 + }, + { + "epoch": 1.02, + "learning_rate": 3.394657758344509e-05, + "loss": 4.007, + "step": 980480 + }, + { + "epoch": 1.02, + "learning_rate": 3.393819163593457e-05, + "loss": 3.9899, + "step": 980992 + }, + { + "epoch": 1.02, + "learning_rate": 3.392982206722779e-05, + "loss": 4.0067, + "step": 981504 + }, + { + "epoch": 1.02, + "learning_rate": 3.392143611971727e-05, + "loss": 3.9944, + "step": 982016 + }, + { + "epoch": 1.02, + "learning_rate": 3.391305017220675e-05, + "loss": 4.0046, + "step": 982528 + }, + { + "epoch": 1.02, + "learning_rate": 3.390466422469623e-05, + "loss": 4.0072, + "step": 983040 + }, + { + "epoch": 1.02, + "learning_rate": 3.389627827718571e-05, + "loss": 4.0098, + "step": 983552 + }, + { + "epoch": 1.02, + "learning_rate": 3.388789232967519e-05, + "loss": 4.0037, + "step": 984064 + }, + { + "epoch": 1.02, + "learning_rate": 3.3879539139772125e-05, + "loss": 4.0088, + "step": 984576 + }, + { + "epoch": 1.02, + "learning_rate": 3.3871153192261605e-05, + "loss": 3.9868, + "step": 985088 + }, + { + "epoch": 1.02, + "learning_rate": 3.3862767244751085e-05, + "loss": 3.9907, + "step": 985600 + }, + { + "epoch": 1.02, + "learning_rate": 3.3854381297240565e-05, + "loss": 3.9959, + "step": 986112 + }, + { + "epoch": 1.02, + "learning_rate": 3.3845995349730045e-05, + "loss": 4.0061, + "step": 986624 + }, + { + "epoch": 1.02, + "learning_rate": 3.3837609402219525e-05, + "loss": 4.0097, + "step": 987136 + }, + { + "epoch": 1.02, + "learning_rate": 3.3829223454709005e-05, + "loss": 4.0038, + "step": 987648 + }, + { + "epoch": 1.02, + "learning_rate": 3.382083750719849e-05, + "loss": 4.0052, + "step": 988160 + }, + { + "epoch": 1.02, + "learning_rate": 3.3812451559687965e-05, + "loss": 3.9934, + "step": 988672 + }, + { + "epoch": 1.02, + "learning_rate": 3.380408199098118e-05, + "loss": 3.9851, + "step": 989184 + }, + { + "epoch": 1.02, + "learning_rate": 3.379569604347066e-05, + "loss": 4.0008, + "step": 989696 + }, + { + "epoch": 1.02, + "learning_rate": 3.378731009596014e-05, + "loss": 4.0062, + "step": 990208 + }, + { + "epoch": 1.02, + "learning_rate": 3.3778924148449614e-05, + "loss": 4.0134, + "step": 990720 + }, + { + "epoch": 1.02, + "learning_rate": 3.3770538200939094e-05, + "loss": 3.994, + "step": 991232 + }, + { + "epoch": 1.02, + "learning_rate": 3.376216863223231e-05, + "loss": 3.9911, + "step": 991744 + }, + { + "epoch": 1.03, + "eval_loss": 4.0417304039001465, + "eval_runtime": 543.7856, + "eval_samples_per_second": 701.731, + "eval_steps_per_second": 21.93, + "step": 992147 + }, + { + "epoch": 0.0, + "learning_rate": 3.375378268472178e-05, + "loss": 3.9804, + "step": 992256 + }, + { + "epoch": 0.0, + "learning_rate": 3.374539673721126e-05, + "loss": 4.014, + "step": 992768 + }, + { + "epoch": 0.0, + "learning_rate": 3.373701078970074e-05, + "loss": 3.9938, + "step": 993280 + }, + { + "epoch": 0.0, + "learning_rate": 3.372862484219023e-05, + "loss": 3.9796, + "step": 993792 + }, + { + "epoch": 0.0, + "learning_rate": 3.372023889467971e-05, + "loss": 4.0017, + "step": 994304 + }, + { + "epoch": 0.0, + "learning_rate": 3.371185294716919e-05, + "loss": 3.9957, + "step": 994816 + }, + { + "epoch": 0.0, + "learning_rate": 3.370346699965867e-05, + "loss": 4.002, + "step": 995328 + }, + { + "epoch": 0.0, + "learning_rate": 3.369508105214815e-05, + "loss": 3.9913, + "step": 995840 + }, + { + "epoch": 0.0, + "learning_rate": 3.368669510463763e-05, + "loss": 3.9929, + "step": 996352 + }, + { + "epoch": 0.0, + "learning_rate": 3.367830915712711e-05, + "loss": 3.9788, + "step": 996864 + }, + { + "epoch": 0.0, + "learning_rate": 3.366992320961659e-05, + "loss": 4.0109, + "step": 997376 + }, + { + "epoch": 0.0, + "learning_rate": 3.366153726210607e-05, + "loss": 3.9922, + "step": 997888 + }, + { + "epoch": 0.0, + "learning_rate": 3.365315131459555e-05, + "loss": 3.9991, + "step": 998400 + }, + { + "epoch": 0.0, + "learning_rate": 3.364476536708503e-05, + "loss": 4.0065, + "step": 998912 + }, + { + "epoch": 0.0, + "learning_rate": 3.36363794195745e-05, + "loss": 3.994, + "step": 999424 + }, + { + "epoch": 0.0, + "learning_rate": 3.362799347206398e-05, + "loss": 3.9857, + "step": 999936 + }, + { + "epoch": 0.0, + "learning_rate": 3.361960752455346e-05, + "loss": 4.0058, + "step": 1000448 + }, + { + "epoch": 0.0, + "learning_rate": 3.361123795584668e-05, + "loss": 3.9968, + "step": 1000960 + }, + { + "epoch": 0.0, + "learning_rate": 3.360285200833616e-05, + "loss": 3.9911, + "step": 1001472 + }, + { + "epoch": 0.0, + "learning_rate": 3.359446606082564e-05, + "loss": 4.0103, + "step": 1001984 + }, + { + "epoch": 0.0, + "learning_rate": 3.358608011331512e-05, + "loss": 4.0172, + "step": 1002496 + }, + { + "epoch": 0.0, + "learning_rate": 3.35776941658046e-05, + "loss": 4.0007, + "step": 1003008 + }, + { + "epoch": 0.0, + "learning_rate": 3.356930821829408e-05, + "loss": 3.9892, + "step": 1003520 + }, + { + "epoch": 0.0, + "learning_rate": 3.356092227078356e-05, + "loss": 3.9975, + "step": 1004032 + }, + { + "epoch": 0.0, + "learning_rate": 3.355253632327304e-05, + "loss": 3.9933, + "step": 1004544 + }, + { + "epoch": 0.0, + "learning_rate": 3.354416675456625e-05, + "loss": 3.9876, + "step": 1005056 + }, + { + "epoch": 0.0, + "learning_rate": 3.353578080705573e-05, + "loss": 3.9961, + "step": 1005568 + }, + { + "epoch": 0.0, + "learning_rate": 3.352739485954521e-05, + "loss": 3.9909, + "step": 1006080 + }, + { + "epoch": 0.0, + "learning_rate": 3.3519008912034687e-05, + "loss": 3.9954, + "step": 1006592 + }, + { + "epoch": 0.0, + "learning_rate": 3.3510639343327896e-05, + "loss": 4.0024, + "step": 1007104 + }, + { + "epoch": 0.01, + "learning_rate": 3.3502253395817376e-05, + "loss": 4.0018, + "step": 1007616 + }, + { + "epoch": 0.01, + "learning_rate": 3.349386744830686e-05, + "loss": 3.9974, + "step": 1008128 + }, + { + "epoch": 0.01, + "learning_rate": 3.348549787960007e-05, + "loss": 3.9967, + "step": 1008640 + }, + { + "epoch": 0.01, + "learning_rate": 3.347711193208955e-05, + "loss": 4.0064, + "step": 1009152 + }, + { + "epoch": 0.01, + "learning_rate": 3.346872598457903e-05, + "loss": 3.9866, + "step": 1009664 + }, + { + "epoch": 0.01, + "learning_rate": 3.346034003706851e-05, + "loss": 3.9925, + "step": 1010176 + }, + { + "epoch": 0.01, + "learning_rate": 3.345195408955799e-05, + "loss": 3.9902, + "step": 1010688 + }, + { + "epoch": 0.01, + "learning_rate": 3.34435845208512e-05, + "loss": 4.0042, + "step": 1011200 + }, + { + "epoch": 0.01, + "learning_rate": 3.343519857334068e-05, + "loss": 4.0051, + "step": 1011712 + }, + { + "epoch": 0.01, + "learning_rate": 3.342681262583016e-05, + "loss": 4.0077, + "step": 1012224 + }, + { + "epoch": 0.01, + "learning_rate": 3.341842667831964e-05, + "loss": 4.0003, + "step": 1012736 + }, + { + "epoch": 0.01, + "learning_rate": 3.341004073080912e-05, + "loss": 3.9993, + "step": 1013248 + }, + { + "epoch": 0.01, + "learning_rate": 3.34016547832986e-05, + "loss": 3.9896, + "step": 1013760 + }, + { + "epoch": 0.01, + "learning_rate": 3.339326883578808e-05, + "loss": 3.9896, + "step": 1014272 + }, + { + "epoch": 0.01, + "learning_rate": 3.338488288827756e-05, + "loss": 3.9856, + "step": 1014784 + }, + { + "epoch": 0.01, + "learning_rate": 3.3376513319570776e-05, + "loss": 3.9821, + "step": 1015296 + }, + { + "epoch": 0.01, + "learning_rate": 3.3368127372060256e-05, + "loss": 3.9883, + "step": 1015808 + }, + { + "epoch": 0.01, + "learning_rate": 3.3359741424549736e-05, + "loss": 3.9946, + "step": 1016320 + }, + { + "epoch": 0.01, + "learning_rate": 3.3351355477039216e-05, + "loss": 3.9925, + "step": 1016832 + }, + { + "epoch": 0.01, + "learning_rate": 3.3342985908332425e-05, + "loss": 3.9945, + "step": 1017344 + }, + { + "epoch": 0.01, + "learning_rate": 3.3334616339625634e-05, + "loss": 3.9828, + "step": 1017856 + }, + { + "epoch": 0.01, + "learning_rate": 3.3326230392115114e-05, + "loss": 3.994, + "step": 1018368 + }, + { + "epoch": 0.01, + "learning_rate": 3.3317844444604594e-05, + "loss": 3.9932, + "step": 1018880 + }, + { + "epoch": 0.01, + "learning_rate": 3.3309458497094074e-05, + "loss": 3.9784, + "step": 1019392 + }, + { + "epoch": 0.01, + "learning_rate": 3.3301072549583554e-05, + "loss": 3.9791, + "step": 1019904 + }, + { + "epoch": 0.01, + "learning_rate": 3.329270298087677e-05, + "loss": 3.9891, + "step": 1020416 + }, + { + "epoch": 0.01, + "learning_rate": 3.328431703336625e-05, + "loss": 4.0014, + "step": 1020928 + }, + { + "epoch": 0.01, + "learning_rate": 3.327593108585573e-05, + "loss": 3.9738, + "step": 1021440 + }, + { + "epoch": 0.01, + "learning_rate": 3.326754513834521e-05, + "loss": 3.9935, + "step": 1021952 + }, + { + "epoch": 0.01, + "learning_rate": 3.325917556963842e-05, + "loss": 3.9961, + "step": 1022464 + }, + { + "epoch": 0.01, + "learning_rate": 3.32507896221279e-05, + "loss": 3.9828, + "step": 1022976 + }, + { + "epoch": 0.01, + "learning_rate": 3.324240367461738e-05, + "loss": 3.9784, + "step": 1023488 + }, + { + "epoch": 0.01, + "learning_rate": 3.323401772710686e-05, + "loss": 3.976, + "step": 1024000 + }, + { + "epoch": 0.01, + "learning_rate": 3.322563177959633e-05, + "loss": 3.9781, + "step": 1024512 + }, + { + "epoch": 0.01, + "learning_rate": 3.321724583208581e-05, + "loss": 4.0004, + "step": 1025024 + }, + { + "epoch": 0.01, + "learning_rate": 3.320885988457529e-05, + "loss": 3.9989, + "step": 1025536 + }, + { + "epoch": 0.01, + "learning_rate": 3.320047393706477e-05, + "loss": 3.9842, + "step": 1026048 + }, + { + "epoch": 0.01, + "learning_rate": 3.319210436835799e-05, + "loss": 3.9911, + "step": 1026560 + }, + { + "epoch": 0.01, + "learning_rate": 3.318371842084747e-05, + "loss": 3.9976, + "step": 1027072 + }, + { + "epoch": 0.01, + "learning_rate": 3.317533247333695e-05, + "loss": 3.9831, + "step": 1027584 + }, + { + "epoch": 0.01, + "learning_rate": 3.316696290463016e-05, + "loss": 3.9988, + "step": 1028096 + }, + { + "epoch": 0.01, + "learning_rate": 3.3158576957119636e-05, + "loss": 3.99, + "step": 1028608 + }, + { + "epoch": 0.01, + "learning_rate": 3.3150191009609116e-05, + "loss": 3.9895, + "step": 1029120 + }, + { + "epoch": 0.01, + "learning_rate": 3.3141805062098596e-05, + "loss": 3.984, + "step": 1029632 + }, + { + "epoch": 0.01, + "learning_rate": 3.3133419114588076e-05, + "loss": 4.0002, + "step": 1030144 + }, + { + "epoch": 0.01, + "learning_rate": 3.3125033167077556e-05, + "loss": 3.9874, + "step": 1030656 + }, + { + "epoch": 0.01, + "learning_rate": 3.31166799771745e-05, + "loss": 3.9971, + "step": 1031168 + }, + { + "epoch": 0.01, + "learning_rate": 3.310829402966398e-05, + "loss": 3.9932, + "step": 1031680 + }, + { + "epoch": 0.01, + "learning_rate": 3.309990808215346e-05, + "loss": 3.9921, + "step": 1032192 + }, + { + "epoch": 0.01, + "learning_rate": 3.309152213464294e-05, + "loss": 3.9867, + "step": 1032704 + }, + { + "epoch": 0.01, + "learning_rate": 3.308313618713242e-05, + "loss": 3.9938, + "step": 1033216 + }, + { + "epoch": 0.01, + "learning_rate": 3.30747502396219e-05, + "loss": 3.9842, + "step": 1033728 + }, + { + "epoch": 0.01, + "learning_rate": 3.306636429211138e-05, + "loss": 3.9841, + "step": 1034240 + }, + { + "epoch": 0.01, + "learning_rate": 3.305797834460086e-05, + "loss": 3.9856, + "step": 1034752 + }, + { + "epoch": 0.01, + "learning_rate": 3.304959239709034e-05, + "loss": 3.9775, + "step": 1035264 + }, + { + "epoch": 0.01, + "learning_rate": 3.304120644957982e-05, + "loss": 3.9927, + "step": 1035776 + }, + { + "epoch": 0.01, + "learning_rate": 3.303283688087303e-05, + "loss": 3.98, + "step": 1036288 + }, + { + "epoch": 0.01, + "learning_rate": 3.302446731216624e-05, + "loss": 3.9895, + "step": 1036800 + }, + { + "epoch": 0.01, + "learning_rate": 3.301608136465572e-05, + "loss": 3.9756, + "step": 1037312 + }, + { + "epoch": 0.01, + "learning_rate": 3.30076954171452e-05, + "loss": 3.995, + "step": 1037824 + }, + { + "epoch": 0.02, + "learning_rate": 3.299930946963468e-05, + "loss": 3.9941, + "step": 1038336 + }, + { + "epoch": 0.02, + "learning_rate": 3.299092352212416e-05, + "loss": 3.9945, + "step": 1038848 + }, + { + "epoch": 0.02, + "learning_rate": 3.2982537574613646e-05, + "loss": 3.9927, + "step": 1039360 + }, + { + "epoch": 0.02, + "learning_rate": 3.2974168005906855e-05, + "loss": 3.979, + "step": 1039872 + }, + { + "epoch": 0.02, + "learning_rate": 3.2965782058396335e-05, + "loss": 3.9922, + "step": 1040384 + }, + { + "epoch": 0.02, + "learning_rate": 3.2957396110885815e-05, + "loss": 3.9856, + "step": 1040896 + }, + { + "epoch": 0.02, + "learning_rate": 3.2949010163375295e-05, + "loss": 3.9858, + "step": 1041408 + }, + { + "epoch": 0.02, + "learning_rate": 3.2940624215864775e-05, + "loss": 3.9767, + "step": 1041920 + }, + { + "epoch": 0.02, + "learning_rate": 3.2932238268354254e-05, + "loss": 3.9828, + "step": 1042432 + }, + { + "epoch": 0.02, + "learning_rate": 3.2923852320843734e-05, + "loss": 3.9962, + "step": 1042944 + }, + { + "epoch": 0.02, + "learning_rate": 3.2915466373333214e-05, + "loss": 3.9883, + "step": 1043456 + }, + { + "epoch": 0.02, + "learning_rate": 3.2907080425822694e-05, + "loss": 3.9992, + "step": 1043968 + }, + { + "epoch": 0.02, + "learning_rate": 3.289869447831217e-05, + "loss": 3.9877, + "step": 1044480 + }, + { + "epoch": 0.02, + "learning_rate": 3.289030853080165e-05, + "loss": 3.9872, + "step": 1044992 + }, + { + "epoch": 0.02, + "learning_rate": 3.288192258329113e-05, + "loss": 3.9796, + "step": 1045504 + }, + { + "epoch": 0.02, + "learning_rate": 3.287355301458434e-05, + "loss": 3.9825, + "step": 1046016 + }, + { + "epoch": 0.02, + "learning_rate": 3.286518344587756e-05, + "loss": 3.9932, + "step": 1046528 + }, + { + "epoch": 0.02, + "learning_rate": 3.285679749836704e-05, + "loss": 3.993, + "step": 1047040 + }, + { + "epoch": 0.02, + "learning_rate": 3.284841155085652e-05, + "loss": 3.9811, + "step": 1047552 + }, + { + "epoch": 0.02, + "learning_rate": 3.284002560334599e-05, + "loss": 3.9753, + "step": 1048064 + }, + { + "epoch": 0.02, + "learning_rate": 3.283163965583547e-05, + "loss": 3.9884, + "step": 1048576 + }, + { + "epoch": 0.02, + "learning_rate": 3.282325370832495e-05, + "loss": 3.9908, + "step": 1049088 + }, + { + "epoch": 0.02, + "learning_rate": 3.281486776081443e-05, + "loss": 3.974, + "step": 1049600 + }, + { + "epoch": 0.02, + "learning_rate": 3.280649819210764e-05, + "loss": 3.9879, + "step": 1050112 + }, + { + "epoch": 0.02, + "learning_rate": 3.279811224459712e-05, + "loss": 3.9809, + "step": 1050624 + }, + { + "epoch": 0.02, + "learning_rate": 3.27897262970866e-05, + "loss": 3.9821, + "step": 1051136 + }, + { + "epoch": 0.02, + "learning_rate": 3.278135672837982e-05, + "loss": 3.9757, + "step": 1051648 + }, + { + "epoch": 0.02, + "learning_rate": 3.27729707808693e-05, + "loss": 3.9901, + "step": 1052160 + }, + { + "epoch": 0.02, + "learning_rate": 3.276458483335878e-05, + "loss": 3.9872, + "step": 1052672 + }, + { + "epoch": 0.02, + "learning_rate": 3.275619888584826e-05, + "loss": 3.9829, + "step": 1053184 + }, + { + "epoch": 0.02, + "learning_rate": 3.274781293833774e-05, + "loss": 3.9952, + "step": 1053696 + }, + { + "epoch": 0.02, + "learning_rate": 3.273942699082722e-05, + "loss": 4.0018, + "step": 1054208 + }, + { + "epoch": 0.02, + "learning_rate": 3.27310410433167e-05, + "loss": 3.9868, + "step": 1054720 + }, + { + "epoch": 0.02, + "learning_rate": 3.2722671474609906e-05, + "loss": 3.9891, + "step": 1055232 + }, + { + "epoch": 0.02, + "learning_rate": 3.2714301905903115e-05, + "loss": 3.9866, + "step": 1055744 + }, + { + "epoch": 0.02, + "learning_rate": 3.2705915958392595e-05, + "loss": 3.9877, + "step": 1056256 + }, + { + "epoch": 0.02, + "learning_rate": 3.2697530010882075e-05, + "loss": 3.9866, + "step": 1056768 + }, + { + "epoch": 0.02, + "learning_rate": 3.2689144063371555e-05, + "loss": 3.982, + "step": 1057280 + }, + { + "epoch": 0.02, + "learning_rate": 3.2680758115861035e-05, + "loss": 3.9888, + "step": 1057792 + }, + { + "epoch": 0.02, + "learning_rate": 3.2672372168350515e-05, + "loss": 3.982, + "step": 1058304 + }, + { + "epoch": 0.02, + "learning_rate": 3.266398622084e-05, + "loss": 4.0006, + "step": 1058816 + }, + { + "epoch": 0.02, + "learning_rate": 3.265560027332948e-05, + "loss": 3.9831, + "step": 1059328 + }, + { + "epoch": 0.02, + "learning_rate": 3.264723070462269e-05, + "loss": 4.0003, + "step": 1059840 + }, + { + "epoch": 0.02, + "learning_rate": 3.26388611359159e-05, + "loss": 3.9848, + "step": 1060352 + }, + { + "epoch": 0.02, + "learning_rate": 3.263047518840538e-05, + "loss": 3.9912, + "step": 1060864 + }, + { + "epoch": 0.02, + "learning_rate": 3.262208924089486e-05, + "loss": 3.9855, + "step": 1061376 + }, + { + "epoch": 0.02, + "learning_rate": 3.261370329338434e-05, + "loss": 3.9897, + "step": 1061888 + }, + { + "epoch": 0.02, + "learning_rate": 3.260531734587382e-05, + "loss": 3.999, + "step": 1062400 + }, + { + "epoch": 0.02, + "learning_rate": 3.25969313983633e-05, + "loss": 3.9847, + "step": 1062912 + }, + { + "epoch": 0.02, + "learning_rate": 3.258854545085278e-05, + "loss": 3.9884, + "step": 1063424 + }, + { + "epoch": 0.02, + "learning_rate": 3.2580192260949724e-05, + "loss": 3.9919, + "step": 1063936 + }, + { + "epoch": 0.02, + "learning_rate": 3.2571806313439204e-05, + "loss": 3.9836, + "step": 1064448 + }, + { + "epoch": 0.02, + "learning_rate": 3.2563420365928684e-05, + "loss": 3.9856, + "step": 1064960 + }, + { + "epoch": 0.02, + "learning_rate": 3.2555034418418164e-05, + "loss": 3.9917, + "step": 1065472 + }, + { + "epoch": 0.02, + "learning_rate": 3.2546648470907644e-05, + "loss": 3.9853, + "step": 1065984 + }, + { + "epoch": 0.02, + "learning_rate": 3.2538262523397124e-05, + "loss": 3.9865, + "step": 1066496 + }, + { + "epoch": 0.02, + "learning_rate": 3.2529876575886604e-05, + "loss": 3.9901, + "step": 1067008 + }, + { + "epoch": 0.02, + "learning_rate": 3.2521490628376084e-05, + "loss": 3.9823, + "step": 1067520 + }, + { + "epoch": 0.02, + "learning_rate": 3.2513104680865564e-05, + "loss": 3.9793, + "step": 1068032 + }, + { + "epoch": 0.03, + "eval_loss": 4.03324556350708, + "eval_runtime": 299.846, + "eval_samples_per_second": 1272.623, + "eval_steps_per_second": 39.77, + "step": 1068467 + }, + { + "epoch": 1.0, + "learning_rate": 3.2504718733355044e-05, + "loss": 3.9832, + "step": 1068544 + }, + { + "epoch": 1.0, + "learning_rate": 3.2496332785844524e-05, + "loss": 4.0008, + "step": 1069056 + }, + { + "epoch": 1.0, + "learning_rate": 3.248796321713773e-05, + "loss": 3.9828, + "step": 1069568 + }, + { + "epoch": 1.0, + "learning_rate": 3.247957726962721e-05, + "loss": 3.9645, + "step": 1070080 + }, + { + "epoch": 1.0, + "learning_rate": 3.247119132211669e-05, + "loss": 3.9836, + "step": 1070592 + }, + { + "epoch": 1.0, + "learning_rate": 3.246280537460617e-05, + "loss": 3.9851, + "step": 1071104 + }, + { + "epoch": 1.0, + "learning_rate": 3.245441942709565e-05, + "loss": 3.9865, + "step": 1071616 + }, + { + "epoch": 1.0, + "learning_rate": 3.244604985838887e-05, + "loss": 3.978, + "step": 1072128 + }, + { + "epoch": 1.0, + "learning_rate": 3.243766391087835e-05, + "loss": 3.975, + "step": 1072640 + }, + { + "epoch": 1.0, + "learning_rate": 3.242927796336783e-05, + "loss": 3.9723, + "step": 1073152 + }, + { + "epoch": 1.0, + "learning_rate": 3.24208920158573e-05, + "loss": 3.9928, + "step": 1073664 + }, + { + "epoch": 1.0, + "learning_rate": 3.241250606834678e-05, + "loss": 3.9767, + "step": 1074176 + }, + { + "epoch": 1.0, + "learning_rate": 3.240412012083626e-05, + "loss": 3.9872, + "step": 1074688 + }, + { + "epoch": 1.0, + "learning_rate": 3.239573417332574e-05, + "loss": 3.9907, + "step": 1075200 + }, + { + "epoch": 1.0, + "learning_rate": 3.238734822581522e-05, + "loss": 3.984, + "step": 1075712 + }, + { + "epoch": 1.0, + "learning_rate": 3.237897865710843e-05, + "loss": 3.9713, + "step": 1076224 + }, + { + "epoch": 1.0, + "learning_rate": 3.237059270959791e-05, + "loss": 3.9891, + "step": 1076736 + }, + { + "epoch": 1.0, + "learning_rate": 3.2362223140891127e-05, + "loss": 3.9836, + "step": 1077248 + }, + { + "epoch": 1.0, + "learning_rate": 3.2353837193380606e-05, + "loss": 3.9743, + "step": 1077760 + }, + { + "epoch": 1.0, + "learning_rate": 3.2345451245870086e-05, + "loss": 3.994, + "step": 1078272 + }, + { + "epoch": 1.0, + "learning_rate": 3.2337065298359566e-05, + "loss": 4.0048, + "step": 1078784 + }, + { + "epoch": 1.0, + "learning_rate": 3.2328695729652775e-05, + "loss": 3.9896, + "step": 1079296 + }, + { + "epoch": 1.0, + "learning_rate": 3.2320309782142255e-05, + "loss": 3.9751, + "step": 1079808 + }, + { + "epoch": 1.0, + "learning_rate": 3.2311923834631735e-05, + "loss": 3.983, + "step": 1080320 + }, + { + "epoch": 1.0, + "learning_rate": 3.2303537887121215e-05, + "loss": 3.9789, + "step": 1080832 + }, + { + "epoch": 1.0, + "learning_rate": 3.2295151939610695e-05, + "loss": 3.9768, + "step": 1081344 + }, + { + "epoch": 1.0, + "learning_rate": 3.2286765992100175e-05, + "loss": 3.9821, + "step": 1081856 + }, + { + "epoch": 1.0, + "learning_rate": 3.2278380044589655e-05, + "loss": 3.9766, + "step": 1082368 + }, + { + "epoch": 1.0, + "learning_rate": 3.2269994097079135e-05, + "loss": 3.9775, + "step": 1082880 + }, + { + "epoch": 1.0, + "learning_rate": 3.2261624528372344e-05, + "loss": 3.9904, + "step": 1083392 + }, + { + "epoch": 1.01, + "learning_rate": 3.225325495966556e-05, + "loss": 3.9852, + "step": 1083904 + }, + { + "epoch": 1.01, + "learning_rate": 3.224486901215504e-05, + "loss": 3.9872, + "step": 1084416 + }, + { + "epoch": 1.01, + "learning_rate": 3.223648306464452e-05, + "loss": 3.9835, + "step": 1084928 + }, + { + "epoch": 1.01, + "learning_rate": 3.2228097117134e-05, + "loss": 3.9895, + "step": 1085440 + }, + { + "epoch": 1.01, + "learning_rate": 3.221971116962348e-05, + "loss": 3.9706, + "step": 1085952 + }, + { + "epoch": 1.01, + "learning_rate": 3.221132522211296e-05, + "loss": 3.9813, + "step": 1086464 + }, + { + "epoch": 1.01, + "learning_rate": 3.220293927460244e-05, + "loss": 3.9747, + "step": 1086976 + }, + { + "epoch": 1.01, + "learning_rate": 3.219456970589565e-05, + "loss": 3.9964, + "step": 1087488 + }, + { + "epoch": 1.01, + "learning_rate": 3.218618375838513e-05, + "loss": 3.9869, + "step": 1088000 + }, + { + "epoch": 1.01, + "learning_rate": 3.217779781087461e-05, + "loss": 3.9959, + "step": 1088512 + }, + { + "epoch": 1.01, + "learning_rate": 3.216941186336409e-05, + "loss": 3.9902, + "step": 1089024 + }, + { + "epoch": 1.01, + "learning_rate": 3.216102591585357e-05, + "loss": 3.9815, + "step": 1089536 + }, + { + "epoch": 1.01, + "learning_rate": 3.215263996834305e-05, + "loss": 3.9773, + "step": 1090048 + }, + { + "epoch": 1.01, + "learning_rate": 3.214425402083253e-05, + "loss": 3.9739, + "step": 1090560 + }, + { + "epoch": 1.01, + "learning_rate": 3.213586807332201e-05, + "loss": 3.9751, + "step": 1091072 + }, + { + "epoch": 1.01, + "learning_rate": 3.2127514883418954e-05, + "loss": 3.9661, + "step": 1091584 + }, + { + "epoch": 1.01, + "learning_rate": 3.2119128935908434e-05, + "loss": 3.9762, + "step": 1092096 + }, + { + "epoch": 1.01, + "learning_rate": 3.2110742988397914e-05, + "loss": 3.9798, + "step": 1092608 + }, + { + "epoch": 1.01, + "learning_rate": 3.2102357040887394e-05, + "loss": 3.9784, + "step": 1093120 + }, + { + "epoch": 1.01, + "learning_rate": 3.2093971093376874e-05, + "loss": 3.9803, + "step": 1093632 + }, + { + "epoch": 1.01, + "learning_rate": 3.2085585145866353e-05, + "loss": 3.9707, + "step": 1094144 + }, + { + "epoch": 1.01, + "learning_rate": 3.2077199198355833e-05, + "loss": 3.9782, + "step": 1094656 + }, + { + "epoch": 1.01, + "learning_rate": 3.206882962964904e-05, + "loss": 3.9842, + "step": 1095168 + }, + { + "epoch": 1.01, + "learning_rate": 3.206044368213852e-05, + "loss": 3.955, + "step": 1095680 + }, + { + "epoch": 1.01, + "learning_rate": 3.2052057734628e-05, + "loss": 3.9722, + "step": 1096192 + }, + { + "epoch": 1.01, + "learning_rate": 3.204368816592122e-05, + "loss": 3.9707, + "step": 1096704 + }, + { + "epoch": 1.01, + "learning_rate": 3.20353022184107e-05, + "loss": 3.9918, + "step": 1097216 + }, + { + "epoch": 1.01, + "learning_rate": 3.202691627090018e-05, + "loss": 3.9581, + "step": 1097728 + }, + { + "epoch": 1.01, + "learning_rate": 3.201853032338966e-05, + "loss": 3.9817, + "step": 1098240 + }, + { + "epoch": 1.01, + "learning_rate": 3.201016075468287e-05, + "loss": 3.9775, + "step": 1098752 + }, + { + "epoch": 1.01, + "learning_rate": 3.200177480717235e-05, + "loss": 3.9712, + "step": 1099264 + }, + { + "epoch": 1.01, + "learning_rate": 3.199338885966183e-05, + "loss": 3.9703, + "step": 1099776 + }, + { + "epoch": 1.01, + "learning_rate": 3.198500291215131e-05, + "loss": 3.9608, + "step": 1100288 + }, + { + "epoch": 1.01, + "learning_rate": 3.197661696464079e-05, + "loss": 3.9635, + "step": 1100800 + }, + { + "epoch": 1.01, + "learning_rate": 3.196823101713026e-05, + "loss": 3.987, + "step": 1101312 + }, + { + "epoch": 1.01, + "learning_rate": 3.195984506961974e-05, + "loss": 3.9828, + "step": 1101824 + }, + { + "epoch": 1.01, + "learning_rate": 3.195145912210922e-05, + "loss": 3.9714, + "step": 1102336 + }, + { + "epoch": 1.01, + "learning_rate": 3.19430731745987e-05, + "loss": 3.9805, + "step": 1102848 + }, + { + "epoch": 1.01, + "learning_rate": 3.1934703605891916e-05, + "loss": 3.9807, + "step": 1103360 + }, + { + "epoch": 1.01, + "learning_rate": 3.1926317658381396e-05, + "loss": 3.9726, + "step": 1103872 + }, + { + "epoch": 1.01, + "learning_rate": 3.1917931710870876e-05, + "loss": 3.98, + "step": 1104384 + }, + { + "epoch": 1.01, + "learning_rate": 3.1909545763360356e-05, + "loss": 3.9786, + "step": 1104896 + }, + { + "epoch": 1.01, + "learning_rate": 3.1901159815849836e-05, + "loss": 3.9711, + "step": 1105408 + }, + { + "epoch": 1.01, + "learning_rate": 3.1892773868339316e-05, + "loss": 3.9726, + "step": 1105920 + }, + { + "epoch": 1.01, + "learning_rate": 3.1884387920828796e-05, + "loss": 3.9856, + "step": 1106432 + }, + { + "epoch": 1.01, + "learning_rate": 3.1876018352122005e-05, + "loss": 3.9775, + "step": 1106944 + }, + { + "epoch": 1.01, + "learning_rate": 3.1867632404611485e-05, + "loss": 3.9855, + "step": 1107456 + }, + { + "epoch": 1.01, + "learning_rate": 3.1859246457100965e-05, + "loss": 3.9806, + "step": 1107968 + }, + { + "epoch": 1.01, + "learning_rate": 3.1850860509590445e-05, + "loss": 3.9764, + "step": 1108480 + }, + { + "epoch": 1.01, + "learning_rate": 3.1842490940883654e-05, + "loss": 3.9703, + "step": 1108992 + }, + { + "epoch": 1.01, + "learning_rate": 3.183410499337314e-05, + "loss": 3.9793, + "step": 1109504 + }, + { + "epoch": 1.01, + "learning_rate": 3.182571904586262e-05, + "loss": 3.9727, + "step": 1110016 + }, + { + "epoch": 1.01, + "learning_rate": 3.18173330983521e-05, + "loss": 3.9689, + "step": 1110528 + }, + { + "epoch": 1.01, + "learning_rate": 3.180894715084158e-05, + "loss": 3.9749, + "step": 1111040 + }, + { + "epoch": 1.01, + "learning_rate": 3.180056120333106e-05, + "loss": 3.9652, + "step": 1111552 + }, + { + "epoch": 1.01, + "learning_rate": 3.179219163462427e-05, + "loss": 3.9762, + "step": 1112064 + }, + { + "epoch": 1.01, + "learning_rate": 3.178380568711375e-05, + "loss": 3.9668, + "step": 1112576 + }, + { + "epoch": 1.01, + "learning_rate": 3.177541973960323e-05, + "loss": 3.9762, + "step": 1113088 + }, + { + "epoch": 1.01, + "learning_rate": 3.176703379209271e-05, + "loss": 3.9618, + "step": 1113600 + }, + { + "epoch": 1.01, + "learning_rate": 3.175864784458219e-05, + "loss": 3.9798, + "step": 1114112 + }, + { + "epoch": 1.02, + "learning_rate": 3.175026189707167e-05, + "loss": 3.9824, + "step": 1114624 + }, + { + "epoch": 1.02, + "learning_rate": 3.174187594956115e-05, + "loss": 3.9798, + "step": 1115136 + }, + { + "epoch": 1.02, + "learning_rate": 3.173349000205062e-05, + "loss": 3.9778, + "step": 1115648 + }, + { + "epoch": 1.02, + "learning_rate": 3.172512043334384e-05, + "loss": 3.9688, + "step": 1116160 + }, + { + "epoch": 1.02, + "learning_rate": 3.171673448583332e-05, + "loss": 3.9729, + "step": 1116672 + }, + { + "epoch": 1.02, + "learning_rate": 3.17083485383228e-05, + "loss": 3.9724, + "step": 1117184 + }, + { + "epoch": 1.02, + "learning_rate": 3.169996259081228e-05, + "loss": 3.9819, + "step": 1117696 + }, + { + "epoch": 1.02, + "learning_rate": 3.1691593022105494e-05, + "loss": 3.96, + "step": 1118208 + }, + { + "epoch": 1.02, + "learning_rate": 3.1683207074594974e-05, + "loss": 3.9677, + "step": 1118720 + }, + { + "epoch": 1.02, + "learning_rate": 3.167482112708445e-05, + "loss": 3.9828, + "step": 1119232 + }, + { + "epoch": 1.02, + "learning_rate": 3.166643517957393e-05, + "loss": 3.9714, + "step": 1119744 + }, + { + "epoch": 1.02, + "learning_rate": 3.165804923206341e-05, + "loss": 3.9887, + "step": 1120256 + }, + { + "epoch": 1.02, + "learning_rate": 3.164966328455289e-05, + "loss": 3.9691, + "step": 1120768 + }, + { + "epoch": 1.02, + "learning_rate": 3.164127733704237e-05, + "loss": 3.9783, + "step": 1121280 + }, + { + "epoch": 1.02, + "learning_rate": 3.163289138953185e-05, + "loss": 3.9615, + "step": 1121792 + }, + { + "epoch": 1.02, + "learning_rate": 3.1624521820825056e-05, + "loss": 3.9671, + "step": 1122304 + }, + { + "epoch": 1.02, + "learning_rate": 3.161613587331454e-05, + "loss": 3.9793, + "step": 1122816 + }, + { + "epoch": 1.02, + "learning_rate": 3.160776630460775e-05, + "loss": 3.982, + "step": 1123328 + }, + { + "epoch": 1.02, + "learning_rate": 3.159938035709723e-05, + "loss": 3.971, + "step": 1123840 + }, + { + "epoch": 1.02, + "learning_rate": 3.159099440958671e-05, + "loss": 3.9595, + "step": 1124352 + }, + { + "epoch": 1.02, + "learning_rate": 3.158260846207619e-05, + "loss": 3.975, + "step": 1124864 + }, + { + "epoch": 1.02, + "learning_rate": 3.157422251456567e-05, + "loss": 3.9754, + "step": 1125376 + }, + { + "epoch": 1.02, + "learning_rate": 3.156583656705515e-05, + "loss": 3.9662, + "step": 1125888 + }, + { + "epoch": 1.02, + "learning_rate": 3.155745061954463e-05, + "loss": 3.9697, + "step": 1126400 + }, + { + "epoch": 1.02, + "learning_rate": 3.154908105083784e-05, + "loss": 3.9659, + "step": 1126912 + }, + { + "epoch": 1.02, + "learning_rate": 3.154069510332732e-05, + "loss": 3.9692, + "step": 1127424 + }, + { + "epoch": 1.02, + "learning_rate": 3.15323091558168e-05, + "loss": 3.9653, + "step": 1127936 + }, + { + "epoch": 1.02, + "learning_rate": 3.152392320830628e-05, + "loss": 3.9752, + "step": 1128448 + }, + { + "epoch": 1.02, + "learning_rate": 3.151553726079576e-05, + "loss": 3.9729, + "step": 1128960 + }, + { + "epoch": 1.02, + "learning_rate": 3.150715131328524e-05, + "loss": 3.9714, + "step": 1129472 + }, + { + "epoch": 1.02, + "learning_rate": 3.149876536577473e-05, + "loss": 3.9791, + "step": 1129984 + }, + { + "epoch": 1.02, + "learning_rate": 3.149037941826421e-05, + "loss": 3.9933, + "step": 1130496 + }, + { + "epoch": 1.02, + "learning_rate": 3.1482009849557416e-05, + "loss": 3.9684, + "step": 1131008 + }, + { + "epoch": 1.02, + "learning_rate": 3.1473623902046896e-05, + "loss": 3.9777, + "step": 1131520 + }, + { + "epoch": 1.02, + "learning_rate": 3.1465254333340105e-05, + "loss": 3.9759, + "step": 1132032 + }, + { + "epoch": 1.02, + "learning_rate": 3.1456868385829585e-05, + "loss": 3.9727, + "step": 1132544 + }, + { + "epoch": 1.02, + "learning_rate": 3.1448482438319065e-05, + "loss": 3.9725, + "step": 1133056 + }, + { + "epoch": 1.02, + "learning_rate": 3.1440096490808545e-05, + "loss": 3.9685, + "step": 1133568 + }, + { + "epoch": 1.02, + "learning_rate": 3.1431710543298025e-05, + "loss": 3.9778, + "step": 1134080 + }, + { + "epoch": 1.02, + "learning_rate": 3.1423324595787505e-05, + "loss": 3.9636, + "step": 1134592 + }, + { + "epoch": 1.02, + "learning_rate": 3.1414955027080714e-05, + "loss": 3.989, + "step": 1135104 + }, + { + "epoch": 1.02, + "learning_rate": 3.1406569079570194e-05, + "loss": 3.9719, + "step": 1135616 + }, + { + "epoch": 1.02, + "learning_rate": 3.139818313205968e-05, + "loss": 3.9838, + "step": 1136128 + }, + { + "epoch": 1.02, + "learning_rate": 3.138979718454916e-05, + "loss": 3.9716, + "step": 1136640 + }, + { + "epoch": 1.02, + "learning_rate": 3.1381411237038634e-05, + "loss": 3.9792, + "step": 1137152 + }, + { + "epoch": 1.02, + "learning_rate": 3.137304166833185e-05, + "loss": 3.9719, + "step": 1137664 + }, + { + "epoch": 1.02, + "learning_rate": 3.136465572082133e-05, + "loss": 3.9793, + "step": 1138176 + }, + { + "epoch": 1.02, + "learning_rate": 3.135626977331081e-05, + "loss": 3.9874, + "step": 1138688 + }, + { + "epoch": 1.02, + "learning_rate": 3.134788382580028e-05, + "loss": 3.9695, + "step": 1139200 + }, + { + "epoch": 1.02, + "learning_rate": 3.133949787828976e-05, + "loss": 3.9766, + "step": 1139712 + }, + { + "epoch": 1.02, + "learning_rate": 3.133111193077924e-05, + "loss": 3.9799, + "step": 1140224 + }, + { + "epoch": 1.02, + "learning_rate": 3.132272598326872e-05, + "loss": 3.9728, + "step": 1140736 + }, + { + "epoch": 1.02, + "learning_rate": 3.13143400357582e-05, + "loss": 3.9662, + "step": 1141248 + }, + { + "epoch": 1.02, + "learning_rate": 3.130595408824768e-05, + "loss": 3.9803, + "step": 1141760 + }, + { + "epoch": 1.02, + "learning_rate": 3.129756814073716e-05, + "loss": 3.9736, + "step": 1142272 + }, + { + "epoch": 1.02, + "learning_rate": 3.128919857203038e-05, + "loss": 3.973, + "step": 1142784 + }, + { + "epoch": 1.02, + "learning_rate": 3.128081262451986e-05, + "loss": 3.9725, + "step": 1143296 + }, + { + "epoch": 1.02, + "learning_rate": 3.127242667700934e-05, + "loss": 3.9736, + "step": 1143808 + }, + { + "epoch": 1.02, + "learning_rate": 3.126405710830255e-05, + "loss": 3.9657, + "step": 1144320 + }, + { + "epoch": 1.03, + "eval_loss": 4.026485443115234, + "eval_runtime": 299.6495, + "eval_samples_per_second": 1273.458, + "eval_steps_per_second": 39.796, + "step": 1144787 + }, + { + "epoch": 0.0, + "learning_rate": 3.125567116079203e-05, + "loss": 3.9304, + "step": 1144832 + }, + { + "epoch": 0.0, + "learning_rate": 3.124728521328151e-05, + "loss": 3.9671, + "step": 1145344 + }, + { + "epoch": 0.0, + "learning_rate": 3.123889926577099e-05, + "loss": 3.9617, + "step": 1145856 + }, + { + "epoch": 0.0, + "learning_rate": 3.123051331826047e-05, + "loss": 3.9834, + "step": 1146368 + }, + { + "epoch": 0.0, + "learning_rate": 3.122212737074995e-05, + "loss": 3.9736, + "step": 1146880 + }, + { + "epoch": 0.0, + "learning_rate": 3.121374142323943e-05, + "loss": 3.9756, + "step": 1147392 + }, + { + "epoch": 0.0, + "learning_rate": 3.120535547572891e-05, + "loss": 3.9669, + "step": 1147904 + }, + { + "epoch": 0.0, + "learning_rate": 3.119696952821839e-05, + "loss": 3.9709, + "step": 1148416 + }, + { + "epoch": 0.0, + "learning_rate": 3.118858358070787e-05, + "loss": 3.961, + "step": 1148928 + }, + { + "epoch": 0.0, + "learning_rate": 3.118019763319735e-05, + "loss": 3.9673, + "step": 1149440 + }, + { + "epoch": 0.0, + "learning_rate": 3.117181168568683e-05, + "loss": 3.9706, + "step": 1149952 + }, + { + "epoch": 0.0, + "learning_rate": 3.116342573817631e-05, + "loss": 3.9861, + "step": 1150464 + }, + { + "epoch": 0.0, + "learning_rate": 3.115505616946952e-05, + "loss": 3.9822, + "step": 1150976 + }, + { + "epoch": 0.0, + "learning_rate": 3.1146670221958996e-05, + "loss": 3.9535, + "step": 1151488 + }, + { + "epoch": 0.0, + "learning_rate": 3.1138284274448476e-05, + "loss": 3.9697, + "step": 1152000 + }, + { + "epoch": 0.0, + "learning_rate": 3.1129898326937956e-05, + "loss": 3.9606, + "step": 1152512 + }, + { + "epoch": 0.0, + "learning_rate": 3.1121512379427436e-05, + "loss": 3.9724, + "step": 1153024 + }, + { + "epoch": 0.0, + "learning_rate": 3.1113126431916916e-05, + "loss": 3.969, + "step": 1153536 + }, + { + "epoch": 0.0, + "learning_rate": 3.1104740484406396e-05, + "loss": 3.9704, + "step": 1154048 + }, + { + "epoch": 0.0, + "learning_rate": 3.1096354536895876e-05, + "loss": 3.9669, + "step": 1154560 + }, + { + "epoch": 0.0, + "learning_rate": 3.1087968589385356e-05, + "loss": 3.9851, + "step": 1155072 + }, + { + "epoch": 0.0, + "learning_rate": 3.1079582641874836e-05, + "loss": 3.9732, + "step": 1155584 + }, + { + "epoch": 0.0, + "learning_rate": 3.1071196694364316e-05, + "loss": 3.9689, + "step": 1156096 + }, + { + "epoch": 0.0, + "learning_rate": 3.1062810746853796e-05, + "loss": 3.9669, + "step": 1156608 + }, + { + "epoch": 0.0, + "learning_rate": 3.105442479934328e-05, + "loss": 3.9813, + "step": 1157120 + }, + { + "epoch": 0.0, + "learning_rate": 3.104605523063649e-05, + "loss": 3.9676, + "step": 1157632 + }, + { + "epoch": 0.0, + "learning_rate": 3.103766928312597e-05, + "loss": 3.9597, + "step": 1158144 + }, + { + "epoch": 0.0, + "learning_rate": 3.102928333561545e-05, + "loss": 3.9697, + "step": 1158656 + }, + { + "epoch": 0.0, + "learning_rate": 3.102091376690866e-05, + "loss": 3.9661, + "step": 1159168 + }, + { + "epoch": 0.0, + "learning_rate": 3.101252781939814e-05, + "loss": 3.9638, + "step": 1159680 + }, + { + "epoch": 0.01, + "learning_rate": 3.100414187188762e-05, + "loss": 3.9698, + "step": 1160192 + }, + { + "epoch": 0.01, + "learning_rate": 3.09957559243771e-05, + "loss": 3.9643, + "step": 1160704 + }, + { + "epoch": 0.01, + "learning_rate": 3.098738635567031e-05, + "loss": 3.9775, + "step": 1161216 + }, + { + "epoch": 0.01, + "learning_rate": 3.097900040815979e-05, + "loss": 3.9762, + "step": 1161728 + }, + { + "epoch": 0.01, + "learning_rate": 3.097061446064927e-05, + "loss": 3.9752, + "step": 1162240 + }, + { + "epoch": 0.01, + "learning_rate": 3.0962244891942485e-05, + "loss": 3.9714, + "step": 1162752 + }, + { + "epoch": 0.01, + "learning_rate": 3.0953858944431965e-05, + "loss": 3.9769, + "step": 1163264 + }, + { + "epoch": 0.01, + "learning_rate": 3.0945489375725174e-05, + "loss": 3.9579, + "step": 1163776 + }, + { + "epoch": 0.01, + "learning_rate": 3.0937103428214654e-05, + "loss": 3.9657, + "step": 1164288 + }, + { + "epoch": 0.01, + "learning_rate": 3.0928717480704134e-05, + "loss": 3.9621, + "step": 1164800 + }, + { + "epoch": 0.01, + "learning_rate": 3.0920331533193614e-05, + "loss": 3.9572, + "step": 1165312 + }, + { + "epoch": 0.01, + "learning_rate": 3.0911945585683094e-05, + "loss": 3.9697, + "step": 1165824 + }, + { + "epoch": 0.01, + "learning_rate": 3.0903559638172574e-05, + "loss": 3.9681, + "step": 1166336 + }, + { + "epoch": 0.01, + "learning_rate": 3.0895173690662054e-05, + "loss": 3.9615, + "step": 1166848 + }, + { + "epoch": 0.01, + "learning_rate": 3.088678774315153e-05, + "loss": 3.97, + "step": 1167360 + }, + { + "epoch": 0.01, + "learning_rate": 3.087840179564101e-05, + "loss": 3.9721, + "step": 1167872 + }, + { + "epoch": 0.01, + "learning_rate": 3.087001584813049e-05, + "loss": 3.9719, + "step": 1168384 + }, + { + "epoch": 0.01, + "learning_rate": 3.0861629900619974e-05, + "loss": 3.9684, + "step": 1168896 + }, + { + "epoch": 0.01, + "learning_rate": 3.0853243953109454e-05, + "loss": 3.9505, + "step": 1169408 + }, + { + "epoch": 0.01, + "learning_rate": 3.0844858005598934e-05, + "loss": 3.9684, + "step": 1169920 + }, + { + "epoch": 0.01, + "learning_rate": 3.0836472058088414e-05, + "loss": 3.9731, + "step": 1170432 + }, + { + "epoch": 0.01, + "learning_rate": 3.082810248938162e-05, + "loss": 3.9691, + "step": 1170944 + }, + { + "epoch": 0.01, + "learning_rate": 3.08197165418711e-05, + "loss": 3.963, + "step": 1171456 + }, + { + "epoch": 0.01, + "learning_rate": 3.081133059436058e-05, + "loss": 3.9636, + "step": 1171968 + }, + { + "epoch": 0.01, + "learning_rate": 3.080294464685006e-05, + "loss": 3.9556, + "step": 1172480 + }, + { + "epoch": 0.01, + "learning_rate": 3.079455869933954e-05, + "loss": 3.9577, + "step": 1172992 + }, + { + "epoch": 0.01, + "learning_rate": 3.078617275182902e-05, + "loss": 3.9678, + "step": 1173504 + }, + { + "epoch": 0.01, + "learning_rate": 3.07777868043185e-05, + "loss": 3.9516, + "step": 1174016 + }, + { + "epoch": 0.01, + "learning_rate": 3.076940085680798e-05, + "loss": 3.9725, + "step": 1174528 + }, + { + "epoch": 0.01, + "learning_rate": 3.076103128810119e-05, + "loss": 3.9705, + "step": 1175040 + }, + { + "epoch": 0.01, + "learning_rate": 3.075264534059067e-05, + "loss": 3.952, + "step": 1175552 + }, + { + "epoch": 0.01, + "learning_rate": 3.074425939308015e-05, + "loss": 3.9755, + "step": 1176064 + }, + { + "epoch": 0.01, + "learning_rate": 3.073588982437337e-05, + "loss": 3.9517, + "step": 1176576 + }, + { + "epoch": 0.01, + "learning_rate": 3.072750387686285e-05, + "loss": 3.9565, + "step": 1177088 + }, + { + "epoch": 0.01, + "learning_rate": 3.071911792935233e-05, + "loss": 3.9552, + "step": 1177600 + }, + { + "epoch": 0.01, + "learning_rate": 3.071073198184181e-05, + "loss": 3.9694, + "step": 1178112 + }, + { + "epoch": 0.01, + "learning_rate": 3.070234603433129e-05, + "loss": 3.9538, + "step": 1178624 + }, + { + "epoch": 0.01, + "learning_rate": 3.0693976465624496e-05, + "loss": 3.9698, + "step": 1179136 + }, + { + "epoch": 0.01, + "learning_rate": 3.0685590518113976e-05, + "loss": 3.9435, + "step": 1179648 + }, + { + "epoch": 0.01, + "learning_rate": 3.0677204570603456e-05, + "loss": 3.9552, + "step": 1180160 + }, + { + "epoch": 0.01, + "learning_rate": 3.0668818623092936e-05, + "loss": 3.9719, + "step": 1180672 + }, + { + "epoch": 0.01, + "learning_rate": 3.0660432675582416e-05, + "loss": 3.9626, + "step": 1181184 + }, + { + "epoch": 0.01, + "learning_rate": 3.065204672807189e-05, + "loss": 3.9683, + "step": 1181696 + }, + { + "epoch": 0.01, + "learning_rate": 3.0643660780561376e-05, + "loss": 3.9696, + "step": 1182208 + }, + { + "epoch": 0.01, + "learning_rate": 3.063529121185459e-05, + "loss": 3.9791, + "step": 1182720 + }, + { + "epoch": 0.01, + "learning_rate": 3.062690526434407e-05, + "loss": 3.9598, + "step": 1183232 + }, + { + "epoch": 0.01, + "learning_rate": 3.0618519316833545e-05, + "loss": 3.9743, + "step": 1183744 + }, + { + "epoch": 0.01, + "learning_rate": 3.0610133369323025e-05, + "loss": 3.9549, + "step": 1184256 + }, + { + "epoch": 0.01, + "learning_rate": 3.0601747421812505e-05, + "loss": 3.9602, + "step": 1184768 + }, + { + "epoch": 0.01, + "learning_rate": 3.0593361474301985e-05, + "loss": 3.9621, + "step": 1185280 + }, + { + "epoch": 0.01, + "learning_rate": 3.0584975526791465e-05, + "loss": 3.9699, + "step": 1185792 + }, + { + "epoch": 0.01, + "learning_rate": 3.0576605958084674e-05, + "loss": 3.9675, + "step": 1186304 + }, + { + "epoch": 0.01, + "learning_rate": 3.0568220010574154e-05, + "loss": 3.9754, + "step": 1186816 + }, + { + "epoch": 0.01, + "learning_rate": 3.0559834063063634e-05, + "loss": 3.9553, + "step": 1187328 + }, + { + "epoch": 0.01, + "learning_rate": 3.0551448115553114e-05, + "loss": 3.9482, + "step": 1187840 + }, + { + "epoch": 0.01, + "learning_rate": 3.054307854684633e-05, + "loss": 3.9571, + "step": 1188352 + }, + { + "epoch": 0.01, + "learning_rate": 3.053469259933581e-05, + "loss": 3.9655, + "step": 1188864 + }, + { + "epoch": 0.01, + "learning_rate": 3.052630665182529e-05, + "loss": 3.9609, + "step": 1189376 + }, + { + "epoch": 0.01, + "learning_rate": 3.051792070431477e-05, + "loss": 3.9588, + "step": 1189888 + }, + { + "epoch": 0.01, + "learning_rate": 3.050953475680425e-05, + "loss": 3.9666, + "step": 1190400 + }, + { + "epoch": 0.02, + "learning_rate": 3.050114880929373e-05, + "loss": 3.9587, + "step": 1190912 + }, + { + "epoch": 0.02, + "learning_rate": 3.049276286178321e-05, + "loss": 3.9615, + "step": 1191424 + }, + { + "epoch": 0.02, + "learning_rate": 3.048437691427269e-05, + "loss": 3.9571, + "step": 1191936 + }, + { + "epoch": 0.02, + "learning_rate": 3.04760073455659e-05, + "loss": 3.9697, + "step": 1192448 + }, + { + "epoch": 0.02, + "learning_rate": 3.046763777685911e-05, + "loss": 3.9764, + "step": 1192960 + }, + { + "epoch": 0.02, + "learning_rate": 3.045925182934859e-05, + "loss": 3.9699, + "step": 1193472 + }, + { + "epoch": 0.02, + "learning_rate": 3.045086588183807e-05, + "loss": 3.9507, + "step": 1193984 + }, + { + "epoch": 0.02, + "learning_rate": 3.044247993432755e-05, + "loss": 3.9604, + "step": 1194496 + }, + { + "epoch": 0.02, + "learning_rate": 3.043411036562076e-05, + "loss": 3.9598, + "step": 1195008 + }, + { + "epoch": 0.02, + "learning_rate": 3.042572441811024e-05, + "loss": 3.9669, + "step": 1195520 + }, + { + "epoch": 0.02, + "learning_rate": 3.041733847059972e-05, + "loss": 3.97, + "step": 1196032 + }, + { + "epoch": 0.02, + "learning_rate": 3.04089525230892e-05, + "loss": 3.9546, + "step": 1196544 + }, + { + "epoch": 0.02, + "learning_rate": 3.0400566575578683e-05, + "loss": 3.9641, + "step": 1197056 + }, + { + "epoch": 0.02, + "learning_rate": 3.0392180628068163e-05, + "loss": 3.9677, + "step": 1197568 + }, + { + "epoch": 0.02, + "learning_rate": 3.0383811059361372e-05, + "loss": 3.9627, + "step": 1198080 + }, + { + "epoch": 0.02, + "learning_rate": 3.0375425111850852e-05, + "loss": 3.9569, + "step": 1198592 + }, + { + "epoch": 0.02, + "learning_rate": 3.0367039164340332e-05, + "loss": 3.9542, + "step": 1199104 + }, + { + "epoch": 0.02, + "learning_rate": 3.0358653216829812e-05, + "loss": 3.9509, + "step": 1199616 + }, + { + "epoch": 0.02, + "learning_rate": 3.0350267269319292e-05, + "loss": 3.9613, + "step": 1200128 + }, + { + "epoch": 0.02, + "learning_rate": 3.0341881321808775e-05, + "loss": 3.9556, + "step": 1200640 + }, + { + "epoch": 0.02, + "learning_rate": 3.0333511753101984e-05, + "loss": 3.9543, + "step": 1201152 + }, + { + "epoch": 0.02, + "learning_rate": 3.0325125805591464e-05, + "loss": 3.9579, + "step": 1201664 + }, + { + "epoch": 0.02, + "learning_rate": 3.0316739858080944e-05, + "loss": 3.9657, + "step": 1202176 + }, + { + "epoch": 0.02, + "learning_rate": 3.0308353910570424e-05, + "loss": 3.9549, + "step": 1202688 + }, + { + "epoch": 0.02, + "learning_rate": 3.0299967963059904e-05, + "loss": 3.9608, + "step": 1203200 + }, + { + "epoch": 0.02, + "learning_rate": 3.029158201554938e-05, + "loss": 3.9733, + "step": 1203712 + }, + { + "epoch": 0.02, + "learning_rate": 3.0283212446842597e-05, + "loss": 3.9683, + "step": 1204224 + }, + { + "epoch": 0.02, + "learning_rate": 3.0274826499332077e-05, + "loss": 3.97, + "step": 1204736 + }, + { + "epoch": 0.02, + "learning_rate": 3.026644055182155e-05, + "loss": 3.9592, + "step": 1205248 + }, + { + "epoch": 0.02, + "learning_rate": 3.025805460431103e-05, + "loss": 3.9632, + "step": 1205760 + }, + { + "epoch": 0.02, + "learning_rate": 3.0249685035604246e-05, + "loss": 3.9597, + "step": 1206272 + }, + { + "epoch": 0.02, + "learning_rate": 3.0241315466897458e-05, + "loss": 3.9512, + "step": 1206784 + }, + { + "epoch": 0.02, + "learning_rate": 3.0232929519386938e-05, + "loss": 3.9617, + "step": 1207296 + }, + { + "epoch": 0.02, + "learning_rate": 3.0224543571876418e-05, + "loss": 3.9556, + "step": 1207808 + }, + { + "epoch": 0.02, + "learning_rate": 3.0216157624365898e-05, + "loss": 3.9653, + "step": 1208320 + }, + { + "epoch": 0.02, + "learning_rate": 3.0207771676855378e-05, + "loss": 3.9582, + "step": 1208832 + }, + { + "epoch": 0.02, + "learning_rate": 3.0199385729344855e-05, + "loss": 3.9639, + "step": 1209344 + }, + { + "epoch": 0.02, + "learning_rate": 3.0190999781834334e-05, + "loss": 3.9567, + "step": 1209856 + }, + { + "epoch": 0.02, + "learning_rate": 3.0182613834323814e-05, + "loss": 3.9569, + "step": 1210368 + }, + { + "epoch": 0.02, + "learning_rate": 3.0174227886813294e-05, + "loss": 3.9641, + "step": 1210880 + }, + { + "epoch": 0.02, + "learning_rate": 3.0165841939302774e-05, + "loss": 3.963, + "step": 1211392 + }, + { + "epoch": 0.02, + "learning_rate": 3.0157455991792254e-05, + "loss": 3.9706, + "step": 1211904 + }, + { + "epoch": 0.02, + "learning_rate": 3.0149086423085467e-05, + "loss": 3.9598, + "step": 1212416 + }, + { + "epoch": 0.02, + "learning_rate": 3.0140700475574947e-05, + "loss": 3.9665, + "step": 1212928 + }, + { + "epoch": 0.02, + "learning_rate": 3.0132314528064427e-05, + "loss": 3.9659, + "step": 1213440 + }, + { + "epoch": 0.02, + "learning_rate": 3.0123928580553907e-05, + "loss": 3.9657, + "step": 1213952 + }, + { + "epoch": 0.02, + "learning_rate": 3.0115542633043387e-05, + "loss": 3.9651, + "step": 1214464 + }, + { + "epoch": 0.02, + "learning_rate": 3.0107173064336596e-05, + "loss": 3.9624, + "step": 1214976 + }, + { + "epoch": 0.02, + "learning_rate": 3.0098787116826076e-05, + "loss": 3.9616, + "step": 1215488 + }, + { + "epoch": 0.02, + "learning_rate": 3.009040116931556e-05, + "loss": 3.9702, + "step": 1216000 + }, + { + "epoch": 0.02, + "learning_rate": 3.008201522180504e-05, + "loss": 3.956, + "step": 1216512 + }, + { + "epoch": 0.02, + "learning_rate": 3.007362927429452e-05, + "loss": 3.953, + "step": 1217024 + }, + { + "epoch": 0.02, + "learning_rate": 3.0065243326784e-05, + "loss": 3.9619, + "step": 1217536 + }, + { + "epoch": 0.02, + "learning_rate": 3.005685737927348e-05, + "loss": 3.9623, + "step": 1218048 + }, + { + "epoch": 0.02, + "learning_rate": 3.0048487810566688e-05, + "loss": 3.9606, + "step": 1218560 + }, + { + "epoch": 0.02, + "learning_rate": 3.0040101863056168e-05, + "loss": 3.9659, + "step": 1219072 + }, + { + "epoch": 0.02, + "learning_rate": 3.003171591554565e-05, + "loss": 3.9561, + "step": 1219584 + }, + { + "epoch": 0.02, + "learning_rate": 3.002332996803513e-05, + "loss": 3.9728, + "step": 1220096 + }, + { + "epoch": 0.02, + "learning_rate": 3.001494402052461e-05, + "loss": 3.961, + "step": 1220608 + }, + { + "epoch": 0.03, + "eval_loss": 4.018325328826904, + "eval_runtime": 300.6672, + "eval_samples_per_second": 1269.147, + "eval_steps_per_second": 39.662, + "step": 1221107 + }, + { + "epoch": 1.0, + "learning_rate": 3.000655807301409e-05, + "loss": 3.9585, + "step": 1221120 + }, + { + "epoch": 1.0, + "learning_rate": 2.9998172125503564e-05, + "loss": 3.9526, + "step": 1221632 + }, + { + "epoch": 1.0, + "learning_rate": 2.9989786177993044e-05, + "loss": 3.9507, + "step": 1222144 + }, + { + "epoch": 1.0, + "learning_rate": 2.998141660928626e-05, + "loss": 3.9693, + "step": 1222656 + }, + { + "epoch": 1.0, + "learning_rate": 2.9973030661775737e-05, + "loss": 3.9645, + "step": 1223168 + }, + { + "epoch": 1.0, + "learning_rate": 2.9964644714265217e-05, + "loss": 3.9647, + "step": 1223680 + }, + { + "epoch": 1.0, + "learning_rate": 2.9956258766754697e-05, + "loss": 3.9551, + "step": 1224192 + }, + { + "epoch": 1.0, + "learning_rate": 2.994790557685164e-05, + "loss": 3.9573, + "step": 1224704 + }, + { + "epoch": 1.0, + "learning_rate": 2.993951962934112e-05, + "loss": 3.9472, + "step": 1225216 + }, + { + "epoch": 1.0, + "learning_rate": 2.9931133681830605e-05, + "loss": 3.9589, + "step": 1225728 + }, + { + "epoch": 1.0, + "learning_rate": 2.9922747734320085e-05, + "loss": 3.9576, + "step": 1226240 + }, + { + "epoch": 1.0, + "learning_rate": 2.9914361786809565e-05, + "loss": 3.9744, + "step": 1226752 + }, + { + "epoch": 1.0, + "learning_rate": 2.9906008596906503e-05, + "loss": 3.9706, + "step": 1227264 + }, + { + "epoch": 1.0, + "learning_rate": 2.9897622649395983e-05, + "loss": 3.9411, + "step": 1227776 + }, + { + "epoch": 1.0, + "learning_rate": 2.9889236701885466e-05, + "loss": 3.9576, + "step": 1228288 + }, + { + "epoch": 1.0, + "learning_rate": 2.9880850754374946e-05, + "loss": 3.9515, + "step": 1228800 + }, + { + "epoch": 1.0, + "learning_rate": 2.9872464806864426e-05, + "loss": 3.9538, + "step": 1229312 + }, + { + "epoch": 1.0, + "learning_rate": 2.9864078859353906e-05, + "loss": 3.9618, + "step": 1229824 + }, + { + "epoch": 1.0, + "learning_rate": 2.9855692911843386e-05, + "loss": 3.9587, + "step": 1230336 + }, + { + "epoch": 1.0, + "learning_rate": 2.984730696433286e-05, + "loss": 3.9506, + "step": 1230848 + }, + { + "epoch": 1.0, + "learning_rate": 2.9838921016822343e-05, + "loss": 3.9747, + "step": 1231360 + }, + { + "epoch": 1.0, + "learning_rate": 2.9830535069311823e-05, + "loss": 3.9617, + "step": 1231872 + }, + { + "epoch": 1.0, + "learning_rate": 2.9822149121801303e-05, + "loss": 3.9555, + "step": 1232384 + }, + { + "epoch": 1.0, + "learning_rate": 2.9813763174290783e-05, + "loss": 3.9525, + "step": 1232896 + }, + { + "epoch": 1.0, + "learning_rate": 2.9805377226780262e-05, + "loss": 3.9712, + "step": 1233408 + }, + { + "epoch": 1.0, + "learning_rate": 2.9797024036877208e-05, + "loss": 3.956, + "step": 1233920 + }, + { + "epoch": 1.0, + "learning_rate": 2.9788638089366684e-05, + "loss": 3.9485, + "step": 1234432 + }, + { + "epoch": 1.0, + "learning_rate": 2.9780252141856164e-05, + "loss": 3.9586, + "step": 1234944 + }, + { + "epoch": 1.0, + "learning_rate": 2.9771866194345644e-05, + "loss": 3.9504, + "step": 1235456 + }, + { + "epoch": 1.0, + "learning_rate": 2.9763480246835124e-05, + "loss": 3.9533, + "step": 1235968 + }, + { + "epoch": 1.01, + "learning_rate": 2.9755110678128333e-05, + "loss": 3.9561, + "step": 1236480 + }, + { + "epoch": 1.01, + "learning_rate": 2.9746724730617813e-05, + "loss": 3.9554, + "step": 1236992 + }, + { + "epoch": 1.01, + "learning_rate": 2.9738338783107293e-05, + "loss": 3.964, + "step": 1237504 + }, + { + "epoch": 1.01, + "learning_rate": 2.9729952835596776e-05, + "loss": 3.9585, + "step": 1238016 + }, + { + "epoch": 1.01, + "learning_rate": 2.9721566888086256e-05, + "loss": 3.9656, + "step": 1238528 + }, + { + "epoch": 1.01, + "learning_rate": 2.9713197319379465e-05, + "loss": 3.9618, + "step": 1239040 + }, + { + "epoch": 1.01, + "learning_rate": 2.9704811371868945e-05, + "loss": 3.9635, + "step": 1239552 + }, + { + "epoch": 1.01, + "learning_rate": 2.9696441803162154e-05, + "loss": 3.946, + "step": 1240064 + }, + { + "epoch": 1.01, + "learning_rate": 2.9688055855651638e-05, + "loss": 3.956, + "step": 1240576 + }, + { + "epoch": 1.01, + "learning_rate": 2.9679669908141118e-05, + "loss": 3.9471, + "step": 1241088 + }, + { + "epoch": 1.01, + "learning_rate": 2.9671283960630598e-05, + "loss": 3.9514, + "step": 1241600 + }, + { + "epoch": 1.01, + "learning_rate": 2.9662898013120078e-05, + "loss": 3.9531, + "step": 1242112 + }, + { + "epoch": 1.01, + "learning_rate": 2.9654512065609558e-05, + "loss": 3.9592, + "step": 1242624 + }, + { + "epoch": 1.01, + "learning_rate": 2.9646126118099038e-05, + "loss": 3.9502, + "step": 1243136 + }, + { + "epoch": 1.01, + "learning_rate": 2.9637740170588517e-05, + "loss": 3.9598, + "step": 1243648 + }, + { + "epoch": 1.01, + "learning_rate": 2.962937060188173e-05, + "loss": 3.9578, + "step": 1244160 + }, + { + "epoch": 1.01, + "learning_rate": 2.962098465437121e-05, + "loss": 3.9633, + "step": 1244672 + }, + { + "epoch": 1.01, + "learning_rate": 2.961259870686069e-05, + "loss": 3.956, + "step": 1245184 + }, + { + "epoch": 1.01, + "learning_rate": 2.960421275935017e-05, + "loss": 3.9383, + "step": 1245696 + }, + { + "epoch": 1.01, + "learning_rate": 2.959582681183965e-05, + "loss": 3.9516, + "step": 1246208 + }, + { + "epoch": 1.01, + "learning_rate": 2.958744086432913e-05, + "loss": 3.9646, + "step": 1246720 + }, + { + "epoch": 1.01, + "learning_rate": 2.957907129562234e-05, + "loss": 3.9569, + "step": 1247232 + }, + { + "epoch": 1.01, + "learning_rate": 2.9570685348111822e-05, + "loss": 3.9474, + "step": 1247744 + }, + { + "epoch": 1.01, + "learning_rate": 2.9562299400601302e-05, + "loss": 3.9495, + "step": 1248256 + }, + { + "epoch": 1.01, + "learning_rate": 2.9553913453090782e-05, + "loss": 3.9464, + "step": 1248768 + }, + { + "epoch": 1.01, + "learning_rate": 2.9545527505580262e-05, + "loss": 3.9436, + "step": 1249280 + }, + { + "epoch": 1.01, + "learning_rate": 2.9537141558069742e-05, + "loss": 3.9614, + "step": 1249792 + }, + { + "epoch": 1.01, + "learning_rate": 2.9528755610559222e-05, + "loss": 3.9389, + "step": 1250304 + }, + { + "epoch": 1.01, + "learning_rate": 2.95203696630487e-05, + "loss": 3.9584, + "step": 1250816 + }, + { + "epoch": 1.01, + "learning_rate": 2.9512000094341914e-05, + "loss": 3.9574, + "step": 1251328 + }, + { + "epoch": 1.01, + "learning_rate": 2.9503630525635123e-05, + "loss": 3.9427, + "step": 1251840 + }, + { + "epoch": 1.01, + "learning_rate": 2.9495244578124603e-05, + "loss": 3.964, + "step": 1252352 + }, + { + "epoch": 1.01, + "learning_rate": 2.9486858630614083e-05, + "loss": 3.9419, + "step": 1252864 + }, + { + "epoch": 1.01, + "learning_rate": 2.9478472683103563e-05, + "loss": 3.9476, + "step": 1253376 + }, + { + "epoch": 1.01, + "learning_rate": 2.9470086735593043e-05, + "loss": 3.9401, + "step": 1253888 + }, + { + "epoch": 1.01, + "learning_rate": 2.946170078808252e-05, + "loss": 3.9592, + "step": 1254400 + }, + { + "epoch": 1.01, + "learning_rate": 2.9453314840572e-05, + "loss": 3.9454, + "step": 1254912 + }, + { + "epoch": 1.01, + "learning_rate": 2.944492889306148e-05, + "loss": 3.9527, + "step": 1255424 + }, + { + "epoch": 1.01, + "learning_rate": 2.9436559324354696e-05, + "loss": 3.9357, + "step": 1255936 + }, + { + "epoch": 1.01, + "learning_rate": 2.942817337684417e-05, + "loss": 3.9435, + "step": 1256448 + }, + { + "epoch": 1.01, + "learning_rate": 2.9419787429333652e-05, + "loss": 3.9592, + "step": 1256960 + }, + { + "epoch": 1.01, + "learning_rate": 2.9411401481823132e-05, + "loss": 3.9576, + "step": 1257472 + }, + { + "epoch": 1.01, + "learning_rate": 2.9403031913116348e-05, + "loss": 3.9511, + "step": 1257984 + }, + { + "epoch": 1.01, + "learning_rate": 2.939464596560582e-05, + "loss": 3.9567, + "step": 1258496 + }, + { + "epoch": 1.01, + "learning_rate": 2.93862600180953e-05, + "loss": 3.9669, + "step": 1259008 + }, + { + "epoch": 1.01, + "learning_rate": 2.937787407058478e-05, + "loss": 3.9482, + "step": 1259520 + }, + { + "epoch": 1.01, + "learning_rate": 2.936948812307426e-05, + "loss": 3.9644, + "step": 1260032 + }, + { + "epoch": 1.01, + "learning_rate": 2.9361118554367474e-05, + "loss": 3.942, + "step": 1260544 + }, + { + "epoch": 1.01, + "learning_rate": 2.9352732606856954e-05, + "loss": 3.9528, + "step": 1261056 + }, + { + "epoch": 1.01, + "learning_rate": 2.9344346659346433e-05, + "loss": 3.9519, + "step": 1261568 + }, + { + "epoch": 1.01, + "learning_rate": 2.9335960711835913e-05, + "loss": 3.9562, + "step": 1262080 + }, + { + "epoch": 1.01, + "learning_rate": 2.9327591143129123e-05, + "loss": 3.9558, + "step": 1262592 + }, + { + "epoch": 1.01, + "learning_rate": 2.9319205195618606e-05, + "loss": 3.9669, + "step": 1263104 + }, + { + "epoch": 1.01, + "learning_rate": 2.9310819248108086e-05, + "loss": 3.9502, + "step": 1263616 + }, + { + "epoch": 1.01, + "learning_rate": 2.9302433300597566e-05, + "loss": 3.9325, + "step": 1264128 + }, + { + "epoch": 1.01, + "learning_rate": 2.9294063731890775e-05, + "loss": 3.944, + "step": 1264640 + }, + { + "epoch": 1.01, + "learning_rate": 2.9285677784380255e-05, + "loss": 3.9551, + "step": 1265152 + }, + { + "epoch": 1.01, + "learning_rate": 2.9277291836869735e-05, + "loss": 3.9484, + "step": 1265664 + }, + { + "epoch": 1.01, + "learning_rate": 2.9268905889359215e-05, + "loss": 3.9479, + "step": 1266176 + }, + { + "epoch": 1.01, + "learning_rate": 2.9260536320652427e-05, + "loss": 3.9567, + "step": 1266688 + }, + { + "epoch": 1.02, + "learning_rate": 2.9252150373141907e-05, + "loss": 3.9461, + "step": 1267200 + }, + { + "epoch": 1.02, + "learning_rate": 2.9243780804435116e-05, + "loss": 3.9503, + "step": 1267712 + }, + { + "epoch": 1.02, + "learning_rate": 2.9235394856924596e-05, + "loss": 3.9467, + "step": 1268224 + }, + { + "epoch": 1.02, + "learning_rate": 2.9227008909414076e-05, + "loss": 3.9617, + "step": 1268736 + }, + { + "epoch": 1.02, + "learning_rate": 2.921862296190356e-05, + "loss": 3.9619, + "step": 1269248 + }, + { + "epoch": 1.02, + "learning_rate": 2.921023701439304e-05, + "loss": 3.9579, + "step": 1269760 + }, + { + "epoch": 1.02, + "learning_rate": 2.920185106688252e-05, + "loss": 3.941, + "step": 1270272 + }, + { + "epoch": 1.02, + "learning_rate": 2.919348149817573e-05, + "loss": 3.9474, + "step": 1270784 + }, + { + "epoch": 1.02, + "learning_rate": 2.918509555066521e-05, + "loss": 3.9525, + "step": 1271296 + }, + { + "epoch": 1.02, + "learning_rate": 2.917670960315469e-05, + "loss": 3.954, + "step": 1271808 + }, + { + "epoch": 1.02, + "learning_rate": 2.916832365564417e-05, + "loss": 3.96, + "step": 1272320 + }, + { + "epoch": 1.02, + "learning_rate": 2.915995408693738e-05, + "loss": 3.9448, + "step": 1272832 + }, + { + "epoch": 1.02, + "learning_rate": 2.915156813942686e-05, + "loss": 3.9516, + "step": 1273344 + }, + { + "epoch": 1.02, + "learning_rate": 2.914318219191634e-05, + "loss": 3.9532, + "step": 1273856 + }, + { + "epoch": 1.02, + "learning_rate": 2.913479624440582e-05, + "loss": 3.9541, + "step": 1274368 + }, + { + "epoch": 1.02, + "learning_rate": 2.91264102968953e-05, + "loss": 3.942, + "step": 1274880 + }, + { + "epoch": 1.02, + "learning_rate": 2.911804072818851e-05, + "loss": 3.9489, + "step": 1275392 + }, + { + "epoch": 1.02, + "learning_rate": 2.9109654780677993e-05, + "loss": 3.9397, + "step": 1275904 + }, + { + "epoch": 1.02, + "learning_rate": 2.9101268833167473e-05, + "loss": 3.9432, + "step": 1276416 + }, + { + "epoch": 1.02, + "learning_rate": 2.9092882885656953e-05, + "loss": 3.9475, + "step": 1276928 + }, + { + "epoch": 1.02, + "learning_rate": 2.9084496938146433e-05, + "loss": 3.9451, + "step": 1277440 + }, + { + "epoch": 1.02, + "learning_rate": 2.9076110990635913e-05, + "loss": 3.9417, + "step": 1277952 + }, + { + "epoch": 1.02, + "learning_rate": 2.9067725043125393e-05, + "loss": 3.9528, + "step": 1278464 + }, + { + "epoch": 1.02, + "learning_rate": 2.9059339095614873e-05, + "loss": 3.9455, + "step": 1278976 + }, + { + "epoch": 1.02, + "learning_rate": 2.9050969526908085e-05, + "loss": 3.9513, + "step": 1279488 + }, + { + "epoch": 1.02, + "learning_rate": 2.9042583579397565e-05, + "loss": 3.9588, + "step": 1280000 + }, + { + "epoch": 1.02, + "learning_rate": 2.9034197631887045e-05, + "loss": 3.9628, + "step": 1280512 + }, + { + "epoch": 1.02, + "learning_rate": 2.9025828063180254e-05, + "loss": 3.9568, + "step": 1281024 + }, + { + "epoch": 1.02, + "learning_rate": 2.9017442115669734e-05, + "loss": 3.9467, + "step": 1281536 + }, + { + "epoch": 1.02, + "learning_rate": 2.9009072546962947e-05, + "loss": 3.951, + "step": 1282048 + }, + { + "epoch": 1.02, + "learning_rate": 2.9000702978256156e-05, + "loss": 3.9481, + "step": 1282560 + }, + { + "epoch": 1.02, + "learning_rate": 2.8992317030745636e-05, + "loss": 3.9418, + "step": 1283072 + }, + { + "epoch": 1.02, + "learning_rate": 2.8983931083235116e-05, + "loss": 3.9486, + "step": 1283584 + }, + { + "epoch": 1.02, + "learning_rate": 2.8975545135724596e-05, + "loss": 3.9469, + "step": 1284096 + }, + { + "epoch": 1.02, + "learning_rate": 2.8967159188214076e-05, + "loss": 3.9521, + "step": 1284608 + }, + { + "epoch": 1.02, + "learning_rate": 2.8958773240703556e-05, + "loss": 3.947, + "step": 1285120 + }, + { + "epoch": 1.02, + "learning_rate": 2.895038729319304e-05, + "loss": 3.9543, + "step": 1285632 + }, + { + "epoch": 1.02, + "learning_rate": 2.894200134568252e-05, + "loss": 3.9516, + "step": 1286144 + }, + { + "epoch": 1.02, + "learning_rate": 2.8933615398172e-05, + "loss": 3.9447, + "step": 1286656 + }, + { + "epoch": 1.02, + "learning_rate": 2.892522945066148e-05, + "loss": 3.9424, + "step": 1287168 + }, + { + "epoch": 1.02, + "learning_rate": 2.8916843503150952e-05, + "loss": 3.9625, + "step": 1287680 + }, + { + "epoch": 1.02, + "learning_rate": 2.8908457555640432e-05, + "loss": 3.953, + "step": 1288192 + }, + { + "epoch": 1.02, + "learning_rate": 2.8900071608129915e-05, + "loss": 3.9542, + "step": 1288704 + }, + { + "epoch": 1.02, + "learning_rate": 2.8891702039423124e-05, + "loss": 3.9511, + "step": 1289216 + }, + { + "epoch": 1.02, + "learning_rate": 2.8883316091912604e-05, + "loss": 3.9566, + "step": 1289728 + }, + { + "epoch": 1.02, + "learning_rate": 2.8874930144402084e-05, + "loss": 3.9562, + "step": 1290240 + }, + { + "epoch": 1.02, + "learning_rate": 2.8866544196891564e-05, + "loss": 3.9578, + "step": 1290752 + }, + { + "epoch": 1.02, + "learning_rate": 2.8858158249381044e-05, + "loss": 3.9486, + "step": 1291264 + }, + { + "epoch": 1.02, + "learning_rate": 2.8849788680674257e-05, + "loss": 3.952, + "step": 1291776 + }, + { + "epoch": 1.02, + "learning_rate": 2.8841402733163737e-05, + "loss": 3.9578, + "step": 1292288 + }, + { + "epoch": 1.02, + "learning_rate": 2.8833016785653217e-05, + "loss": 3.9457, + "step": 1292800 + }, + { + "epoch": 1.02, + "learning_rate": 2.8824630838142697e-05, + "loss": 3.9414, + "step": 1293312 + }, + { + "epoch": 1.02, + "learning_rate": 2.8816244890632177e-05, + "loss": 3.9498, + "step": 1293824 + }, + { + "epoch": 1.02, + "learning_rate": 2.8807858943121657e-05, + "loss": 3.9577, + "step": 1294336 + }, + { + "epoch": 1.02, + "learning_rate": 2.879948937441487e-05, + "loss": 3.9443, + "step": 1294848 + }, + { + "epoch": 1.02, + "learning_rate": 2.879110342690435e-05, + "loss": 3.9561, + "step": 1295360 + }, + { + "epoch": 1.02, + "learning_rate": 2.878271747939383e-05, + "loss": 3.9463, + "step": 1295872 + }, + { + "epoch": 1.02, + "learning_rate": 2.877433153188331e-05, + "loss": 3.9605, + "step": 1296384 + }, + { + "epoch": 1.02, + "learning_rate": 2.876594558437279e-05, + "loss": 3.9539, + "step": 1296896 + }, + { + "epoch": 1.02, + "learning_rate": 2.875755963686227e-05, + "loss": 3.942, + "step": 1297408 + }, + { + "epoch": 1.03, + "eval_loss": 4.0134358406066895, + "eval_runtime": 294.8736, + "eval_samples_per_second": 1294.083, + "eval_steps_per_second": 40.441, + "step": 1297427 + }, + { + "epoch": 0.0, + "learning_rate": 2.874917368935175e-05, + "loss": 3.9397, + "step": 1297920 + }, + { + "epoch": 0.0, + "learning_rate": 2.874078774184123e-05, + "loss": 3.9398, + "step": 1298432 + }, + { + "epoch": 0.0, + "learning_rate": 2.873240179433071e-05, + "loss": 3.9596, + "step": 1298944 + }, + { + "epoch": 0.0, + "learning_rate": 2.872401584682019e-05, + "loss": 3.9511, + "step": 1299456 + }, + { + "epoch": 0.0, + "learning_rate": 2.8715629899309665e-05, + "loss": 3.9536, + "step": 1299968 + }, + { + "epoch": 0.0, + "learning_rate": 2.8707243951799145e-05, + "loss": 3.9499, + "step": 1300480 + }, + { + "epoch": 0.0, + "learning_rate": 2.8698858004288625e-05, + "loss": 3.9428, + "step": 1300992 + }, + { + "epoch": 0.0, + "learning_rate": 2.8690472056778105e-05, + "loss": 3.9372, + "step": 1301504 + }, + { + "epoch": 0.0, + "learning_rate": 2.8682086109267585e-05, + "loss": 3.9523, + "step": 1302016 + }, + { + "epoch": 0.0, + "learning_rate": 2.8673700161757065e-05, + "loss": 3.9422, + "step": 1302528 + }, + { + "epoch": 0.0, + "learning_rate": 2.866531421424655e-05, + "loss": 3.9686, + "step": 1303040 + }, + { + "epoch": 0.0, + "learning_rate": 2.8656928266736028e-05, + "loss": 3.9565, + "step": 1303552 + }, + { + "epoch": 0.0, + "learning_rate": 2.8648558698029237e-05, + "loss": 3.9375, + "step": 1304064 + }, + { + "epoch": 0.0, + "learning_rate": 2.8640172750518717e-05, + "loss": 3.9428, + "step": 1304576 + }, + { + "epoch": 0.0, + "learning_rate": 2.8631786803008197e-05, + "loss": 3.9423, + "step": 1305088 + }, + { + "epoch": 0.0, + "learning_rate": 2.8623400855497677e-05, + "loss": 3.9416, + "step": 1305600 + }, + { + "epoch": 0.0, + "learning_rate": 2.8615014907987157e-05, + "loss": 3.9499, + "step": 1306112 + }, + { + "epoch": 0.0, + "learning_rate": 2.860662896047664e-05, + "loss": 3.951, + "step": 1306624 + }, + { + "epoch": 0.0, + "learning_rate": 2.859825939176985e-05, + "loss": 3.9368, + "step": 1307136 + }, + { + "epoch": 0.0, + "learning_rate": 2.858987344425933e-05, + "loss": 3.966, + "step": 1307648 + }, + { + "epoch": 0.0, + "learning_rate": 2.858148749674881e-05, + "loss": 3.9461, + "step": 1308160 + }, + { + "epoch": 0.0, + "learning_rate": 2.857310154923829e-05, + "loss": 3.9501, + "step": 1308672 + }, + { + "epoch": 0.0, + "learning_rate": 2.856471560172777e-05, + "loss": 3.9428, + "step": 1309184 + }, + { + "epoch": 0.0, + "learning_rate": 2.855632965421725e-05, + "loss": 3.9614, + "step": 1309696 + }, + { + "epoch": 0.0, + "learning_rate": 2.8547943706706726e-05, + "loss": 3.9429, + "step": 1310208 + }, + { + "epoch": 0.0, + "learning_rate": 2.8539557759196206e-05, + "loss": 3.9452, + "step": 1310720 + }, + { + "epoch": 0.0, + "learning_rate": 2.8531171811685686e-05, + "loss": 3.9433, + "step": 1311232 + }, + { + "epoch": 0.0, + "learning_rate": 2.8522802242978902e-05, + "loss": 3.9457, + "step": 1311744 + }, + { + "epoch": 0.0, + "learning_rate": 2.851441629546838e-05, + "loss": 3.9423, + "step": 1312256 + }, + { + "epoch": 0.01, + "learning_rate": 2.8506046726761594e-05, + "loss": 3.944, + "step": 1312768 + }, + { + "epoch": 0.01, + "learning_rate": 2.8497660779251074e-05, + "loss": 3.9469, + "step": 1313280 + }, + { + "epoch": 0.01, + "learning_rate": 2.8489274831740554e-05, + "loss": 3.949, + "step": 1313792 + }, + { + "epoch": 0.01, + "learning_rate": 2.8480888884230027e-05, + "loss": 3.9523, + "step": 1314304 + }, + { + "epoch": 0.01, + "learning_rate": 2.8472502936719507e-05, + "loss": 3.9555, + "step": 1314816 + }, + { + "epoch": 0.01, + "learning_rate": 2.8464133368012723e-05, + "loss": 3.9504, + "step": 1315328 + }, + { + "epoch": 0.01, + "learning_rate": 2.84557474205022e-05, + "loss": 3.9523, + "step": 1315840 + }, + { + "epoch": 0.01, + "learning_rate": 2.8447377851795416e-05, + "loss": 3.9404, + "step": 1316352 + }, + { + "epoch": 0.01, + "learning_rate": 2.8438991904284896e-05, + "loss": 3.946, + "step": 1316864 + }, + { + "epoch": 0.01, + "learning_rate": 2.8430605956774375e-05, + "loss": 3.9351, + "step": 1317376 + }, + { + "epoch": 0.01, + "learning_rate": 2.842222000926385e-05, + "loss": 3.9462, + "step": 1317888 + }, + { + "epoch": 0.01, + "learning_rate": 2.8413834061753332e-05, + "loss": 3.9425, + "step": 1318400 + }, + { + "epoch": 0.01, + "learning_rate": 2.8405448114242812e-05, + "loss": 3.949, + "step": 1318912 + }, + { + "epoch": 0.01, + "learning_rate": 2.8397062166732292e-05, + "loss": 3.9383, + "step": 1319424 + }, + { + "epoch": 0.01, + "learning_rate": 2.8388676219221772e-05, + "loss": 3.9529, + "step": 1319936 + }, + { + "epoch": 0.01, + "learning_rate": 2.8380290271711252e-05, + "loss": 3.9472, + "step": 1320448 + }, + { + "epoch": 0.01, + "learning_rate": 2.8371904324200732e-05, + "loss": 3.9534, + "step": 1320960 + }, + { + "epoch": 0.01, + "learning_rate": 2.8363518376690212e-05, + "loss": 3.9458, + "step": 1321472 + }, + { + "epoch": 0.01, + "learning_rate": 2.835513242917969e-05, + "loss": 3.9334, + "step": 1321984 + }, + { + "epoch": 0.01, + "learning_rate": 2.8346762860472904e-05, + "loss": 3.9364, + "step": 1322496 + }, + { + "epoch": 0.01, + "learning_rate": 2.8338376912962384e-05, + "loss": 3.9564, + "step": 1323008 + }, + { + "epoch": 0.01, + "learning_rate": 2.8329990965451864e-05, + "loss": 3.9449, + "step": 1323520 + }, + { + "epoch": 0.01, + "learning_rate": 2.8321605017941344e-05, + "loss": 3.9393, + "step": 1324032 + }, + { + "epoch": 0.01, + "learning_rate": 2.8313219070430824e-05, + "loss": 3.9354, + "step": 1324544 + }, + { + "epoch": 0.01, + "learning_rate": 2.8304833122920304e-05, + "loss": 3.9433, + "step": 1325056 + }, + { + "epoch": 0.01, + "learning_rate": 2.8296463554213516e-05, + "loss": 3.9245, + "step": 1325568 + }, + { + "epoch": 0.01, + "learning_rate": 2.8288077606702996e-05, + "loss": 3.9574, + "step": 1326080 + }, + { + "epoch": 0.01, + "learning_rate": 2.8279691659192476e-05, + "loss": 3.9255, + "step": 1326592 + }, + { + "epoch": 0.01, + "learning_rate": 2.8271305711681956e-05, + "loss": 3.9485, + "step": 1327104 + }, + { + "epoch": 0.01, + "learning_rate": 2.8262919764171436e-05, + "loss": 3.9495, + "step": 1327616 + }, + { + "epoch": 0.01, + "learning_rate": 2.8254550195464645e-05, + "loss": 3.9327, + "step": 1328128 + }, + { + "epoch": 0.01, + "learning_rate": 2.8246164247954125e-05, + "loss": 3.948, + "step": 1328640 + }, + { + "epoch": 0.01, + "learning_rate": 2.8237778300443605e-05, + "loss": 3.9362, + "step": 1329152 + }, + { + "epoch": 0.01, + "learning_rate": 2.822939235293309e-05, + "loss": 3.9386, + "step": 1329664 + }, + { + "epoch": 0.01, + "learning_rate": 2.8221006405422562e-05, + "loss": 3.9288, + "step": 1330176 + }, + { + "epoch": 0.01, + "learning_rate": 2.8212620457912042e-05, + "loss": 3.951, + "step": 1330688 + }, + { + "epoch": 0.01, + "learning_rate": 2.8204234510401522e-05, + "loss": 3.9347, + "step": 1331200 + }, + { + "epoch": 0.01, + "learning_rate": 2.8195848562891e-05, + "loss": 3.94, + "step": 1331712 + }, + { + "epoch": 0.01, + "learning_rate": 2.8187478994184214e-05, + "loss": 3.9256, + "step": 1332224 + }, + { + "epoch": 0.01, + "learning_rate": 2.8179093046673694e-05, + "loss": 3.9338, + "step": 1332736 + }, + { + "epoch": 0.01, + "learning_rate": 2.8170707099163174e-05, + "loss": 3.9449, + "step": 1333248 + }, + { + "epoch": 0.01, + "learning_rate": 2.8162321151652654e-05, + "loss": 3.948, + "step": 1333760 + }, + { + "epoch": 0.01, + "learning_rate": 2.81539679617496e-05, + "loss": 3.9435, + "step": 1334272 + }, + { + "epoch": 0.01, + "learning_rate": 2.814558201423908e-05, + "loss": 3.9481, + "step": 1334784 + }, + { + "epoch": 0.01, + "learning_rate": 2.813719606672856e-05, + "loss": 3.9525, + "step": 1335296 + }, + { + "epoch": 0.01, + "learning_rate": 2.8128810119218036e-05, + "loss": 3.9414, + "step": 1335808 + }, + { + "epoch": 0.01, + "learning_rate": 2.8120424171707515e-05, + "loss": 3.9515, + "step": 1336320 + }, + { + "epoch": 0.01, + "learning_rate": 2.811205460300073e-05, + "loss": 3.9364, + "step": 1336832 + }, + { + "epoch": 0.01, + "learning_rate": 2.810366865549021e-05, + "loss": 3.9421, + "step": 1337344 + }, + { + "epoch": 0.01, + "learning_rate": 2.8095282707979688e-05, + "loss": 3.9374, + "step": 1337856 + }, + { + "epoch": 0.01, + "learning_rate": 2.8086896760469168e-05, + "loss": 3.9482, + "step": 1338368 + }, + { + "epoch": 0.01, + "learning_rate": 2.8078527191762384e-05, + "loss": 3.9455, + "step": 1338880 + }, + { + "epoch": 0.01, + "learning_rate": 2.8070141244251857e-05, + "loss": 3.9538, + "step": 1339392 + }, + { + "epoch": 0.01, + "learning_rate": 2.8061755296741337e-05, + "loss": 3.9456, + "step": 1339904 + }, + { + "epoch": 0.01, + "learning_rate": 2.8053369349230817e-05, + "loss": 3.9199, + "step": 1340416 + }, + { + "epoch": 0.01, + "learning_rate": 2.8044983401720297e-05, + "loss": 3.9331, + "step": 1340928 + }, + { + "epoch": 0.01, + "learning_rate": 2.803659745420978e-05, + "loss": 3.9432, + "step": 1341440 + }, + { + "epoch": 0.01, + "learning_rate": 2.802821150669926e-05, + "loss": 3.9373, + "step": 1341952 + }, + { + "epoch": 0.01, + "learning_rate": 2.801984193799247e-05, + "loss": 3.9375, + "step": 1342464 + }, + { + "epoch": 0.01, + "learning_rate": 2.801145599048195e-05, + "loss": 3.9459, + "step": 1342976 + }, + { + "epoch": 0.02, + "learning_rate": 2.800307004297143e-05, + "loss": 3.933, + "step": 1343488 + }, + { + "epoch": 0.02, + "learning_rate": 2.799468409546091e-05, + "loss": 3.9381, + "step": 1344000 + }, + { + "epoch": 0.02, + "learning_rate": 2.798629814795039e-05, + "loss": 3.9395, + "step": 1344512 + }, + { + "epoch": 0.02, + "learning_rate": 2.7977912200439872e-05, + "loss": 3.9487, + "step": 1345024 + }, + { + "epoch": 0.02, + "learning_rate": 2.7969526252929352e-05, + "loss": 3.9485, + "step": 1345536 + }, + { + "epoch": 0.02, + "learning_rate": 2.7961140305418832e-05, + "loss": 3.953, + "step": 1346048 + }, + { + "epoch": 0.02, + "learning_rate": 2.7952754357908312e-05, + "loss": 3.9276, + "step": 1346560 + }, + { + "epoch": 0.02, + "learning_rate": 2.794438478920152e-05, + "loss": 3.9403, + "step": 1347072 + }, + { + "epoch": 0.02, + "learning_rate": 2.7935998841691e-05, + "loss": 3.9391, + "step": 1347584 + }, + { + "epoch": 0.02, + "learning_rate": 2.7927629272984214e-05, + "loss": 3.9448, + "step": 1348096 + }, + { + "epoch": 0.02, + "learning_rate": 2.7919243325473694e-05, + "loss": 3.9555, + "step": 1348608 + }, + { + "epoch": 0.02, + "learning_rate": 2.7910857377963174e-05, + "loss": 3.9317, + "step": 1349120 + }, + { + "epoch": 0.02, + "learning_rate": 2.7902471430452654e-05, + "loss": 3.9404, + "step": 1349632 + }, + { + "epoch": 0.02, + "learning_rate": 2.7894085482942134e-05, + "loss": 3.9447, + "step": 1350144 + }, + { + "epoch": 0.02, + "learning_rate": 2.7885699535431613e-05, + "loss": 3.9436, + "step": 1350656 + }, + { + "epoch": 0.02, + "learning_rate": 2.7877329966724826e-05, + "loss": 3.9313, + "step": 1351168 + }, + { + "epoch": 0.02, + "learning_rate": 2.7868944019214306e-05, + "loss": 3.9379, + "step": 1351680 + }, + { + "epoch": 0.02, + "learning_rate": 2.7860558071703786e-05, + "loss": 3.9326, + "step": 1352192 + }, + { + "epoch": 0.02, + "learning_rate": 2.7852172124193266e-05, + "loss": 3.9342, + "step": 1352704 + }, + { + "epoch": 0.02, + "learning_rate": 2.7843786176682746e-05, + "loss": 3.935, + "step": 1353216 + }, + { + "epoch": 0.02, + "learning_rate": 2.7835416607975955e-05, + "loss": 3.9353, + "step": 1353728 + }, + { + "epoch": 0.02, + "learning_rate": 2.7827030660465435e-05, + "loss": 3.9345, + "step": 1354240 + }, + { + "epoch": 0.02, + "learning_rate": 2.7818644712954918e-05, + "loss": 3.9407, + "step": 1354752 + }, + { + "epoch": 0.02, + "learning_rate": 2.7810258765444398e-05, + "loss": 3.9346, + "step": 1355264 + }, + { + "epoch": 0.02, + "learning_rate": 2.780187281793387e-05, + "loss": 3.94, + "step": 1355776 + }, + { + "epoch": 0.02, + "learning_rate": 2.779348687042335e-05, + "loss": 3.954, + "step": 1356288 + }, + { + "epoch": 0.02, + "learning_rate": 2.778510092291283e-05, + "loss": 3.9493, + "step": 1356800 + }, + { + "epoch": 0.02, + "learning_rate": 2.777671497540231e-05, + "loss": 3.9444, + "step": 1357312 + }, + { + "epoch": 0.02, + "learning_rate": 2.776836178549926e-05, + "loss": 3.9401, + "step": 1357824 + }, + { + "epoch": 0.02, + "learning_rate": 2.775997583798874e-05, + "loss": 3.9411, + "step": 1358336 + }, + { + "epoch": 0.02, + "learning_rate": 2.775158989047822e-05, + "loss": 3.9398, + "step": 1358848 + }, + { + "epoch": 0.02, + "learning_rate": 2.7743203942967693e-05, + "loss": 3.9291, + "step": 1359360 + }, + { + "epoch": 0.02, + "learning_rate": 2.7734817995457173e-05, + "loss": 3.9403, + "step": 1359872 + }, + { + "epoch": 0.02, + "learning_rate": 2.7726432047946656e-05, + "loss": 3.939, + "step": 1360384 + }, + { + "epoch": 0.02, + "learning_rate": 2.7718046100436136e-05, + "loss": 3.9426, + "step": 1360896 + }, + { + "epoch": 0.02, + "learning_rate": 2.7709660152925616e-05, + "loss": 3.9385, + "step": 1361408 + }, + { + "epoch": 0.02, + "learning_rate": 2.7701290584218825e-05, + "loss": 3.9414, + "step": 1361920 + }, + { + "epoch": 0.02, + "learning_rate": 2.7692904636708305e-05, + "loss": 3.9386, + "step": 1362432 + }, + { + "epoch": 0.02, + "learning_rate": 2.7684518689197785e-05, + "loss": 3.9362, + "step": 1362944 + }, + { + "epoch": 0.02, + "learning_rate": 2.7676132741687265e-05, + "loss": 3.9305, + "step": 1363456 + }, + { + "epoch": 0.02, + "learning_rate": 2.7667763172980477e-05, + "loss": 3.9522, + "step": 1363968 + }, + { + "epoch": 0.02, + "learning_rate": 2.7659377225469957e-05, + "loss": 3.945, + "step": 1364480 + }, + { + "epoch": 0.02, + "learning_rate": 2.7650991277959437e-05, + "loss": 3.9433, + "step": 1364992 + }, + { + "epoch": 0.02, + "learning_rate": 2.7642605330448917e-05, + "loss": 3.9401, + "step": 1365504 + }, + { + "epoch": 0.02, + "learning_rate": 2.7634235761742126e-05, + "loss": 3.9461, + "step": 1366016 + }, + { + "epoch": 0.02, + "learning_rate": 2.762584981423161e-05, + "loss": 3.946, + "step": 1366528 + }, + { + "epoch": 0.02, + "learning_rate": 2.761748024552482e-05, + "loss": 3.9515, + "step": 1367040 + }, + { + "epoch": 0.02, + "learning_rate": 2.76090942980143e-05, + "loss": 3.9415, + "step": 1367552 + }, + { + "epoch": 0.02, + "learning_rate": 2.760070835050378e-05, + "loss": 3.9436, + "step": 1368064 + }, + { + "epoch": 0.02, + "learning_rate": 2.759232240299326e-05, + "loss": 3.9422, + "step": 1368576 + }, + { + "epoch": 0.02, + "learning_rate": 2.758395283428647e-05, + "loss": 3.9369, + "step": 1369088 + }, + { + "epoch": 0.02, + "learning_rate": 2.757556688677595e-05, + "loss": 3.934, + "step": 1369600 + }, + { + "epoch": 0.02, + "learning_rate": 2.756718093926543e-05, + "loss": 3.9408, + "step": 1370112 + }, + { + "epoch": 0.02, + "learning_rate": 2.755879499175491e-05, + "loss": 3.9446, + "step": 1370624 + }, + { + "epoch": 0.02, + "learning_rate": 2.755040904424439e-05, + "loss": 3.9348, + "step": 1371136 + }, + { + "epoch": 0.02, + "learning_rate": 2.75420394755376e-05, + "loss": 3.9479, + "step": 1371648 + }, + { + "epoch": 0.02, + "learning_rate": 2.753365352802708e-05, + "loss": 3.9392, + "step": 1372160 + }, + { + "epoch": 0.02, + "learning_rate": 2.7525267580516563e-05, + "loss": 3.9445, + "step": 1372672 + }, + { + "epoch": 0.02, + "learning_rate": 2.7516881633006043e-05, + "loss": 3.9439, + "step": 1373184 + }, + { + "epoch": 0.02, + "learning_rate": 2.7508512064299252e-05, + "loss": 3.9346, + "step": 1373696 + }, + { + "epoch": 0.03, + "eval_loss": 4.008107662200928, + "eval_runtime": 305.2146, + "eval_samples_per_second": 1250.238, + "eval_steps_per_second": 39.071, + "step": 1373747 + }, + { + "epoch": 1.0, + "learning_rate": 2.7500126116788732e-05, + "loss": 3.9331, + "step": 1374208 + }, + { + "epoch": 1.0, + "learning_rate": 2.7491740169278212e-05, + "loss": 3.9288, + "step": 1374720 + }, + { + "epoch": 1.0, + "learning_rate": 2.7483354221767692e-05, + "loss": 3.951, + "step": 1375232 + }, + { + "epoch": 1.0, + "learning_rate": 2.7474968274257172e-05, + "loss": 3.938, + "step": 1375744 + }, + { + "epoch": 1.0, + "learning_rate": 2.7466598705550385e-05, + "loss": 3.9495, + "step": 1376256 + }, + { + "epoch": 1.0, + "learning_rate": 2.7458212758039865e-05, + "loss": 3.9354, + "step": 1376768 + }, + { + "epoch": 1.0, + "learning_rate": 2.7449826810529345e-05, + "loss": 3.9368, + "step": 1377280 + }, + { + "epoch": 1.0, + "learning_rate": 2.7441440863018825e-05, + "loss": 3.9258, + "step": 1377792 + }, + { + "epoch": 1.0, + "learning_rate": 2.7433054915508304e-05, + "loss": 3.9409, + "step": 1378304 + }, + { + "epoch": 1.0, + "learning_rate": 2.7424668967997784e-05, + "loss": 3.9365, + "step": 1378816 + }, + { + "epoch": 1.0, + "learning_rate": 2.7416283020487264e-05, + "loss": 3.9553, + "step": 1379328 + }, + { + "epoch": 1.0, + "learning_rate": 2.7407897072976744e-05, + "loss": 3.9465, + "step": 1379840 + }, + { + "epoch": 1.0, + "learning_rate": 2.7399527504269957e-05, + "loss": 3.9288, + "step": 1380352 + }, + { + "epoch": 1.0, + "learning_rate": 2.7391141556759437e-05, + "loss": 3.9341, + "step": 1380864 + }, + { + "epoch": 1.0, + "learning_rate": 2.7382755609248917e-05, + "loss": 3.9414, + "step": 1381376 + }, + { + "epoch": 1.0, + "learning_rate": 2.7374369661738397e-05, + "loss": 3.9214, + "step": 1381888 + }, + { + "epoch": 1.0, + "learning_rate": 2.7365983714227877e-05, + "loss": 3.9431, + "step": 1382400 + }, + { + "epoch": 1.0, + "learning_rate": 2.7357597766717353e-05, + "loss": 3.9381, + "step": 1382912 + }, + { + "epoch": 1.0, + "learning_rate": 2.734922819801057e-05, + "loss": 3.9303, + "step": 1383424 + }, + { + "epoch": 1.0, + "learning_rate": 2.734084225050005e-05, + "loss": 3.9598, + "step": 1383936 + }, + { + "epoch": 1.0, + "learning_rate": 2.733245630298953e-05, + "loss": 3.9356, + "step": 1384448 + }, + { + "epoch": 1.0, + "learning_rate": 2.7324070355479002e-05, + "loss": 3.9428, + "step": 1384960 + }, + { + "epoch": 1.0, + "learning_rate": 2.7315684407968482e-05, + "loss": 3.9353, + "step": 1385472 + }, + { + "epoch": 1.0, + "learning_rate": 2.7307298460457965e-05, + "loss": 3.9495, + "step": 1385984 + }, + { + "epoch": 1.0, + "learning_rate": 2.7298912512947445e-05, + "loss": 3.9283, + "step": 1386496 + }, + { + "epoch": 1.0, + "learning_rate": 2.7290526565436925e-05, + "loss": 3.9379, + "step": 1387008 + }, + { + "epoch": 1.0, + "learning_rate": 2.7282156996730134e-05, + "loss": 3.928, + "step": 1387520 + }, + { + "epoch": 1.0, + "learning_rate": 2.7273771049219614e-05, + "loss": 3.9368, + "step": 1388032 + }, + { + "epoch": 1.0, + "learning_rate": 2.7265385101709094e-05, + "loss": 3.9343, + "step": 1388544 + }, + { + "epoch": 1.01, + "learning_rate": 2.7256999154198574e-05, + "loss": 3.9339, + "step": 1389056 + }, + { + "epoch": 1.01, + "learning_rate": 2.7248629585491787e-05, + "loss": 3.9362, + "step": 1389568 + }, + { + "epoch": 1.01, + "learning_rate": 2.7240243637981267e-05, + "loss": 3.9421, + "step": 1390080 + }, + { + "epoch": 1.01, + "learning_rate": 2.7231857690470747e-05, + "loss": 3.9383, + "step": 1390592 + }, + { + "epoch": 1.01, + "learning_rate": 2.7223471742960227e-05, + "loss": 3.9508, + "step": 1391104 + }, + { + "epoch": 1.01, + "learning_rate": 2.7215102174253436e-05, + "loss": 3.9404, + "step": 1391616 + }, + { + "epoch": 1.01, + "learning_rate": 2.720671622674292e-05, + "loss": 3.9406, + "step": 1392128 + }, + { + "epoch": 1.01, + "learning_rate": 2.71983302792324e-05, + "loss": 3.9322, + "step": 1392640 + }, + { + "epoch": 1.01, + "learning_rate": 2.718994433172188e-05, + "loss": 3.9368, + "step": 1393152 + }, + { + "epoch": 1.01, + "learning_rate": 2.718155838421136e-05, + "loss": 3.927, + "step": 1393664 + }, + { + "epoch": 1.01, + "learning_rate": 2.7173188815504568e-05, + "loss": 3.9348, + "step": 1394176 + }, + { + "epoch": 1.01, + "learning_rate": 2.7164802867994048e-05, + "loss": 3.9326, + "step": 1394688 + }, + { + "epoch": 1.01, + "learning_rate": 2.7156416920483528e-05, + "loss": 3.9449, + "step": 1395200 + }, + { + "epoch": 1.01, + "learning_rate": 2.714804735177674e-05, + "loss": 3.9276, + "step": 1395712 + }, + { + "epoch": 1.01, + "learning_rate": 2.713966140426622e-05, + "loss": 3.9401, + "step": 1396224 + }, + { + "epoch": 1.01, + "learning_rate": 2.71312754567557e-05, + "loss": 3.9405, + "step": 1396736 + }, + { + "epoch": 1.01, + "learning_rate": 2.712288950924518e-05, + "loss": 3.9394, + "step": 1397248 + }, + { + "epoch": 1.01, + "learning_rate": 2.711451994053839e-05, + "loss": 3.9392, + "step": 1397760 + }, + { + "epoch": 1.01, + "learning_rate": 2.7106133993027873e-05, + "loss": 3.9205, + "step": 1398272 + }, + { + "epoch": 1.01, + "learning_rate": 2.7097748045517353e-05, + "loss": 3.9306, + "step": 1398784 + }, + { + "epoch": 1.01, + "learning_rate": 2.7089362098006833e-05, + "loss": 3.944, + "step": 1399296 + }, + { + "epoch": 1.01, + "learning_rate": 2.7080976150496313e-05, + "loss": 3.9372, + "step": 1399808 + }, + { + "epoch": 1.01, + "learning_rate": 2.7072590202985793e-05, + "loss": 3.9325, + "step": 1400320 + }, + { + "epoch": 1.01, + "learning_rate": 2.7064220634279002e-05, + "loss": 3.9239, + "step": 1400832 + }, + { + "epoch": 1.01, + "learning_rate": 2.7055834686768482e-05, + "loss": 3.9352, + "step": 1401344 + }, + { + "epoch": 1.01, + "learning_rate": 2.7047448739257965e-05, + "loss": 3.9132, + "step": 1401856 + }, + { + "epoch": 1.01, + "learning_rate": 2.7039062791747445e-05, + "loss": 3.9508, + "step": 1402368 + }, + { + "epoch": 1.01, + "learning_rate": 2.7030693223040654e-05, + "loss": 3.9137, + "step": 1402880 + }, + { + "epoch": 1.01, + "learning_rate": 2.7022307275530134e-05, + "loss": 3.9445, + "step": 1403392 + }, + { + "epoch": 1.01, + "learning_rate": 2.7013921328019614e-05, + "loss": 3.9345, + "step": 1403904 + }, + { + "epoch": 1.01, + "learning_rate": 2.7005535380509094e-05, + "loss": 3.9256, + "step": 1404416 + }, + { + "epoch": 1.01, + "learning_rate": 2.6997149432998574e-05, + "loss": 3.9405, + "step": 1404928 + }, + { + "epoch": 1.01, + "learning_rate": 2.6988779864291786e-05, + "loss": 3.9288, + "step": 1405440 + }, + { + "epoch": 1.01, + "learning_rate": 2.6980393916781266e-05, + "loss": 3.9269, + "step": 1405952 + }, + { + "epoch": 1.01, + "learning_rate": 2.6972007969270746e-05, + "loss": 3.9193, + "step": 1406464 + }, + { + "epoch": 1.01, + "learning_rate": 2.6963622021760226e-05, + "loss": 3.944, + "step": 1406976 + }, + { + "epoch": 1.01, + "learning_rate": 2.6955236074249706e-05, + "loss": 3.9264, + "step": 1407488 + }, + { + "epoch": 1.01, + "learning_rate": 2.6946850126739186e-05, + "loss": 3.9328, + "step": 1408000 + }, + { + "epoch": 1.01, + "learning_rate": 2.6938464179228663e-05, + "loss": 3.9158, + "step": 1408512 + }, + { + "epoch": 1.01, + "learning_rate": 2.693009461052188e-05, + "loss": 3.9263, + "step": 1409024 + }, + { + "epoch": 1.01, + "learning_rate": 2.692170866301136e-05, + "loss": 3.9356, + "step": 1409536 + }, + { + "epoch": 1.01, + "learning_rate": 2.691332271550084e-05, + "loss": 3.9397, + "step": 1410048 + }, + { + "epoch": 1.01, + "learning_rate": 2.6904936767990312e-05, + "loss": 3.9309, + "step": 1410560 + }, + { + "epoch": 1.01, + "learning_rate": 2.689655082047979e-05, + "loss": 3.9396, + "step": 1411072 + }, + { + "epoch": 1.01, + "learning_rate": 2.6888181251773008e-05, + "loss": 3.9407, + "step": 1411584 + }, + { + "epoch": 1.01, + "learning_rate": 2.6879795304262484e-05, + "loss": 3.9346, + "step": 1412096 + }, + { + "epoch": 1.01, + "learning_rate": 2.68714257355557e-05, + "loss": 3.9389, + "step": 1412608 + }, + { + "epoch": 1.01, + "learning_rate": 2.686303978804518e-05, + "loss": 3.9336, + "step": 1413120 + }, + { + "epoch": 1.01, + "learning_rate": 2.685465384053466e-05, + "loss": 3.9302, + "step": 1413632 + }, + { + "epoch": 1.01, + "learning_rate": 2.6846267893024136e-05, + "loss": 3.9288, + "step": 1414144 + }, + { + "epoch": 1.01, + "learning_rate": 2.6837881945513616e-05, + "loss": 3.9375, + "step": 1414656 + }, + { + "epoch": 1.01, + "learning_rate": 2.6829495998003096e-05, + "loss": 3.9388, + "step": 1415168 + }, + { + "epoch": 1.01, + "learning_rate": 2.6821110050492576e-05, + "loss": 3.9477, + "step": 1415680 + }, + { + "epoch": 1.01, + "learning_rate": 2.6812724102982056e-05, + "loss": 3.9333, + "step": 1416192 + }, + { + "epoch": 1.01, + "learning_rate": 2.6804338155471536e-05, + "loss": 3.9145, + "step": 1416704 + }, + { + "epoch": 1.01, + "learning_rate": 2.6795952207961016e-05, + "loss": 3.9228, + "step": 1417216 + }, + { + "epoch": 1.01, + "learning_rate": 2.6787566260450496e-05, + "loss": 3.9364, + "step": 1417728 + }, + { + "epoch": 1.01, + "learning_rate": 2.6779180312939976e-05, + "loss": 3.9323, + "step": 1418240 + }, + { + "epoch": 1.01, + "learning_rate": 2.6770827123036918e-05, + "loss": 3.9286, + "step": 1418752 + }, + { + "epoch": 1.01, + "learning_rate": 2.6762441175526398e-05, + "loss": 3.9379, + "step": 1419264 + }, + { + "epoch": 1.02, + "learning_rate": 2.6754055228015878e-05, + "loss": 3.9283, + "step": 1419776 + }, + { + "epoch": 1.02, + "learning_rate": 2.6745669280505358e-05, + "loss": 3.9239, + "step": 1420288 + }, + { + "epoch": 1.02, + "learning_rate": 2.6737283332994838e-05, + "loss": 3.9286, + "step": 1420800 + }, + { + "epoch": 1.02, + "learning_rate": 2.672889738548432e-05, + "loss": 3.9446, + "step": 1421312 + }, + { + "epoch": 1.02, + "learning_rate": 2.672052781677753e-05, + "loss": 3.9381, + "step": 1421824 + }, + { + "epoch": 1.02, + "learning_rate": 2.671214186926701e-05, + "loss": 3.9427, + "step": 1422336 + }, + { + "epoch": 1.02, + "learning_rate": 2.670375592175649e-05, + "loss": 3.922, + "step": 1422848 + }, + { + "epoch": 1.02, + "learning_rate": 2.669536997424597e-05, + "loss": 3.9301, + "step": 1423360 + }, + { + "epoch": 1.02, + "learning_rate": 2.668698402673545e-05, + "loss": 3.9332, + "step": 1423872 + }, + { + "epoch": 1.02, + "learning_rate": 2.667859807922493e-05, + "loss": 3.9352, + "step": 1424384 + }, + { + "epoch": 1.02, + "learning_rate": 2.6670212131714413e-05, + "loss": 3.9436, + "step": 1424896 + }, + { + "epoch": 1.02, + "learning_rate": 2.6661826184203893e-05, + "loss": 3.9267, + "step": 1425408 + }, + { + "epoch": 1.02, + "learning_rate": 2.6653456615497102e-05, + "loss": 3.9304, + "step": 1425920 + }, + { + "epoch": 1.02, + "learning_rate": 2.6645070667986582e-05, + "loss": 3.9352, + "step": 1426432 + }, + { + "epoch": 1.02, + "learning_rate": 2.6636684720476062e-05, + "loss": 3.9364, + "step": 1426944 + }, + { + "epoch": 1.02, + "learning_rate": 2.6628298772965542e-05, + "loss": 3.9211, + "step": 1427456 + }, + { + "epoch": 1.02, + "learning_rate": 2.6619929204258755e-05, + "loss": 3.9283, + "step": 1427968 + }, + { + "epoch": 1.02, + "learning_rate": 2.6611559635551964e-05, + "loss": 3.9293, + "step": 1428480 + }, + { + "epoch": 1.02, + "learning_rate": 2.6603173688041444e-05, + "loss": 3.9263, + "step": 1428992 + }, + { + "epoch": 1.02, + "learning_rate": 2.6594787740530924e-05, + "loss": 3.9242, + "step": 1429504 + }, + { + "epoch": 1.02, + "learning_rate": 2.6586401793020403e-05, + "loss": 3.927, + "step": 1430016 + }, + { + "epoch": 1.02, + "learning_rate": 2.6578015845509883e-05, + "loss": 3.9274, + "step": 1430528 + }, + { + "epoch": 1.02, + "learning_rate": 2.6569629897999367e-05, + "loss": 3.9318, + "step": 1431040 + }, + { + "epoch": 1.02, + "learning_rate": 2.6561243950488847e-05, + "loss": 3.9221, + "step": 1431552 + }, + { + "epoch": 1.02, + "learning_rate": 2.655285800297832e-05, + "loss": 3.9321, + "step": 1432064 + }, + { + "epoch": 1.02, + "learning_rate": 2.65444720554678e-05, + "loss": 3.9456, + "step": 1432576 + }, + { + "epoch": 1.02, + "learning_rate": 2.653608610795728e-05, + "loss": 3.9407, + "step": 1433088 + }, + { + "epoch": 1.02, + "learning_rate": 2.652770016044676e-05, + "loss": 3.9359, + "step": 1433600 + }, + { + "epoch": 1.02, + "learning_rate": 2.6519314212936243e-05, + "loss": 3.9345, + "step": 1434112 + }, + { + "epoch": 1.02, + "learning_rate": 2.6510944644229452e-05, + "loss": 3.9303, + "step": 1434624 + }, + { + "epoch": 1.02, + "learning_rate": 2.6502558696718932e-05, + "loss": 3.9296, + "step": 1435136 + }, + { + "epoch": 1.02, + "learning_rate": 2.6494205506815877e-05, + "loss": 3.9255, + "step": 1435648 + }, + { + "epoch": 1.02, + "learning_rate": 2.6485819559305357e-05, + "loss": 3.927, + "step": 1436160 + }, + { + "epoch": 1.02, + "learning_rate": 2.6477433611794837e-05, + "loss": 3.9275, + "step": 1436672 + }, + { + "epoch": 1.02, + "learning_rate": 2.646904766428432e-05, + "loss": 3.9386, + "step": 1437184 + }, + { + "epoch": 1.02, + "learning_rate": 2.6460661716773794e-05, + "loss": 3.9318, + "step": 1437696 + }, + { + "epoch": 1.02, + "learning_rate": 2.6452275769263274e-05, + "loss": 3.9315, + "step": 1438208 + }, + { + "epoch": 1.02, + "learning_rate": 2.6443889821752754e-05, + "loss": 3.9315, + "step": 1438720 + }, + { + "epoch": 1.02, + "learning_rate": 2.6435503874242233e-05, + "loss": 3.9264, + "step": 1439232 + }, + { + "epoch": 1.02, + "learning_rate": 2.6427117926731713e-05, + "loss": 3.9226, + "step": 1439744 + }, + { + "epoch": 1.02, + "learning_rate": 2.6418731979221197e-05, + "loss": 3.9446, + "step": 1440256 + }, + { + "epoch": 1.02, + "learning_rate": 2.6410346031710677e-05, + "loss": 3.9402, + "step": 1440768 + }, + { + "epoch": 1.02, + "learning_rate": 2.6401960084200157e-05, + "loss": 3.9373, + "step": 1441280 + }, + { + "epoch": 1.02, + "learning_rate": 2.6393590515493366e-05, + "loss": 3.9286, + "step": 1441792 + }, + { + "epoch": 1.02, + "learning_rate": 2.6385220946786575e-05, + "loss": 3.9322, + "step": 1442304 + }, + { + "epoch": 1.02, + "learning_rate": 2.6376834999276058e-05, + "loss": 3.9364, + "step": 1442816 + }, + { + "epoch": 1.02, + "learning_rate": 2.6368449051765538e-05, + "loss": 3.9484, + "step": 1443328 + }, + { + "epoch": 1.02, + "learning_rate": 2.6360063104255018e-05, + "loss": 3.9348, + "step": 1443840 + }, + { + "epoch": 1.02, + "learning_rate": 2.6351677156744498e-05, + "loss": 3.9301, + "step": 1444352 + }, + { + "epoch": 1.02, + "learning_rate": 2.6343291209233978e-05, + "loss": 3.9334, + "step": 1444864 + }, + { + "epoch": 1.02, + "learning_rate": 2.6334905261723458e-05, + "loss": 3.9299, + "step": 1445376 + }, + { + "epoch": 1.02, + "learning_rate": 2.6326535693016667e-05, + "loss": 3.9257, + "step": 1445888 + }, + { + "epoch": 1.02, + "learning_rate": 2.6318149745506147e-05, + "loss": 3.9322, + "step": 1446400 + }, + { + "epoch": 1.02, + "learning_rate": 2.630976379799563e-05, + "loss": 3.9388, + "step": 1446912 + }, + { + "epoch": 1.02, + "learning_rate": 2.630137785048511e-05, + "loss": 3.926, + "step": 1447424 + }, + { + "epoch": 1.02, + "learning_rate": 2.629299190297459e-05, + "loss": 3.9374, + "step": 1447936 + }, + { + "epoch": 1.02, + "learning_rate": 2.628460595546407e-05, + "loss": 3.9342, + "step": 1448448 + }, + { + "epoch": 1.02, + "learning_rate": 2.627622000795355e-05, + "loss": 3.9312, + "step": 1448960 + }, + { + "epoch": 1.02, + "learning_rate": 2.626783406044303e-05, + "loss": 3.9359, + "step": 1449472 + }, + { + "epoch": 1.02, + "learning_rate": 2.625946449173624e-05, + "loss": 3.9222, + "step": 1449984 + }, + { + "epoch": 1.03, + "eval_loss": 4.004481315612793, + "eval_runtime": 314.0614, + "eval_samples_per_second": 1215.02, + "eval_steps_per_second": 37.97, + "step": 1450067 + }, + { + "epoch": 0.0, + "learning_rate": 2.6251078544225723e-05, + "loss": 3.9196, + "step": 1450496 + }, + { + "epoch": 0.0, + "learning_rate": 2.6242692596715203e-05, + "loss": 3.9229, + "step": 1451008 + }, + { + "epoch": 0.0, + "learning_rate": 2.6234306649204683e-05, + "loss": 3.9429, + "step": 1451520 + }, + { + "epoch": 0.0, + "learning_rate": 2.6225920701694156e-05, + "loss": 3.9269, + "step": 1452032 + }, + { + "epoch": 0.0, + "learning_rate": 2.6217534754183636e-05, + "loss": 3.9436, + "step": 1452544 + }, + { + "epoch": 0.0, + "learning_rate": 2.6209148806673116e-05, + "loss": 3.9266, + "step": 1453056 + }, + { + "epoch": 0.0, + "learning_rate": 2.62007628591626e-05, + "loss": 3.9286, + "step": 1453568 + }, + { + "epoch": 0.0, + "learning_rate": 2.619237691165208e-05, + "loss": 3.9195, + "step": 1454080 + }, + { + "epoch": 0.0, + "learning_rate": 2.618399096414156e-05, + "loss": 3.9346, + "step": 1454592 + }, + { + "epoch": 0.0, + "learning_rate": 2.617560501663104e-05, + "loss": 3.9248, + "step": 1455104 + }, + { + "epoch": 0.0, + "learning_rate": 2.616721906912052e-05, + "loss": 3.9474, + "step": 1455616 + }, + { + "epoch": 0.0, + "learning_rate": 2.615883312161e-05, + "loss": 3.9356, + "step": 1456128 + }, + { + "epoch": 0.0, + "learning_rate": 2.6150463552903208e-05, + "loss": 3.9178, + "step": 1456640 + }, + { + "epoch": 0.0, + "learning_rate": 2.614207760539269e-05, + "loss": 3.9246, + "step": 1457152 + }, + { + "epoch": 0.0, + "learning_rate": 2.613369165788217e-05, + "loss": 3.934, + "step": 1457664 + }, + { + "epoch": 0.0, + "learning_rate": 2.612530571037165e-05, + "loss": 3.9165, + "step": 1458176 + }, + { + "epoch": 0.0, + "learning_rate": 2.611693614166486e-05, + "loss": 3.9321, + "step": 1458688 + }, + { + "epoch": 0.0, + "learning_rate": 2.610855019415434e-05, + "loss": 3.9276, + "step": 1459200 + }, + { + "epoch": 0.0, + "learning_rate": 2.610016424664382e-05, + "loss": 3.923, + "step": 1459712 + }, + { + "epoch": 0.0, + "learning_rate": 2.60917782991333e-05, + "loss": 3.9518, + "step": 1460224 + }, + { + "epoch": 0.0, + "learning_rate": 2.6083392351622783e-05, + "loss": 3.9296, + "step": 1460736 + }, + { + "epoch": 0.0, + "learning_rate": 2.6075006404112263e-05, + "loss": 3.9299, + "step": 1461248 + }, + { + "epoch": 0.0, + "learning_rate": 2.6066620456601743e-05, + "loss": 3.9264, + "step": 1461760 + }, + { + "epoch": 0.0, + "learning_rate": 2.6058234509091223e-05, + "loss": 3.9442, + "step": 1462272 + }, + { + "epoch": 0.0, + "learning_rate": 2.6049848561580696e-05, + "loss": 3.9216, + "step": 1462784 + }, + { + "epoch": 0.0, + "learning_rate": 2.6041478992873912e-05, + "loss": 3.9258, + "step": 1463296 + }, + { + "epoch": 0.0, + "learning_rate": 2.6033093045363392e-05, + "loss": 3.9223, + "step": 1463808 + }, + { + "epoch": 0.0, + "learning_rate": 2.602470709785287e-05, + "loss": 3.9305, + "step": 1464320 + }, + { + "epoch": 0.0, + "learning_rate": 2.601632115034235e-05, + "loss": 3.9249, + "step": 1464832 + }, + { + "epoch": 0.01, + "learning_rate": 2.600793520283183e-05, + "loss": 3.9245, + "step": 1465344 + }, + { + "epoch": 0.01, + "learning_rate": 2.599954925532131e-05, + "loss": 3.9314, + "step": 1465856 + }, + { + "epoch": 0.01, + "learning_rate": 2.599116330781079e-05, + "loss": 3.9317, + "step": 1466368 + }, + { + "epoch": 0.01, + "learning_rate": 2.598277736030027e-05, + "loss": 3.9308, + "step": 1466880 + }, + { + "epoch": 0.01, + "learning_rate": 2.597440779159348e-05, + "loss": 3.9398, + "step": 1467392 + }, + { + "epoch": 0.01, + "learning_rate": 2.5966038222886697e-05, + "loss": 3.9306, + "step": 1467904 + }, + { + "epoch": 0.01, + "learning_rate": 2.5957668654179906e-05, + "loss": 3.9333, + "step": 1468416 + }, + { + "epoch": 0.01, + "learning_rate": 2.5949282706669386e-05, + "loss": 3.9201, + "step": 1468928 + }, + { + "epoch": 0.01, + "learning_rate": 2.5940896759158866e-05, + "loss": 3.9322, + "step": 1469440 + }, + { + "epoch": 0.01, + "learning_rate": 2.5932510811648343e-05, + "loss": 3.9178, + "step": 1469952 + }, + { + "epoch": 0.01, + "learning_rate": 2.5924124864137823e-05, + "loss": 3.9274, + "step": 1470464 + }, + { + "epoch": 0.01, + "learning_rate": 2.5915738916627302e-05, + "loss": 3.9244, + "step": 1470976 + }, + { + "epoch": 0.01, + "learning_rate": 2.5907352969116782e-05, + "loss": 3.9361, + "step": 1471488 + }, + { + "epoch": 0.01, + "learning_rate": 2.5898967021606262e-05, + "loss": 3.9176, + "step": 1472000 + }, + { + "epoch": 0.01, + "learning_rate": 2.5890597452899475e-05, + "loss": 3.9274, + "step": 1472512 + }, + { + "epoch": 0.01, + "learning_rate": 2.5882211505388955e-05, + "loss": 3.9352, + "step": 1473024 + }, + { + "epoch": 0.01, + "learning_rate": 2.5873825557878435e-05, + "loss": 3.9327, + "step": 1473536 + }, + { + "epoch": 0.01, + "learning_rate": 2.5865439610367915e-05, + "loss": 3.9337, + "step": 1474048 + }, + { + "epoch": 0.01, + "learning_rate": 2.5857053662857395e-05, + "loss": 3.9124, + "step": 1474560 + }, + { + "epoch": 0.01, + "learning_rate": 2.5848667715346875e-05, + "loss": 3.9209, + "step": 1475072 + }, + { + "epoch": 0.01, + "learning_rate": 2.5840281767836355e-05, + "loss": 3.9331, + "step": 1475584 + }, + { + "epoch": 0.01, + "learning_rate": 2.5831912199129564e-05, + "loss": 3.9272, + "step": 1476096 + }, + { + "epoch": 0.01, + "learning_rate": 2.5823542630422776e-05, + "loss": 3.9233, + "step": 1476608 + }, + { + "epoch": 0.01, + "learning_rate": 2.5815156682912256e-05, + "loss": 3.9183, + "step": 1477120 + }, + { + "epoch": 0.01, + "learning_rate": 2.5806770735401736e-05, + "loss": 3.9289, + "step": 1477632 + }, + { + "epoch": 0.01, + "learning_rate": 2.5798384787891216e-05, + "loss": 3.9069, + "step": 1478144 + }, + { + "epoch": 0.01, + "learning_rate": 2.5789998840380696e-05, + "loss": 3.9346, + "step": 1478656 + }, + { + "epoch": 0.01, + "learning_rate": 2.5781612892870176e-05, + "loss": 3.9132, + "step": 1479168 + }, + { + "epoch": 0.01, + "learning_rate": 2.5773226945359656e-05, + "loss": 3.9279, + "step": 1479680 + }, + { + "epoch": 0.01, + "learning_rate": 2.576484099784914e-05, + "loss": 3.9304, + "step": 1480192 + }, + { + "epoch": 0.01, + "learning_rate": 2.575645505033862e-05, + "loss": 3.9183, + "step": 1480704 + }, + { + "epoch": 0.01, + "learning_rate": 2.57480691028281e-05, + "loss": 3.9311, + "step": 1481216 + }, + { + "epoch": 0.01, + "learning_rate": 2.573968315531758e-05, + "loss": 3.9232, + "step": 1481728 + }, + { + "epoch": 0.01, + "learning_rate": 2.5731297207807052e-05, + "loss": 3.9186, + "step": 1482240 + }, + { + "epoch": 0.01, + "learning_rate": 2.5722927639100268e-05, + "loss": 3.9138, + "step": 1482752 + }, + { + "epoch": 0.01, + "learning_rate": 2.5714541691589748e-05, + "loss": 3.9326, + "step": 1483264 + }, + { + "epoch": 0.01, + "learning_rate": 2.570615574407923e-05, + "loss": 3.9184, + "step": 1483776 + }, + { + "epoch": 0.01, + "learning_rate": 2.5697769796568705e-05, + "loss": 3.9242, + "step": 1484288 + }, + { + "epoch": 0.01, + "learning_rate": 2.568940022786192e-05, + "loss": 3.9099, + "step": 1484800 + }, + { + "epoch": 0.01, + "learning_rate": 2.56810142803514e-05, + "loss": 3.9165, + "step": 1485312 + }, + { + "epoch": 0.01, + "learning_rate": 2.567262833284088e-05, + "loss": 3.9265, + "step": 1485824 + }, + { + "epoch": 0.01, + "learning_rate": 2.5664242385330357e-05, + "loss": 3.933, + "step": 1486336 + }, + { + "epoch": 0.01, + "learning_rate": 2.5655872816623573e-05, + "loss": 3.919, + "step": 1486848 + }, + { + "epoch": 0.01, + "learning_rate": 2.5647486869113053e-05, + "loss": 3.9358, + "step": 1487360 + }, + { + "epoch": 0.01, + "learning_rate": 2.5639100921602526e-05, + "loss": 3.9337, + "step": 1487872 + }, + { + "epoch": 0.01, + "learning_rate": 2.5630714974092006e-05, + "loss": 3.9253, + "step": 1488384 + }, + { + "epoch": 0.01, + "learning_rate": 2.5622329026581486e-05, + "loss": 3.9288, + "step": 1488896 + }, + { + "epoch": 0.01, + "learning_rate": 2.5613959457874702e-05, + "loss": 3.9241, + "step": 1489408 + }, + { + "epoch": 0.01, + "learning_rate": 2.560557351036418e-05, + "loss": 3.9236, + "step": 1489920 + }, + { + "epoch": 0.01, + "learning_rate": 2.559718756285366e-05, + "loss": 3.921, + "step": 1490432 + }, + { + "epoch": 0.01, + "learning_rate": 2.5588801615343138e-05, + "loss": 3.9275, + "step": 1490944 + }, + { + "epoch": 0.01, + "learning_rate": 2.5580415667832618e-05, + "loss": 3.933, + "step": 1491456 + }, + { + "epoch": 0.01, + "learning_rate": 2.5572029720322098e-05, + "loss": 3.9379, + "step": 1491968 + }, + { + "epoch": 0.01, + "learning_rate": 2.556366015161531e-05, + "loss": 3.9271, + "step": 1492480 + }, + { + "epoch": 0.01, + "learning_rate": 2.555527420410479e-05, + "loss": 3.904, + "step": 1492992 + }, + { + "epoch": 0.01, + "learning_rate": 2.554688825659427e-05, + "loss": 3.9182, + "step": 1493504 + }, + { + "epoch": 0.01, + "learning_rate": 2.553850230908375e-05, + "loss": 3.9235, + "step": 1494016 + }, + { + "epoch": 0.01, + "learning_rate": 2.553013274037696e-05, + "loss": 3.925, + "step": 1494528 + }, + { + "epoch": 0.01, + "learning_rate": 2.552174679286644e-05, + "loss": 3.9195, + "step": 1495040 + }, + { + "epoch": 0.01, + "learning_rate": 2.5513360845355923e-05, + "loss": 3.9288, + "step": 1495552 + }, + { + "epoch": 0.02, + "learning_rate": 2.5504974897845403e-05, + "loss": 3.9212, + "step": 1496064 + }, + { + "epoch": 0.02, + "learning_rate": 2.5496588950334883e-05, + "loss": 3.9149, + "step": 1496576 + }, + { + "epoch": 0.02, + "learning_rate": 2.5488203002824363e-05, + "loss": 3.9266, + "step": 1497088 + }, + { + "epoch": 0.02, + "learning_rate": 2.5479833434117572e-05, + "loss": 3.9294, + "step": 1497600 + }, + { + "epoch": 0.02, + "learning_rate": 2.5471447486607052e-05, + "loss": 3.9265, + "step": 1498112 + }, + { + "epoch": 0.02, + "learning_rate": 2.5463061539096532e-05, + "loss": 3.938, + "step": 1498624 + }, + { + "epoch": 0.02, + "learning_rate": 2.5454675591586015e-05, + "loss": 3.9186, + "step": 1499136 + }, + { + "epoch": 0.02, + "learning_rate": 2.5446289644075495e-05, + "loss": 3.9192, + "step": 1499648 + }, + { + "epoch": 0.02, + "learning_rate": 2.5437903696564975e-05, + "loss": 3.925, + "step": 1500160 + }, + { + "epoch": 0.02, + "learning_rate": 2.5429534127858184e-05, + "loss": 3.9269, + "step": 1500672 + }, + { + "epoch": 0.02, + "learning_rate": 2.5421148180347664e-05, + "loss": 3.9342, + "step": 1501184 + }, + { + "epoch": 0.02, + "learning_rate": 2.5412762232837144e-05, + "loss": 3.9194, + "step": 1501696 + }, + { + "epoch": 0.02, + "learning_rate": 2.5404376285326624e-05, + "loss": 3.9242, + "step": 1502208 + }, + { + "epoch": 0.02, + "learning_rate": 2.5396006716619837e-05, + "loss": 3.9257, + "step": 1502720 + }, + { + "epoch": 0.02, + "learning_rate": 2.5387620769109316e-05, + "loss": 3.9313, + "step": 1503232 + }, + { + "epoch": 0.02, + "learning_rate": 2.5379234821598796e-05, + "loss": 3.9134, + "step": 1503744 + }, + { + "epoch": 0.02, + "learning_rate": 2.5370848874088276e-05, + "loss": 3.9218, + "step": 1504256 + }, + { + "epoch": 0.02, + "learning_rate": 2.5362462926577756e-05, + "loss": 3.9227, + "step": 1504768 + }, + { + "epoch": 0.02, + "learning_rate": 2.5354076979067236e-05, + "loss": 3.9168, + "step": 1505280 + }, + { + "epoch": 0.02, + "learning_rate": 2.5345691031556716e-05, + "loss": 3.9153, + "step": 1505792 + }, + { + "epoch": 0.02, + "learning_rate": 2.5337305084046193e-05, + "loss": 3.9196, + "step": 1506304 + }, + { + "epoch": 0.02, + "learning_rate": 2.532893551533941e-05, + "loss": 3.9238, + "step": 1506816 + }, + { + "epoch": 0.02, + "learning_rate": 2.532054956782889e-05, + "loss": 3.9203, + "step": 1507328 + }, + { + "epoch": 0.02, + "learning_rate": 2.5312163620318362e-05, + "loss": 3.9163, + "step": 1507840 + }, + { + "epoch": 0.02, + "learning_rate": 2.5303794051611578e-05, + "loss": 3.9223, + "step": 1508352 + }, + { + "epoch": 0.02, + "learning_rate": 2.5295408104101058e-05, + "loss": 3.9388, + "step": 1508864 + }, + { + "epoch": 0.02, + "learning_rate": 2.528702215659054e-05, + "loss": 3.934, + "step": 1509376 + }, + { + "epoch": 0.02, + "learning_rate": 2.5278636209080014e-05, + "loss": 3.9303, + "step": 1509888 + }, + { + "epoch": 0.02, + "learning_rate": 2.5270250261569494e-05, + "loss": 3.9227, + "step": 1510400 + }, + { + "epoch": 0.02, + "learning_rate": 2.5261864314058974e-05, + "loss": 3.9242, + "step": 1510912 + }, + { + "epoch": 0.02, + "learning_rate": 2.525349474535219e-05, + "loss": 3.9224, + "step": 1511424 + }, + { + "epoch": 0.02, + "learning_rate": 2.5245108797841667e-05, + "loss": 3.9162, + "step": 1511936 + }, + { + "epoch": 0.02, + "learning_rate": 2.5236722850331146e-05, + "loss": 3.9223, + "step": 1512448 + }, + { + "epoch": 0.02, + "learning_rate": 2.5228336902820626e-05, + "loss": 3.9198, + "step": 1512960 + }, + { + "epoch": 0.02, + "learning_rate": 2.5219967334113836e-05, + "loss": 3.932, + "step": 1513472 + }, + { + "epoch": 0.02, + "learning_rate": 2.5211581386603315e-05, + "loss": 3.9194, + "step": 1513984 + }, + { + "epoch": 0.02, + "learning_rate": 2.520321181789653e-05, + "loss": 3.9279, + "step": 1514496 + }, + { + "epoch": 0.02, + "learning_rate": 2.519482587038601e-05, + "loss": 3.9203, + "step": 1515008 + }, + { + "epoch": 0.02, + "learning_rate": 2.5186439922875488e-05, + "loss": 3.9179, + "step": 1515520 + }, + { + "epoch": 0.02, + "learning_rate": 2.5178053975364968e-05, + "loss": 3.9164, + "step": 1516032 + }, + { + "epoch": 0.02, + "learning_rate": 2.5169668027854448e-05, + "loss": 3.9353, + "step": 1516544 + }, + { + "epoch": 0.02, + "learning_rate": 2.5161282080343928e-05, + "loss": 3.937, + "step": 1517056 + }, + { + "epoch": 0.02, + "learning_rate": 2.5152896132833408e-05, + "loss": 3.9245, + "step": 1517568 + }, + { + "epoch": 0.02, + "learning_rate": 2.5144510185322888e-05, + "loss": 3.9232, + "step": 1518080 + }, + { + "epoch": 0.02, + "learning_rate": 2.513612423781237e-05, + "loss": 3.926, + "step": 1518592 + }, + { + "epoch": 0.02, + "learning_rate": 2.512775466910558e-05, + "loss": 3.926, + "step": 1519104 + }, + { + "epoch": 0.02, + "learning_rate": 2.511936872159506e-05, + "loss": 3.9427, + "step": 1519616 + }, + { + "epoch": 0.02, + "learning_rate": 2.511098277408454e-05, + "loss": 3.9235, + "step": 1520128 + }, + { + "epoch": 0.02, + "learning_rate": 2.510259682657402e-05, + "loss": 3.9251, + "step": 1520640 + }, + { + "epoch": 0.02, + "learning_rate": 2.50942108790635e-05, + "loss": 3.9222, + "step": 1521152 + }, + { + "epoch": 0.02, + "learning_rate": 2.508582493155298e-05, + "loss": 3.9257, + "step": 1521664 + }, + { + "epoch": 0.02, + "learning_rate": 2.5077438984042463e-05, + "loss": 3.917, + "step": 1522176 + }, + { + "epoch": 0.02, + "learning_rate": 2.5069053036531943e-05, + "loss": 3.9228, + "step": 1522688 + }, + { + "epoch": 0.02, + "learning_rate": 2.5060683467825152e-05, + "loss": 3.9292, + "step": 1523200 + }, + { + "epoch": 0.02, + "learning_rate": 2.505231389911836e-05, + "loss": 3.9203, + "step": 1523712 + }, + { + "epoch": 0.02, + "learning_rate": 2.504392795160784e-05, + "loss": 3.9286, + "step": 1524224 + }, + { + "epoch": 0.02, + "learning_rate": 2.5035542004097325e-05, + "loss": 3.9302, + "step": 1524736 + }, + { + "epoch": 0.02, + "learning_rate": 2.5027156056586805e-05, + "loss": 3.9228, + "step": 1525248 + }, + { + "epoch": 0.02, + "learning_rate": 2.5018770109076285e-05, + "loss": 3.9266, + "step": 1525760 + }, + { + "epoch": 0.02, + "learning_rate": 2.5010384161565765e-05, + "loss": 3.9166, + "step": 1526272 + }, + { + "epoch": 0.03, + "eval_loss": 4.000504493713379, + "eval_runtime": 305.1629, + "eval_samples_per_second": 1250.45, + "eval_steps_per_second": 39.077, + "step": 1526387 + }, + { + "epoch": 1.0, + "learning_rate": 2.5002014592858974e-05, + "loss": 3.9213, + "step": 1526784 + }, + { + "epoch": 1.0, + "learning_rate": 2.4993628645348454e-05, + "loss": 3.9129, + "step": 1527296 + }, + { + "epoch": 1.0, + "learning_rate": 2.4985242697837934e-05, + "loss": 3.9333, + "step": 1527808 + }, + { + "epoch": 1.0, + "learning_rate": 2.4976856750327414e-05, + "loss": 3.9224, + "step": 1528320 + }, + { + "epoch": 1.0, + "learning_rate": 2.4968470802816893e-05, + "loss": 3.937, + "step": 1528832 + }, + { + "epoch": 1.0, + "learning_rate": 2.4960084855306373e-05, + "loss": 3.917, + "step": 1529344 + }, + { + "epoch": 1.0, + "learning_rate": 2.4951698907795853e-05, + "loss": 3.9246, + "step": 1529856 + }, + { + "epoch": 1.0, + "learning_rate": 2.4943312960285333e-05, + "loss": 3.9096, + "step": 1530368 + }, + { + "epoch": 1.0, + "learning_rate": 2.4934943391578542e-05, + "loss": 3.9271, + "step": 1530880 + }, + { + "epoch": 1.0, + "learning_rate": 2.4926557444068026e-05, + "loss": 3.9123, + "step": 1531392 + }, + { + "epoch": 1.0, + "learning_rate": 2.4918171496557506e-05, + "loss": 3.9408, + "step": 1531904 + }, + { + "epoch": 1.0, + "learning_rate": 2.4909785549046986e-05, + "loss": 3.9327, + "step": 1532416 + }, + { + "epoch": 1.0, + "learning_rate": 2.4901415980340195e-05, + "loss": 3.9073, + "step": 1532928 + }, + { + "epoch": 1.0, + "learning_rate": 2.4893030032829675e-05, + "loss": 3.9194, + "step": 1533440 + }, + { + "epoch": 1.0, + "learning_rate": 2.4884644085319155e-05, + "loss": 3.9258, + "step": 1533952 + }, + { + "epoch": 1.0, + "learning_rate": 2.4876258137808635e-05, + "loss": 3.9125, + "step": 1534464 + }, + { + "epoch": 1.0, + "learning_rate": 2.4867872190298115e-05, + "loss": 3.9217, + "step": 1534976 + }, + { + "epoch": 1.0, + "learning_rate": 2.4859502621591327e-05, + "loss": 3.922, + "step": 1535488 + }, + { + "epoch": 1.0, + "learning_rate": 2.4851116674080807e-05, + "loss": 3.9166, + "step": 1536000 + }, + { + "epoch": 1.0, + "learning_rate": 2.4842730726570287e-05, + "loss": 3.9429, + "step": 1536512 + }, + { + "epoch": 1.0, + "learning_rate": 2.4834344779059764e-05, + "loss": 3.9212, + "step": 1537024 + }, + { + "epoch": 1.0, + "learning_rate": 2.4825958831549247e-05, + "loss": 3.9227, + "step": 1537536 + }, + { + "epoch": 1.0, + "learning_rate": 2.4817572884038727e-05, + "loss": 3.9233, + "step": 1538048 + }, + { + "epoch": 1.0, + "learning_rate": 2.4809186936528207e-05, + "loss": 3.932, + "step": 1538560 + }, + { + "epoch": 1.0, + "learning_rate": 2.4800817367821416e-05, + "loss": 3.9139, + "step": 1539072 + }, + { + "epoch": 1.0, + "learning_rate": 2.4792431420310896e-05, + "loss": 3.9257, + "step": 1539584 + }, + { + "epoch": 1.0, + "learning_rate": 2.4784045472800376e-05, + "loss": 3.9114, + "step": 1540096 + }, + { + "epoch": 1.0, + "learning_rate": 2.4775659525289856e-05, + "loss": 3.9194, + "step": 1540608 + }, + { + "epoch": 1.0, + "learning_rate": 2.476727357777934e-05, + "loss": 3.9178, + "step": 1541120 + }, + { + "epoch": 1.0, + "learning_rate": 2.475888763026882e-05, + "loss": 3.9216, + "step": 1541632 + }, + { + "epoch": 1.01, + "learning_rate": 2.4750501682758296e-05, + "loss": 3.9178, + "step": 1542144 + }, + { + "epoch": 1.01, + "learning_rate": 2.4742115735247776e-05, + "loss": 3.9291, + "step": 1542656 + }, + { + "epoch": 1.01, + "learning_rate": 2.4733746166540988e-05, + "loss": 3.9261, + "step": 1543168 + }, + { + "epoch": 1.01, + "learning_rate": 2.4725360219030468e-05, + "loss": 3.9343, + "step": 1543680 + }, + { + "epoch": 1.01, + "learning_rate": 2.471699065032368e-05, + "loss": 3.9193, + "step": 1544192 + }, + { + "epoch": 1.01, + "learning_rate": 2.470860470281316e-05, + "loss": 3.9261, + "step": 1544704 + }, + { + "epoch": 1.01, + "learning_rate": 2.470021875530264e-05, + "loss": 3.9132, + "step": 1545216 + }, + { + "epoch": 1.01, + "learning_rate": 2.469183280779212e-05, + "loss": 3.9239, + "step": 1545728 + }, + { + "epoch": 1.01, + "learning_rate": 2.4683446860281597e-05, + "loss": 3.9096, + "step": 1546240 + }, + { + "epoch": 1.01, + "learning_rate": 2.467507729157481e-05, + "loss": 3.9198, + "step": 1546752 + }, + { + "epoch": 1.01, + "learning_rate": 2.466669134406429e-05, + "loss": 3.9151, + "step": 1547264 + }, + { + "epoch": 1.01, + "learning_rate": 2.465830539655377e-05, + "loss": 3.9293, + "step": 1547776 + }, + { + "epoch": 1.01, + "learning_rate": 2.464991944904325e-05, + "loss": 3.9149, + "step": 1548288 + }, + { + "epoch": 1.01, + "learning_rate": 2.464153350153273e-05, + "loss": 3.9171, + "step": 1548800 + }, + { + "epoch": 1.01, + "learning_rate": 2.463314755402221e-05, + "loss": 3.9308, + "step": 1549312 + }, + { + "epoch": 1.01, + "learning_rate": 2.462476160651169e-05, + "loss": 3.9247, + "step": 1549824 + }, + { + "epoch": 1.01, + "learning_rate": 2.461637565900117e-05, + "loss": 3.9269, + "step": 1550336 + }, + { + "epoch": 1.01, + "learning_rate": 2.460798971149065e-05, + "loss": 3.9104, + "step": 1550848 + }, + { + "epoch": 1.01, + "learning_rate": 2.459960376398013e-05, + "loss": 3.9074, + "step": 1551360 + }, + { + "epoch": 1.01, + "learning_rate": 2.459121781646961e-05, + "loss": 3.9278, + "step": 1551872 + }, + { + "epoch": 1.01, + "learning_rate": 2.458283186895909e-05, + "loss": 3.9215, + "step": 1552384 + }, + { + "epoch": 1.01, + "learning_rate": 2.4574462300252298e-05, + "loss": 3.914, + "step": 1552896 + }, + { + "epoch": 1.01, + "learning_rate": 2.456609273154551e-05, + "loss": 3.914, + "step": 1553408 + }, + { + "epoch": 1.01, + "learning_rate": 2.4557706784034994e-05, + "loss": 3.9221, + "step": 1553920 + }, + { + "epoch": 1.01, + "learning_rate": 2.4549320836524474e-05, + "loss": 3.9043, + "step": 1554432 + }, + { + "epoch": 1.01, + "learning_rate": 2.4540951267817683e-05, + "loss": 3.9264, + "step": 1554944 + }, + { + "epoch": 1.01, + "learning_rate": 2.4532565320307163e-05, + "loss": 3.9054, + "step": 1555456 + }, + { + "epoch": 1.01, + "learning_rate": 2.4524179372796643e-05, + "loss": 3.9176, + "step": 1555968 + }, + { + "epoch": 1.01, + "learning_rate": 2.4515793425286123e-05, + "loss": 3.9255, + "step": 1556480 + }, + { + "epoch": 1.01, + "learning_rate": 2.4507407477775603e-05, + "loss": 3.9108, + "step": 1556992 + }, + { + "epoch": 1.01, + "learning_rate": 2.4499021530265083e-05, + "loss": 3.9204, + "step": 1557504 + }, + { + "epoch": 1.01, + "learning_rate": 2.4490635582754563e-05, + "loss": 3.9179, + "step": 1558016 + }, + { + "epoch": 1.01, + "learning_rate": 2.4482249635244043e-05, + "loss": 3.9101, + "step": 1558528 + }, + { + "epoch": 1.01, + "learning_rate": 2.4473880066537252e-05, + "loss": 3.9123, + "step": 1559040 + }, + { + "epoch": 1.01, + "learning_rate": 2.446549411902673e-05, + "loss": 3.9201, + "step": 1559552 + }, + { + "epoch": 1.01, + "learning_rate": 2.445710817151621e-05, + "loss": 3.9119, + "step": 1560064 + }, + { + "epoch": 1.01, + "learning_rate": 2.4448722224005695e-05, + "loss": 3.9155, + "step": 1560576 + }, + { + "epoch": 1.01, + "learning_rate": 2.4440336276495175e-05, + "loss": 3.9059, + "step": 1561088 + }, + { + "epoch": 1.01, + "learning_rate": 2.4431950328984655e-05, + "loss": 3.9066, + "step": 1561600 + }, + { + "epoch": 1.01, + "learning_rate": 2.442356438147413e-05, + "loss": 3.9179, + "step": 1562112 + }, + { + "epoch": 1.01, + "learning_rate": 2.441517843396361e-05, + "loss": 3.9274, + "step": 1562624 + }, + { + "epoch": 1.01, + "learning_rate": 2.4406825244060556e-05, + "loss": 3.912, + "step": 1563136 + }, + { + "epoch": 1.01, + "learning_rate": 2.4398439296550036e-05, + "loss": 3.928, + "step": 1563648 + }, + { + "epoch": 1.01, + "learning_rate": 2.4390053349039516e-05, + "loss": 3.9259, + "step": 1564160 + }, + { + "epoch": 1.01, + "learning_rate": 2.4381667401528996e-05, + "loss": 3.9177, + "step": 1564672 + }, + { + "epoch": 1.01, + "learning_rate": 2.4373281454018476e-05, + "loss": 3.9185, + "step": 1565184 + }, + { + "epoch": 1.01, + "learning_rate": 2.4364895506507953e-05, + "loss": 3.9245, + "step": 1565696 + }, + { + "epoch": 1.01, + "learning_rate": 2.4356509558997433e-05, + "loss": 3.9154, + "step": 1566208 + }, + { + "epoch": 1.01, + "learning_rate": 2.4348123611486913e-05, + "loss": 3.9159, + "step": 1566720 + }, + { + "epoch": 1.01, + "learning_rate": 2.4339737663976396e-05, + "loss": 3.922, + "step": 1567232 + }, + { + "epoch": 1.01, + "learning_rate": 2.4331368095269605e-05, + "loss": 3.9209, + "step": 1567744 + }, + { + "epoch": 1.01, + "learning_rate": 2.4322982147759085e-05, + "loss": 3.9253, + "step": 1568256 + }, + { + "epoch": 1.01, + "learning_rate": 2.4314596200248565e-05, + "loss": 3.9218, + "step": 1568768 + }, + { + "epoch": 1.01, + "learning_rate": 2.4306210252738045e-05, + "loss": 3.9024, + "step": 1569280 + }, + { + "epoch": 1.01, + "learning_rate": 2.4297824305227525e-05, + "loss": 3.9039, + "step": 1569792 + }, + { + "epoch": 1.01, + "learning_rate": 2.4289438357717005e-05, + "loss": 3.9171, + "step": 1570304 + }, + { + "epoch": 1.01, + "learning_rate": 2.4281052410206488e-05, + "loss": 3.9202, + "step": 1570816 + }, + { + "epoch": 1.01, + "learning_rate": 2.4272666462695965e-05, + "loss": 3.9144, + "step": 1571328 + }, + { + "epoch": 1.01, + "learning_rate": 2.4264296893989177e-05, + "loss": 3.9181, + "step": 1571840 + }, + { + "epoch": 1.02, + "learning_rate": 2.4255910946478657e-05, + "loss": 3.9153, + "step": 1572352 + }, + { + "epoch": 1.02, + "learning_rate": 2.4247524998968134e-05, + "loss": 3.9089, + "step": 1572864 + }, + { + "epoch": 1.02, + "learning_rate": 2.4239139051457617e-05, + "loss": 3.9168, + "step": 1573376 + }, + { + "epoch": 1.02, + "learning_rate": 2.423076948275083e-05, + "loss": 3.9177, + "step": 1573888 + }, + { + "epoch": 1.02, + "learning_rate": 2.422238353524031e-05, + "loss": 3.926, + "step": 1574400 + }, + { + "epoch": 1.02, + "learning_rate": 2.4213997587729786e-05, + "loss": 3.9228, + "step": 1574912 + }, + { + "epoch": 1.02, + "learning_rate": 2.4205628019023e-05, + "loss": 3.9203, + "step": 1575424 + }, + { + "epoch": 1.02, + "learning_rate": 2.419724207151248e-05, + "loss": 3.9084, + "step": 1575936 + }, + { + "epoch": 1.02, + "learning_rate": 2.418885612400196e-05, + "loss": 3.9209, + "step": 1576448 + }, + { + "epoch": 1.02, + "learning_rate": 2.418047017649144e-05, + "loss": 3.9193, + "step": 1576960 + }, + { + "epoch": 1.02, + "learning_rate": 2.417210060778465e-05, + "loss": 3.9266, + "step": 1577472 + }, + { + "epoch": 1.02, + "learning_rate": 2.416371466027413e-05, + "loss": 3.9158, + "step": 1577984 + }, + { + "epoch": 1.02, + "learning_rate": 2.4155328712763608e-05, + "loss": 3.9122, + "step": 1578496 + }, + { + "epoch": 1.02, + "learning_rate": 2.4146942765253088e-05, + "loss": 3.9206, + "step": 1579008 + }, + { + "epoch": 1.02, + "learning_rate": 2.4138556817742567e-05, + "loss": 3.9216, + "step": 1579520 + }, + { + "epoch": 1.02, + "learning_rate": 2.413017087023205e-05, + "loss": 3.9127, + "step": 1580032 + }, + { + "epoch": 1.02, + "learning_rate": 2.412180130152526e-05, + "loss": 3.9134, + "step": 1580544 + }, + { + "epoch": 1.02, + "learning_rate": 2.411341535401474e-05, + "loss": 3.9119, + "step": 1581056 + }, + { + "epoch": 1.02, + "learning_rate": 2.4105045785307952e-05, + "loss": 3.9077, + "step": 1581568 + }, + { + "epoch": 1.02, + "learning_rate": 2.4096659837797432e-05, + "loss": 3.9064, + "step": 1582080 + }, + { + "epoch": 1.02, + "learning_rate": 2.4088273890286912e-05, + "loss": 3.9153, + "step": 1582592 + }, + { + "epoch": 1.02, + "learning_rate": 2.4079887942776392e-05, + "loss": 3.9134, + "step": 1583104 + }, + { + "epoch": 1.02, + "learning_rate": 2.4071501995265872e-05, + "loss": 3.9152, + "step": 1583616 + }, + { + "epoch": 1.02, + "learning_rate": 2.4063116047755352e-05, + "loss": 3.9097, + "step": 1584128 + }, + { + "epoch": 1.02, + "learning_rate": 2.4054730100244832e-05, + "loss": 3.9145, + "step": 1584640 + }, + { + "epoch": 1.02, + "learning_rate": 2.4046344152734312e-05, + "loss": 3.9308, + "step": 1585152 + }, + { + "epoch": 1.02, + "learning_rate": 2.403795820522379e-05, + "loss": 3.9296, + "step": 1585664 + }, + { + "epoch": 1.02, + "learning_rate": 2.4029588636517004e-05, + "loss": 3.9209, + "step": 1586176 + }, + { + "epoch": 1.02, + "learning_rate": 2.4021202689006484e-05, + "loss": 3.9185, + "step": 1586688 + }, + { + "epoch": 1.02, + "learning_rate": 2.4012816741495964e-05, + "loss": 3.9143, + "step": 1587200 + }, + { + "epoch": 1.02, + "learning_rate": 2.400443079398544e-05, + "loss": 3.9141, + "step": 1587712 + }, + { + "epoch": 1.02, + "learning_rate": 2.399604484647492e-05, + "loss": 3.9089, + "step": 1588224 + }, + { + "epoch": 1.02, + "learning_rate": 2.3987675277768133e-05, + "loss": 3.9155, + "step": 1588736 + }, + { + "epoch": 1.02, + "learning_rate": 2.3979289330257613e-05, + "loss": 3.915, + "step": 1589248 + }, + { + "epoch": 1.02, + "learning_rate": 2.3970903382747093e-05, + "loss": 3.9222, + "step": 1589760 + }, + { + "epoch": 1.02, + "learning_rate": 2.3962517435236573e-05, + "loss": 3.914, + "step": 1590272 + }, + { + "epoch": 1.02, + "learning_rate": 2.3954147866529786e-05, + "loss": 3.92, + "step": 1590784 + }, + { + "epoch": 1.02, + "learning_rate": 2.3945761919019262e-05, + "loss": 3.9117, + "step": 1591296 + }, + { + "epoch": 1.02, + "learning_rate": 2.3937375971508742e-05, + "loss": 3.9106, + "step": 1591808 + }, + { + "epoch": 1.02, + "learning_rate": 2.3928990023998226e-05, + "loss": 3.9096, + "step": 1592320 + }, + { + "epoch": 1.02, + "learning_rate": 2.3920604076487706e-05, + "loss": 3.9274, + "step": 1592832 + }, + { + "epoch": 1.02, + "learning_rate": 2.3912234507780915e-05, + "loss": 3.9287, + "step": 1593344 + }, + { + "epoch": 1.02, + "learning_rate": 2.3903848560270395e-05, + "loss": 3.9236, + "step": 1593856 + }, + { + "epoch": 1.02, + "learning_rate": 2.3895462612759875e-05, + "loss": 3.911, + "step": 1594368 + }, + { + "epoch": 1.02, + "learning_rate": 2.3887076665249355e-05, + "loss": 3.9213, + "step": 1594880 + }, + { + "epoch": 1.02, + "learning_rate": 2.3878690717738835e-05, + "loss": 3.9177, + "step": 1595392 + }, + { + "epoch": 1.02, + "learning_rate": 2.3870321149032047e-05, + "loss": 3.9325, + "step": 1595904 + }, + { + "epoch": 1.02, + "learning_rate": 2.3861935201521527e-05, + "loss": 3.9152, + "step": 1596416 + }, + { + "epoch": 1.02, + "learning_rate": 2.3853549254011007e-05, + "loss": 3.9153, + "step": 1596928 + }, + { + "epoch": 1.02, + "learning_rate": 2.3845163306500487e-05, + "loss": 3.9177, + "step": 1597440 + }, + { + "epoch": 1.02, + "learning_rate": 2.3836777358989967e-05, + "loss": 3.9222, + "step": 1597952 + }, + { + "epoch": 1.02, + "learning_rate": 2.3828391411479443e-05, + "loss": 3.9088, + "step": 1598464 + }, + { + "epoch": 1.02, + "learning_rate": 2.3820005463968927e-05, + "loss": 3.9134, + "step": 1598976 + }, + { + "epoch": 1.02, + "learning_rate": 2.3811619516458407e-05, + "loss": 3.9215, + "step": 1599488 + }, + { + "epoch": 1.02, + "learning_rate": 2.380324994775162e-05, + "loss": 3.9155, + "step": 1600000 + }, + { + "epoch": 1.02, + "learning_rate": 2.3794864000241096e-05, + "loss": 3.9222, + "step": 1600512 + }, + { + "epoch": 1.02, + "learning_rate": 2.3786478052730576e-05, + "loss": 3.9235, + "step": 1601024 + }, + { + "epoch": 1.02, + "learning_rate": 2.3778092105220056e-05, + "loss": 3.9146, + "step": 1601536 + }, + { + "epoch": 1.02, + "learning_rate": 2.3769722536513268e-05, + "loss": 3.9167, + "step": 1602048 + }, + { + "epoch": 1.02, + "learning_rate": 2.3761336589002748e-05, + "loss": 3.9154, + "step": 1602560 + }, + { + "epoch": 1.03, + "eval_loss": 3.9974606037139893, + "eval_runtime": 305.678, + "eval_samples_per_second": 1248.343, + "eval_steps_per_second": 39.012, + "step": 1602707 + }, + { + "epoch": 0.0, + "learning_rate": 2.3752950641492228e-05, + "loss": 3.9069, + "step": 1603072 + }, + { + "epoch": 0.0, + "learning_rate": 2.3744564693981708e-05, + "loss": 3.9064, + "step": 1603584 + }, + { + "epoch": 0.0, + "learning_rate": 2.3736178746471188e-05, + "loss": 3.926, + "step": 1604096 + }, + { + "epoch": 0.0, + "learning_rate": 2.3727792798960668e-05, + "loss": 3.9161, + "step": 1604608 + }, + { + "epoch": 0.0, + "learning_rate": 2.3719406851450148e-05, + "loss": 3.9258, + "step": 1605120 + }, + { + "epoch": 0.0, + "learning_rate": 2.3711020903939628e-05, + "loss": 3.9155, + "step": 1605632 + }, + { + "epoch": 0.0, + "learning_rate": 2.3702634956429108e-05, + "loss": 3.9149, + "step": 1606144 + }, + { + "epoch": 0.0, + "learning_rate": 2.3694249008918588e-05, + "loss": 3.9036, + "step": 1606656 + }, + { + "epoch": 0.0, + "learning_rate": 2.3685863061408068e-05, + "loss": 3.9191, + "step": 1607168 + }, + { + "epoch": 0.0, + "learning_rate": 2.3677477113897548e-05, + "loss": 3.9106, + "step": 1607680 + }, + { + "epoch": 0.0, + "learning_rate": 2.3669107545190757e-05, + "loss": 3.9255, + "step": 1608192 + }, + { + "epoch": 0.0, + "learning_rate": 2.3660721597680237e-05, + "loss": 3.9263, + "step": 1608704 + }, + { + "epoch": 0.0, + "learning_rate": 2.365233565016972e-05, + "loss": 3.9017, + "step": 1609216 + }, + { + "epoch": 0.0, + "learning_rate": 2.36439497026592e-05, + "loss": 3.9107, + "step": 1609728 + }, + { + "epoch": 0.0, + "learning_rate": 2.363556375514868e-05, + "loss": 3.9211, + "step": 1610240 + }, + { + "epoch": 0.0, + "learning_rate": 2.3627177807638157e-05, + "loss": 3.9036, + "step": 1610752 + }, + { + "epoch": 0.0, + "learning_rate": 2.3618791860127636e-05, + "loss": 3.9154, + "step": 1611264 + }, + { + "epoch": 0.0, + "learning_rate": 2.3610405912617116e-05, + "loss": 3.915, + "step": 1611776 + }, + { + "epoch": 0.0, + "learning_rate": 2.3602019965106596e-05, + "loss": 3.9123, + "step": 1612288 + }, + { + "epoch": 0.0, + "learning_rate": 2.3593634017596076e-05, + "loss": 3.9302, + "step": 1612800 + }, + { + "epoch": 0.0, + "learning_rate": 2.358526444888929e-05, + "loss": 3.9168, + "step": 1613312 + }, + { + "epoch": 0.0, + "learning_rate": 2.357687850137877e-05, + "loss": 3.9168, + "step": 1613824 + }, + { + "epoch": 0.0, + "learning_rate": 2.356849255386825e-05, + "loss": 3.9199, + "step": 1614336 + }, + { + "epoch": 0.0, + "learning_rate": 2.356010660635773e-05, + "loss": 3.9206, + "step": 1614848 + }, + { + "epoch": 0.0, + "learning_rate": 2.355172065884721e-05, + "loss": 3.9084, + "step": 1615360 + }, + { + "epoch": 0.0, + "learning_rate": 2.354335109014042e-05, + "loss": 3.9174, + "step": 1615872 + }, + { + "epoch": 0.0, + "learning_rate": 2.35349651426299e-05, + "loss": 3.9074, + "step": 1616384 + }, + { + "epoch": 0.0, + "learning_rate": 2.352657919511938e-05, + "loss": 3.9121, + "step": 1616896 + }, + { + "epoch": 0.0, + "learning_rate": 2.351819324760886e-05, + "loss": 3.9098, + "step": 1617408 + }, + { + "epoch": 0.0, + "learning_rate": 2.3509807300098338e-05, + "loss": 3.9161, + "step": 1617920 + }, + { + "epoch": 0.01, + "learning_rate": 2.3501421352587818e-05, + "loss": 3.9112, + "step": 1618432 + }, + { + "epoch": 0.01, + "learning_rate": 2.3493035405077297e-05, + "loss": 3.9199, + "step": 1618944 + }, + { + "epoch": 0.01, + "learning_rate": 2.348464945756678e-05, + "loss": 3.9197, + "step": 1619456 + }, + { + "epoch": 0.01, + "learning_rate": 2.347626351005626e-05, + "loss": 3.9231, + "step": 1619968 + }, + { + "epoch": 0.01, + "learning_rate": 2.346789394134947e-05, + "loss": 3.9145, + "step": 1620480 + }, + { + "epoch": 0.01, + "learning_rate": 2.345950799383895e-05, + "loss": 3.9187, + "step": 1620992 + }, + { + "epoch": 0.01, + "learning_rate": 2.345113842513216e-05, + "loss": 3.9103, + "step": 1621504 + }, + { + "epoch": 0.01, + "learning_rate": 2.3442752477621642e-05, + "loss": 3.9133, + "step": 1622016 + }, + { + "epoch": 0.01, + "learning_rate": 2.3434366530111122e-05, + "loss": 3.9023, + "step": 1622528 + }, + { + "epoch": 0.01, + "learning_rate": 2.3425980582600602e-05, + "loss": 3.9099, + "step": 1623040 + }, + { + "epoch": 0.01, + "learning_rate": 2.3417594635090082e-05, + "loss": 3.9103, + "step": 1623552 + }, + { + "epoch": 0.01, + "learning_rate": 2.3409208687579562e-05, + "loss": 3.9213, + "step": 1624064 + }, + { + "epoch": 0.01, + "learning_rate": 2.3400822740069042e-05, + "loss": 3.9048, + "step": 1624576 + }, + { + "epoch": 0.01, + "learning_rate": 2.339243679255852e-05, + "loss": 3.912, + "step": 1625088 + }, + { + "epoch": 0.01, + "learning_rate": 2.338406722385173e-05, + "loss": 3.9254, + "step": 1625600 + }, + { + "epoch": 0.01, + "learning_rate": 2.3375681276341214e-05, + "loss": 3.9168, + "step": 1626112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3367295328830694e-05, + "loss": 3.9186, + "step": 1626624 + }, + { + "epoch": 0.01, + "learning_rate": 2.3358925760123903e-05, + "loss": 3.9058, + "step": 1627136 + }, + { + "epoch": 0.01, + "learning_rate": 2.3350539812613383e-05, + "loss": 3.895, + "step": 1627648 + }, + { + "epoch": 0.01, + "learning_rate": 2.3342153865102863e-05, + "loss": 3.9238, + "step": 1628160 + }, + { + "epoch": 0.01, + "learning_rate": 2.3333767917592343e-05, + "loss": 3.9116, + "step": 1628672 + }, + { + "epoch": 0.01, + "learning_rate": 2.3325381970081823e-05, + "loss": 3.9057, + "step": 1629184 + }, + { + "epoch": 0.01, + "learning_rate": 2.3316996022571303e-05, + "loss": 3.9103, + "step": 1629696 + }, + { + "epoch": 0.01, + "learning_rate": 2.3308610075060783e-05, + "loss": 3.9172, + "step": 1630208 + }, + { + "epoch": 0.01, + "learning_rate": 2.3300224127550263e-05, + "loss": 3.8924, + "step": 1630720 + }, + { + "epoch": 0.01, + "learning_rate": 2.3291838180039743e-05, + "loss": 3.9196, + "step": 1631232 + }, + { + "epoch": 0.01, + "learning_rate": 2.3283452232529223e-05, + "loss": 3.8966, + "step": 1631744 + }, + { + "epoch": 0.01, + "learning_rate": 2.3275082663822436e-05, + "loss": 3.9112, + "step": 1632256 + }, + { + "epoch": 0.01, + "learning_rate": 2.3266696716311916e-05, + "loss": 3.9149, + "step": 1632768 + }, + { + "epoch": 0.01, + "learning_rate": 2.3258310768801395e-05, + "loss": 3.9119, + "step": 1633280 + }, + { + "epoch": 0.01, + "learning_rate": 2.3249924821290875e-05, + "loss": 3.9081, + "step": 1633792 + }, + { + "epoch": 0.01, + "learning_rate": 2.3241555252584085e-05, + "loss": 3.9134, + "step": 1634304 + }, + { + "epoch": 0.01, + "learning_rate": 2.3233169305073564e-05, + "loss": 3.8982, + "step": 1634816 + }, + { + "epoch": 0.01, + "learning_rate": 2.3224783357563044e-05, + "loss": 3.9061, + "step": 1635328 + }, + { + "epoch": 0.01, + "learning_rate": 2.3216397410052524e-05, + "loss": 3.9119, + "step": 1635840 + }, + { + "epoch": 0.01, + "learning_rate": 2.3208011462542004e-05, + "loss": 3.9089, + "step": 1636352 + }, + { + "epoch": 0.01, + "learning_rate": 2.3199625515031484e-05, + "loss": 3.9083, + "step": 1636864 + }, + { + "epoch": 0.01, + "learning_rate": 2.3191239567520964e-05, + "loss": 3.8989, + "step": 1637376 + }, + { + "epoch": 0.01, + "learning_rate": 2.3182853620010444e-05, + "loss": 3.9007, + "step": 1637888 + }, + { + "epoch": 0.01, + "learning_rate": 2.3174467672499924e-05, + "loss": 3.9084, + "step": 1638400 + }, + { + "epoch": 0.01, + "learning_rate": 2.316611448259687e-05, + "loss": 3.9186, + "step": 1638912 + }, + { + "epoch": 0.01, + "learning_rate": 2.315772853508635e-05, + "loss": 3.905, + "step": 1639424 + }, + { + "epoch": 0.01, + "learning_rate": 2.3149342587575826e-05, + "loss": 3.923, + "step": 1639936 + }, + { + "epoch": 0.01, + "learning_rate": 2.3140956640065306e-05, + "loss": 3.9202, + "step": 1640448 + }, + { + "epoch": 0.01, + "learning_rate": 2.3132570692554786e-05, + "loss": 3.9127, + "step": 1640960 + }, + { + "epoch": 0.01, + "learning_rate": 2.3124201123847998e-05, + "loss": 3.9104, + "step": 1641472 + }, + { + "epoch": 0.01, + "learning_rate": 2.3115815176337478e-05, + "loss": 3.9173, + "step": 1641984 + }, + { + "epoch": 0.01, + "learning_rate": 2.3107429228826958e-05, + "loss": 3.9086, + "step": 1642496 + }, + { + "epoch": 0.01, + "learning_rate": 2.3099043281316438e-05, + "loss": 3.909, + "step": 1643008 + }, + { + "epoch": 0.01, + "learning_rate": 2.3090657333805918e-05, + "loss": 3.9166, + "step": 1643520 + }, + { + "epoch": 0.01, + "learning_rate": 2.3082271386295398e-05, + "loss": 3.9121, + "step": 1644032 + }, + { + "epoch": 0.01, + "learning_rate": 2.3073885438784878e-05, + "loss": 3.9204, + "step": 1644544 + }, + { + "epoch": 0.01, + "learning_rate": 2.306551587007809e-05, + "loss": 3.9164, + "step": 1645056 + }, + { + "epoch": 0.01, + "learning_rate": 2.305712992256757e-05, + "loss": 3.8957, + "step": 1645568 + }, + { + "epoch": 0.01, + "learning_rate": 2.304874397505705e-05, + "loss": 3.8986, + "step": 1646080 + }, + { + "epoch": 0.01, + "learning_rate": 2.304035802754653e-05, + "loss": 3.9043, + "step": 1646592 + }, + { + "epoch": 0.01, + "learning_rate": 2.3031972080036007e-05, + "loss": 3.9144, + "step": 1647104 + }, + { + "epoch": 0.01, + "learning_rate": 2.302360251132922e-05, + "loss": 3.9096, + "step": 1647616 + }, + { + "epoch": 0.01, + "learning_rate": 2.30152165638187e-05, + "loss": 3.9112, + "step": 1648128 + }, + { + "epoch": 0.02, + "learning_rate": 2.300683061630818e-05, + "loss": 3.9074, + "step": 1648640 + }, + { + "epoch": 0.02, + "learning_rate": 2.299844466879766e-05, + "loss": 3.9035, + "step": 1649152 + }, + { + "epoch": 0.02, + "learning_rate": 2.299005872128714e-05, + "loss": 3.9112, + "step": 1649664 + }, + { + "epoch": 0.02, + "learning_rate": 2.298168915258035e-05, + "loss": 3.9064, + "step": 1650176 + }, + { + "epoch": 0.02, + "learning_rate": 2.2973303205069828e-05, + "loss": 3.92, + "step": 1650688 + }, + { + "epoch": 0.02, + "learning_rate": 2.2964917257559308e-05, + "loss": 3.9192, + "step": 1651200 + }, + { + "epoch": 0.02, + "learning_rate": 2.295653131004879e-05, + "loss": 3.9153, + "step": 1651712 + }, + { + "epoch": 0.02, + "learning_rate": 2.294814536253827e-05, + "loss": 3.9004, + "step": 1652224 + }, + { + "epoch": 0.02, + "learning_rate": 2.293977579383148e-05, + "loss": 3.9115, + "step": 1652736 + }, + { + "epoch": 0.02, + "learning_rate": 2.293138984632096e-05, + "loss": 3.9117, + "step": 1653248 + }, + { + "epoch": 0.02, + "learning_rate": 2.292300389881044e-05, + "loss": 3.9222, + "step": 1653760 + }, + { + "epoch": 0.02, + "learning_rate": 2.291461795129992e-05, + "loss": 3.9082, + "step": 1654272 + }, + { + "epoch": 0.02, + "learning_rate": 2.29062320037894e-05, + "loss": 3.9028, + "step": 1654784 + }, + { + "epoch": 0.02, + "learning_rate": 2.2897846056278884e-05, + "loss": 3.9193, + "step": 1655296 + }, + { + "epoch": 0.02, + "learning_rate": 2.288946010876836e-05, + "loss": 3.9107, + "step": 1655808 + }, + { + "epoch": 0.02, + "learning_rate": 2.2881090540061573e-05, + "loss": 3.9058, + "step": 1656320 + }, + { + "epoch": 0.02, + "learning_rate": 2.2872720971354782e-05, + "loss": 3.9073, + "step": 1656832 + }, + { + "epoch": 0.02, + "learning_rate": 2.2864335023844262e-05, + "loss": 3.907, + "step": 1657344 + }, + { + "epoch": 0.02, + "learning_rate": 2.2855949076333745e-05, + "loss": 3.9001, + "step": 1657856 + }, + { + "epoch": 0.02, + "learning_rate": 2.2847563128823225e-05, + "loss": 3.8952, + "step": 1658368 + }, + { + "epoch": 0.02, + "learning_rate": 2.2839177181312705e-05, + "loss": 3.9126, + "step": 1658880 + }, + { + "epoch": 0.02, + "learning_rate": 2.2830823991409647e-05, + "loss": 3.9107, + "step": 1659392 + }, + { + "epoch": 0.02, + "learning_rate": 2.2822438043899123e-05, + "loss": 3.9066, + "step": 1659904 + }, + { + "epoch": 0.02, + "learning_rate": 2.2814052096388607e-05, + "loss": 3.9027, + "step": 1660416 + }, + { + "epoch": 0.02, + "learning_rate": 2.2805666148878086e-05, + "loss": 3.9037, + "step": 1660928 + }, + { + "epoch": 0.02, + "learning_rate": 2.2797280201367566e-05, + "loss": 3.9257, + "step": 1661440 + }, + { + "epoch": 0.02, + "learning_rate": 2.2788894253857046e-05, + "loss": 3.9223, + "step": 1661952 + }, + { + "epoch": 0.02, + "learning_rate": 2.2780508306346526e-05, + "loss": 3.9191, + "step": 1662464 + }, + { + "epoch": 0.02, + "learning_rate": 2.2772122358836006e-05, + "loss": 3.9132, + "step": 1662976 + }, + { + "epoch": 0.02, + "learning_rate": 2.2763736411325483e-05, + "loss": 3.9046, + "step": 1663488 + }, + { + "epoch": 0.02, + "learning_rate": 2.2755350463814963e-05, + "loss": 3.9094, + "step": 1664000 + }, + { + "epoch": 0.02, + "learning_rate": 2.2746964516304446e-05, + "loss": 3.9036, + "step": 1664512 + }, + { + "epoch": 0.02, + "learning_rate": 2.2738578568793926e-05, + "loss": 3.9102, + "step": 1665024 + }, + { + "epoch": 0.02, + "learning_rate": 2.2730209000087135e-05, + "loss": 3.9046, + "step": 1665536 + }, + { + "epoch": 0.02, + "learning_rate": 2.2721823052576615e-05, + "loss": 3.9128, + "step": 1666048 + }, + { + "epoch": 0.02, + "learning_rate": 2.2713437105066095e-05, + "loss": 3.9089, + "step": 1666560 + }, + { + "epoch": 0.02, + "learning_rate": 2.2705067536359308e-05, + "loss": 3.9091, + "step": 1667072 + }, + { + "epoch": 0.02, + "learning_rate": 2.2696681588848788e-05, + "loss": 3.9047, + "step": 1667584 + }, + { + "epoch": 0.02, + "learning_rate": 2.2688295641338268e-05, + "loss": 3.9066, + "step": 1668096 + }, + { + "epoch": 0.02, + "learning_rate": 2.2679909693827748e-05, + "loss": 3.9051, + "step": 1668608 + }, + { + "epoch": 0.02, + "learning_rate": 2.2671523746317227e-05, + "loss": 3.9156, + "step": 1669120 + }, + { + "epoch": 0.02, + "learning_rate": 2.2663137798806707e-05, + "loss": 3.9212, + "step": 1669632 + }, + { + "epoch": 0.02, + "learning_rate": 2.2654751851296187e-05, + "loss": 3.918, + "step": 1670144 + }, + { + "epoch": 0.02, + "learning_rate": 2.2646365903785667e-05, + "loss": 3.9041, + "step": 1670656 + }, + { + "epoch": 0.02, + "learning_rate": 2.263799633507888e-05, + "loss": 3.9185, + "step": 1671168 + }, + { + "epoch": 0.02, + "learning_rate": 2.262961038756836e-05, + "loss": 3.91, + "step": 1671680 + }, + { + "epoch": 0.02, + "learning_rate": 2.262124081886157e-05, + "loss": 3.9239, + "step": 1672192 + }, + { + "epoch": 0.02, + "learning_rate": 2.261285487135105e-05, + "loss": 3.9116, + "step": 1672704 + }, + { + "epoch": 0.02, + "learning_rate": 2.260446892384053e-05, + "loss": 3.9107, + "step": 1673216 + }, + { + "epoch": 0.02, + "learning_rate": 2.259608297633001e-05, + "loss": 3.9084, + "step": 1673728 + }, + { + "epoch": 0.02, + "learning_rate": 2.258769702881949e-05, + "loss": 3.9132, + "step": 1674240 + }, + { + "epoch": 0.02, + "learning_rate": 2.257931108130897e-05, + "loss": 3.9065, + "step": 1674752 + }, + { + "epoch": 0.02, + "learning_rate": 2.257092513379845e-05, + "loss": 3.9066, + "step": 1675264 + }, + { + "epoch": 0.02, + "learning_rate": 2.256253918628793e-05, + "loss": 3.9101, + "step": 1675776 + }, + { + "epoch": 0.02, + "learning_rate": 2.255418599638487e-05, + "loss": 3.9138, + "step": 1676288 + }, + { + "epoch": 0.02, + "learning_rate": 2.2545800048874354e-05, + "loss": 3.9149, + "step": 1676800 + }, + { + "epoch": 0.02, + "learning_rate": 2.2537414101363833e-05, + "loss": 3.911, + "step": 1677312 + }, + { + "epoch": 0.02, + "learning_rate": 2.252902815385331e-05, + "loss": 3.9156, + "step": 1677824 + }, + { + "epoch": 0.02, + "learning_rate": 2.252064220634279e-05, + "loss": 3.9087, + "step": 1678336 + }, + { + "epoch": 0.02, + "learning_rate": 2.2512272637636002e-05, + "loss": 3.9098, + "step": 1678848 + }, + { + "epoch": 0.03, + "eval_loss": 3.9947128295898438, + "eval_runtime": 298.8861, + "eval_samples_per_second": 1276.71, + "eval_steps_per_second": 39.898, + "step": 1679027 + }, + { + "epoch": 1.0, + "learning_rate": 2.2503886690125482e-05, + "loss": 3.9092, + "step": 1679360 + }, + { + "epoch": 1.0, + "learning_rate": 2.2495500742614962e-05, + "loss": 3.8985, + "step": 1679872 + }, + { + "epoch": 1.0, + "learning_rate": 2.2487114795104442e-05, + "loss": 3.9152, + "step": 1680384 + }, + { + "epoch": 1.0, + "learning_rate": 2.2478728847593922e-05, + "loss": 3.9131, + "step": 1680896 + }, + { + "epoch": 1.0, + "learning_rate": 2.2470342900083402e-05, + "loss": 3.9186, + "step": 1681408 + }, + { + "epoch": 1.0, + "learning_rate": 2.2461956952572882e-05, + "loss": 3.9072, + "step": 1681920 + }, + { + "epoch": 1.0, + "learning_rate": 2.245358738386609e-05, + "loss": 3.9018, + "step": 1682432 + }, + { + "epoch": 1.0, + "learning_rate": 2.2445217815159307e-05, + "loss": 3.9042, + "step": 1682944 + }, + { + "epoch": 1.0, + "learning_rate": 2.2436831867648784e-05, + "loss": 3.9065, + "step": 1683456 + }, + { + "epoch": 1.0, + "learning_rate": 2.2428445920138264e-05, + "loss": 3.9065, + "step": 1683968 + }, + { + "epoch": 1.0, + "learning_rate": 2.2420059972627744e-05, + "loss": 3.9198, + "step": 1684480 + }, + { + "epoch": 1.0, + "learning_rate": 2.2411674025117224e-05, + "loss": 3.92, + "step": 1684992 + }, + { + "epoch": 1.0, + "learning_rate": 2.2403304456410433e-05, + "loss": 3.8973, + "step": 1685504 + }, + { + "epoch": 1.0, + "learning_rate": 2.2394918508899916e-05, + "loss": 3.9037, + "step": 1686016 + }, + { + "epoch": 1.0, + "learning_rate": 2.2386532561389396e-05, + "loss": 3.9161, + "step": 1686528 + }, + { + "epoch": 1.0, + "learning_rate": 2.2378146613878876e-05, + "loss": 3.8972, + "step": 1687040 + }, + { + "epoch": 1.0, + "learning_rate": 2.2369760666368356e-05, + "loss": 3.9086, + "step": 1687552 + }, + { + "epoch": 1.0, + "learning_rate": 2.2361374718857836e-05, + "loss": 3.9069, + "step": 1688064 + }, + { + "epoch": 1.0, + "learning_rate": 2.2352988771347316e-05, + "loss": 3.9039, + "step": 1688576 + }, + { + "epoch": 1.0, + "learning_rate": 2.2344619202640525e-05, + "loss": 3.9232, + "step": 1689088 + }, + { + "epoch": 1.0, + "learning_rate": 2.2336233255130008e-05, + "loss": 3.9092, + "step": 1689600 + }, + { + "epoch": 1.0, + "learning_rate": 2.2327847307619488e-05, + "loss": 3.9118, + "step": 1690112 + }, + { + "epoch": 1.0, + "learning_rate": 2.2319461360108965e-05, + "loss": 3.9088, + "step": 1690624 + }, + { + "epoch": 1.0, + "learning_rate": 2.2311075412598445e-05, + "loss": 3.9132, + "step": 1691136 + }, + { + "epoch": 1.0, + "learning_rate": 2.2302689465087925e-05, + "loss": 3.9057, + "step": 1691648 + }, + { + "epoch": 1.0, + "learning_rate": 2.2294303517577405e-05, + "loss": 3.9075, + "step": 1692160 + }, + { + "epoch": 1.0, + "learning_rate": 2.2285933948870617e-05, + "loss": 3.904, + "step": 1692672 + }, + { + "epoch": 1.0, + "learning_rate": 2.2277548001360097e-05, + "loss": 3.9011, + "step": 1693184 + }, + { + "epoch": 1.0, + "learning_rate": 2.2269162053849577e-05, + "loss": 3.903, + "step": 1693696 + }, + { + "epoch": 1.0, + "learning_rate": 2.2260776106339057e-05, + "loss": 3.9077, + "step": 1694208 + }, + { + "epoch": 1.01, + "learning_rate": 2.2252390158828537e-05, + "loss": 3.9101, + "step": 1694720 + }, + { + "epoch": 1.01, + "learning_rate": 2.2244004211318017e-05, + "loss": 3.9088, + "step": 1695232 + }, + { + "epoch": 1.01, + "learning_rate": 2.2235618263807493e-05, + "loss": 3.9141, + "step": 1695744 + }, + { + "epoch": 1.01, + "learning_rate": 2.2227232316296977e-05, + "loss": 3.9168, + "step": 1696256 + }, + { + "epoch": 1.01, + "learning_rate": 2.221886274759019e-05, + "loss": 3.9083, + "step": 1696768 + }, + { + "epoch": 1.01, + "learning_rate": 2.221047680007967e-05, + "loss": 3.9087, + "step": 1697280 + }, + { + "epoch": 1.01, + "learning_rate": 2.220210723137288e-05, + "loss": 3.9083, + "step": 1697792 + }, + { + "epoch": 1.01, + "learning_rate": 2.219372128386236e-05, + "loss": 3.9061, + "step": 1698304 + }, + { + "epoch": 1.01, + "learning_rate": 2.2185335336351838e-05, + "loss": 3.8963, + "step": 1698816 + }, + { + "epoch": 1.01, + "learning_rate": 2.2176949388841318e-05, + "loss": 3.9025, + "step": 1699328 + }, + { + "epoch": 1.01, + "learning_rate": 2.2168563441330798e-05, + "loss": 3.9035, + "step": 1699840 + }, + { + "epoch": 1.01, + "learning_rate": 2.2160177493820278e-05, + "loss": 3.914, + "step": 1700352 + }, + { + "epoch": 1.01, + "learning_rate": 2.2151791546309758e-05, + "loss": 3.9011, + "step": 1700864 + }, + { + "epoch": 1.01, + "learning_rate": 2.2143405598799238e-05, + "loss": 3.9038, + "step": 1701376 + }, + { + "epoch": 1.01, + "learning_rate": 2.2135019651288718e-05, + "loss": 3.9225, + "step": 1701888 + }, + { + "epoch": 1.01, + "learning_rate": 2.2126633703778198e-05, + "loss": 3.9083, + "step": 1702400 + }, + { + "epoch": 1.01, + "learning_rate": 2.211826413507141e-05, + "loss": 3.9115, + "step": 1702912 + }, + { + "epoch": 1.01, + "learning_rate": 2.210987818756089e-05, + "loss": 3.9, + "step": 1703424 + }, + { + "epoch": 1.01, + "learning_rate": 2.210149224005037e-05, + "loss": 3.8894, + "step": 1703936 + }, + { + "epoch": 1.01, + "learning_rate": 2.209310629253985e-05, + "loss": 3.9167, + "step": 1704448 + }, + { + "epoch": 1.01, + "learning_rate": 2.2084720345029327e-05, + "loss": 3.9076, + "step": 1704960 + }, + { + "epoch": 1.01, + "learning_rate": 2.2076334397518807e-05, + "loss": 3.8991, + "step": 1705472 + }, + { + "epoch": 1.01, + "learning_rate": 2.2067948450008287e-05, + "loss": 3.9032, + "step": 1705984 + }, + { + "epoch": 1.01, + "learning_rate": 2.205956250249777e-05, + "loss": 3.9107, + "step": 1706496 + }, + { + "epoch": 1.01, + "learning_rate": 2.205119293379098e-05, + "loss": 3.8865, + "step": 1707008 + }, + { + "epoch": 1.01, + "learning_rate": 2.2042823365084192e-05, + "loss": 3.9052, + "step": 1707520 + }, + { + "epoch": 1.01, + "learning_rate": 2.203443741757367e-05, + "loss": 3.8981, + "step": 1708032 + }, + { + "epoch": 1.01, + "learning_rate": 2.2026051470063148e-05, + "loss": 3.8978, + "step": 1708544 + }, + { + "epoch": 1.01, + "learning_rate": 2.201766552255263e-05, + "loss": 3.916, + "step": 1709056 + }, + { + "epoch": 1.01, + "learning_rate": 2.200927957504211e-05, + "loss": 3.9018, + "step": 1709568 + }, + { + "epoch": 1.01, + "learning_rate": 2.200089362753159e-05, + "loss": 3.901, + "step": 1710080 + }, + { + "epoch": 1.01, + "learning_rate": 2.199250768002107e-05, + "loss": 3.9104, + "step": 1710592 + }, + { + "epoch": 1.01, + "learning_rate": 2.198412173251055e-05, + "loss": 3.8939, + "step": 1711104 + }, + { + "epoch": 1.01, + "learning_rate": 2.197573578500003e-05, + "loss": 3.8977, + "step": 1711616 + }, + { + "epoch": 1.01, + "learning_rate": 2.196736621629324e-05, + "loss": 3.9052, + "step": 1712128 + }, + { + "epoch": 1.01, + "learning_rate": 2.1958980268782724e-05, + "loss": 3.901, + "step": 1712640 + }, + { + "epoch": 1.01, + "learning_rate": 2.1950594321272204e-05, + "loss": 3.9052, + "step": 1713152 + }, + { + "epoch": 1.01, + "learning_rate": 2.1942208373761684e-05, + "loss": 3.8932, + "step": 1713664 + }, + { + "epoch": 1.01, + "learning_rate": 2.193382242625116e-05, + "loss": 3.888, + "step": 1714176 + }, + { + "epoch": 1.01, + "learning_rate": 2.192543647874064e-05, + "loss": 3.9009, + "step": 1714688 + }, + { + "epoch": 1.01, + "learning_rate": 2.191705053123012e-05, + "loss": 3.9139, + "step": 1715200 + }, + { + "epoch": 1.01, + "learning_rate": 2.1908680962523333e-05, + "loss": 3.8987, + "step": 1715712 + }, + { + "epoch": 1.01, + "learning_rate": 2.1900295015012813e-05, + "loss": 3.9161, + "step": 1716224 + }, + { + "epoch": 1.01, + "learning_rate": 2.1891909067502293e-05, + "loss": 3.9145, + "step": 1716736 + }, + { + "epoch": 1.01, + "learning_rate": 2.1883523119991773e-05, + "loss": 3.9082, + "step": 1717248 + }, + { + "epoch": 1.01, + "learning_rate": 2.187515355128498e-05, + "loss": 3.8991, + "step": 1717760 + }, + { + "epoch": 1.01, + "learning_rate": 2.186676760377446e-05, + "loss": 3.9138, + "step": 1718272 + }, + { + "epoch": 1.01, + "learning_rate": 2.185838165626394e-05, + "loss": 3.9038, + "step": 1718784 + }, + { + "epoch": 1.01, + "learning_rate": 2.1849995708753425e-05, + "loss": 3.9002, + "step": 1719296 + }, + { + "epoch": 1.01, + "learning_rate": 2.1841609761242905e-05, + "loss": 3.9089, + "step": 1719808 + }, + { + "epoch": 1.01, + "learning_rate": 2.1833240192536114e-05, + "loss": 3.9047, + "step": 1720320 + }, + { + "epoch": 1.01, + "learning_rate": 2.1824854245025594e-05, + "loss": 3.9148, + "step": 1720832 + }, + { + "epoch": 1.01, + "learning_rate": 2.1816468297515074e-05, + "loss": 3.907, + "step": 1721344 + }, + { + "epoch": 1.01, + "learning_rate": 2.1808082350004554e-05, + "loss": 3.8917, + "step": 1721856 + }, + { + "epoch": 1.01, + "learning_rate": 2.1799696402494034e-05, + "loss": 3.8923, + "step": 1722368 + }, + { + "epoch": 1.01, + "learning_rate": 2.1791326833787246e-05, + "loss": 3.8997, + "step": 1722880 + }, + { + "epoch": 1.01, + "learning_rate": 2.1782940886276726e-05, + "loss": 3.9085, + "step": 1723392 + }, + { + "epoch": 1.01, + "learning_rate": 2.1774554938766206e-05, + "loss": 3.9033, + "step": 1723904 + }, + { + "epoch": 1.01, + "learning_rate": 2.1766168991255686e-05, + "loss": 3.9026, + "step": 1724416 + }, + { + "epoch": 1.02, + "learning_rate": 2.1757783043745163e-05, + "loss": 3.9039, + "step": 1724928 + }, + { + "epoch": 1.02, + "learning_rate": 2.1749397096234646e-05, + "loss": 3.8947, + "step": 1725440 + }, + { + "epoch": 1.02, + "learning_rate": 2.174102752752786e-05, + "loss": 3.9039, + "step": 1725952 + }, + { + "epoch": 1.02, + "learning_rate": 2.173264158001734e-05, + "loss": 3.899, + "step": 1726464 + }, + { + "epoch": 1.02, + "learning_rate": 2.1724255632506815e-05, + "loss": 3.9178, + "step": 1726976 + }, + { + "epoch": 1.02, + "learning_rate": 2.1715869684996295e-05, + "loss": 3.9119, + "step": 1727488 + }, + { + "epoch": 1.02, + "learning_rate": 2.1707500116289507e-05, + "loss": 3.9079, + "step": 1728000 + }, + { + "epoch": 1.02, + "learning_rate": 2.1699114168778987e-05, + "loss": 3.8978, + "step": 1728512 + }, + { + "epoch": 1.02, + "learning_rate": 2.1690728221268467e-05, + "loss": 3.906, + "step": 1729024 + }, + { + "epoch": 1.02, + "learning_rate": 2.1682342273757947e-05, + "loss": 3.9008, + "step": 1729536 + }, + { + "epoch": 1.02, + "learning_rate": 2.167397270505116e-05, + "loss": 3.9162, + "step": 1730048 + }, + { + "epoch": 1.02, + "learning_rate": 2.1665586757540636e-05, + "loss": 3.9024, + "step": 1730560 + }, + { + "epoch": 1.02, + "learning_rate": 2.1657200810030116e-05, + "loss": 3.8994, + "step": 1731072 + }, + { + "epoch": 1.02, + "learning_rate": 2.1648814862519596e-05, + "loss": 3.9079, + "step": 1731584 + }, + { + "epoch": 1.02, + "learning_rate": 2.164042891500908e-05, + "loss": 3.9065, + "step": 1732096 + }, + { + "epoch": 1.02, + "learning_rate": 2.163204296749856e-05, + "loss": 3.8978, + "step": 1732608 + }, + { + "epoch": 1.02, + "learning_rate": 2.162365701998804e-05, + "loss": 3.9025, + "step": 1733120 + }, + { + "epoch": 1.02, + "learning_rate": 2.1615271072477516e-05, + "loss": 3.8943, + "step": 1733632 + }, + { + "epoch": 1.02, + "learning_rate": 2.160690150377073e-05, + "loss": 3.895, + "step": 1734144 + }, + { + "epoch": 1.02, + "learning_rate": 2.159851555626021e-05, + "loss": 3.8872, + "step": 1734656 + }, + { + "epoch": 1.02, + "learning_rate": 2.159012960874969e-05, + "loss": 3.9077, + "step": 1735168 + }, + { + "epoch": 1.02, + "learning_rate": 2.158174366123917e-05, + "loss": 3.9011, + "step": 1735680 + }, + { + "epoch": 1.02, + "learning_rate": 2.157337409253238e-05, + "loss": 3.8992, + "step": 1736192 + }, + { + "epoch": 1.02, + "learning_rate": 2.156500452382559e-05, + "loss": 3.8975, + "step": 1736704 + }, + { + "epoch": 1.02, + "learning_rate": 2.155661857631507e-05, + "loss": 3.8952, + "step": 1737216 + }, + { + "epoch": 1.02, + "learning_rate": 2.154823262880455e-05, + "loss": 3.917, + "step": 1737728 + }, + { + "epoch": 1.02, + "learning_rate": 2.1539846681294033e-05, + "loss": 3.9171, + "step": 1738240 + }, + { + "epoch": 1.02, + "learning_rate": 2.1531460733783513e-05, + "loss": 3.9131, + "step": 1738752 + }, + { + "epoch": 1.02, + "learning_rate": 2.152307478627299e-05, + "loss": 3.9029, + "step": 1739264 + }, + { + "epoch": 1.02, + "learning_rate": 2.1514705217566202e-05, + "loss": 3.901, + "step": 1739776 + }, + { + "epoch": 1.02, + "learning_rate": 2.1506319270055682e-05, + "loss": 3.9042, + "step": 1740288 + }, + { + "epoch": 1.02, + "learning_rate": 2.1497933322545162e-05, + "loss": 3.8911, + "step": 1740800 + }, + { + "epoch": 1.02, + "learning_rate": 2.1489547375034642e-05, + "loss": 3.9053, + "step": 1741312 + }, + { + "epoch": 1.02, + "learning_rate": 2.1481161427524122e-05, + "loss": 3.9013, + "step": 1741824 + }, + { + "epoch": 1.02, + "learning_rate": 2.1472775480013602e-05, + "loss": 3.904, + "step": 1742336 + }, + { + "epoch": 1.02, + "learning_rate": 2.1464389532503082e-05, + "loss": 3.9081, + "step": 1742848 + }, + { + "epoch": 1.02, + "learning_rate": 2.145601996379629e-05, + "loss": 3.897, + "step": 1743360 + }, + { + "epoch": 1.02, + "learning_rate": 2.144763401628577e-05, + "loss": 3.9048, + "step": 1743872 + }, + { + "epoch": 1.02, + "learning_rate": 2.1439248068775254e-05, + "loss": 3.8973, + "step": 1744384 + }, + { + "epoch": 1.02, + "learning_rate": 2.1430862121264734e-05, + "loss": 3.9004, + "step": 1744896 + }, + { + "epoch": 1.02, + "learning_rate": 2.1422476173754214e-05, + "loss": 3.904, + "step": 1745408 + }, + { + "epoch": 1.02, + "learning_rate": 2.1414106605047423e-05, + "loss": 3.915, + "step": 1745920 + }, + { + "epoch": 1.02, + "learning_rate": 2.1405720657536903e-05, + "loss": 3.9107, + "step": 1746432 + }, + { + "epoch": 1.02, + "learning_rate": 2.1397334710026383e-05, + "loss": 3.9006, + "step": 1746944 + }, + { + "epoch": 1.02, + "learning_rate": 2.1388948762515863e-05, + "loss": 3.9102, + "step": 1747456 + }, + { + "epoch": 1.02, + "learning_rate": 2.1380562815005343e-05, + "loss": 3.9038, + "step": 1747968 + }, + { + "epoch": 1.02, + "learning_rate": 2.1372176867494823e-05, + "loss": 3.9153, + "step": 1748480 + }, + { + "epoch": 1.02, + "learning_rate": 2.1363790919984303e-05, + "loss": 3.9058, + "step": 1748992 + }, + { + "epoch": 1.02, + "learning_rate": 2.1355404972473783e-05, + "loss": 3.9085, + "step": 1749504 + }, + { + "epoch": 1.02, + "learning_rate": 2.1347019024963263e-05, + "loss": 3.9005, + "step": 1750016 + }, + { + "epoch": 1.02, + "learning_rate": 2.1338649456256472e-05, + "loss": 3.9076, + "step": 1750528 + }, + { + "epoch": 1.02, + "learning_rate": 2.1330263508745956e-05, + "loss": 3.8949, + "step": 1751040 + }, + { + "epoch": 1.02, + "learning_rate": 2.1321877561235436e-05, + "loss": 3.9014, + "step": 1751552 + }, + { + "epoch": 1.02, + "learning_rate": 2.1313491613724915e-05, + "loss": 3.9038, + "step": 1752064 + }, + { + "epoch": 1.02, + "learning_rate": 2.1305122045018125e-05, + "loss": 3.9064, + "step": 1752576 + }, + { + "epoch": 1.02, + "learning_rate": 2.1296736097507605e-05, + "loss": 3.9076, + "step": 1753088 + }, + { + "epoch": 1.02, + "learning_rate": 2.1288350149997084e-05, + "loss": 3.9023, + "step": 1753600 + }, + { + "epoch": 1.02, + "learning_rate": 2.127999696009403e-05, + "loss": 3.9113, + "step": 1754112 + }, + { + "epoch": 1.02, + "learning_rate": 2.127161101258351e-05, + "loss": 3.8986, + "step": 1754624 + }, + { + "epoch": 1.02, + "learning_rate": 2.126322506507299e-05, + "loss": 3.909, + "step": 1755136 + }, + { + "epoch": 1.03, + "eval_loss": 3.992473840713501, + "eval_runtime": 291.3125, + "eval_samples_per_second": 1309.902, + "eval_steps_per_second": 40.935, + "step": 1755347 + }, + { + "epoch": 0.0, + "learning_rate": 2.125483911756247e-05, + "loss": 3.8979, + "step": 1755648 + }, + { + "epoch": 0.0, + "learning_rate": 2.1246453170051946e-05, + "loss": 3.8893, + "step": 1756160 + }, + { + "epoch": 0.0, + "learning_rate": 2.1238067222541426e-05, + "loss": 3.908, + "step": 1756672 + }, + { + "epoch": 0.0, + "learning_rate": 2.122968127503091e-05, + "loss": 3.9073, + "step": 1757184 + }, + { + "epoch": 0.0, + "learning_rate": 2.122129532752039e-05, + "loss": 3.9118, + "step": 1757696 + }, + { + "epoch": 0.0, + "learning_rate": 2.121290938000987e-05, + "loss": 3.9012, + "step": 1758208 + }, + { + "epoch": 0.0, + "learning_rate": 2.120452343249935e-05, + "loss": 3.8972, + "step": 1758720 + }, + { + "epoch": 0.0, + "learning_rate": 2.1196137484988826e-05, + "loss": 3.9001, + "step": 1759232 + }, + { + "epoch": 0.0, + "learning_rate": 2.1187751537478306e-05, + "loss": 3.9027, + "step": 1759744 + }, + { + "epoch": 0.0, + "learning_rate": 2.1179365589967786e-05, + "loss": 3.8969, + "step": 1760256 + }, + { + "epoch": 0.0, + "learning_rate": 2.1170979642457266e-05, + "loss": 3.9129, + "step": 1760768 + }, + { + "epoch": 0.0, + "learning_rate": 2.116259369494675e-05, + "loss": 3.912, + "step": 1761280 + }, + { + "epoch": 0.0, + "learning_rate": 2.1154224126239958e-05, + "loss": 3.8943, + "step": 1761792 + }, + { + "epoch": 0.0, + "learning_rate": 2.1145838178729438e-05, + "loss": 3.8954, + "step": 1762304 + }, + { + "epoch": 0.0, + "learning_rate": 2.1137452231218918e-05, + "loss": 3.9088, + "step": 1762816 + }, + { + "epoch": 0.0, + "learning_rate": 2.1129066283708398e-05, + "loss": 3.8898, + "step": 1763328 + }, + { + "epoch": 0.0, + "learning_rate": 2.1120680336197878e-05, + "loss": 3.9009, + "step": 1763840 + }, + { + "epoch": 0.0, + "learning_rate": 2.1112294388687358e-05, + "loss": 3.8969, + "step": 1764352 + }, + { + "epoch": 0.0, + "learning_rate": 2.1103908441176838e-05, + "loss": 3.9032, + "step": 1764864 + }, + { + "epoch": 0.0, + "learning_rate": 2.1095522493666318e-05, + "loss": 3.9141, + "step": 1765376 + }, + { + "epoch": 0.0, + "learning_rate": 2.1087136546155798e-05, + "loss": 3.9091, + "step": 1765888 + }, + { + "epoch": 0.0, + "learning_rate": 2.1078750598645278e-05, + "loss": 3.9042, + "step": 1766400 + }, + { + "epoch": 0.0, + "learning_rate": 2.1070364651134758e-05, + "loss": 3.9013, + "step": 1766912 + }, + { + "epoch": 0.0, + "learning_rate": 2.1061995082427967e-05, + "loss": 3.9074, + "step": 1767424 + }, + { + "epoch": 0.0, + "learning_rate": 2.105360913491745e-05, + "loss": 3.8954, + "step": 1767936 + }, + { + "epoch": 0.0, + "learning_rate": 2.104522318740693e-05, + "loss": 3.9052, + "step": 1768448 + }, + { + "epoch": 0.0, + "learning_rate": 2.103683723989641e-05, + "loss": 3.896, + "step": 1768960 + }, + { + "epoch": 0.0, + "learning_rate": 2.102845129238589e-05, + "loss": 3.8945, + "step": 1769472 + }, + { + "epoch": 0.0, + "learning_rate": 2.10200817236791e-05, + "loss": 3.8985, + "step": 1769984 + }, + { + "epoch": 0.0, + "learning_rate": 2.101169577616858e-05, + "loss": 3.9055, + "step": 1770496 + }, + { + "epoch": 0.01, + "learning_rate": 2.100330982865806e-05, + "loss": 3.8986, + "step": 1771008 + }, + { + "epoch": 0.01, + "learning_rate": 2.099492388114754e-05, + "loss": 3.9058, + "step": 1771520 + }, + { + "epoch": 0.01, + "learning_rate": 2.098653793363702e-05, + "loss": 3.9089, + "step": 1772032 + }, + { + "epoch": 0.01, + "learning_rate": 2.09781519861265e-05, + "loss": 3.9134, + "step": 1772544 + }, + { + "epoch": 0.01, + "learning_rate": 2.096979879622344e-05, + "loss": 3.8954, + "step": 1773056 + }, + { + "epoch": 0.01, + "learning_rate": 2.096141284871292e-05, + "loss": 3.9046, + "step": 1773568 + }, + { + "epoch": 0.01, + "learning_rate": 2.0953043280006133e-05, + "loss": 3.9064, + "step": 1774080 + }, + { + "epoch": 0.01, + "learning_rate": 2.0944657332495613e-05, + "loss": 3.895, + "step": 1774592 + }, + { + "epoch": 0.01, + "learning_rate": 2.0936271384985093e-05, + "loss": 3.8905, + "step": 1775104 + }, + { + "epoch": 0.01, + "learning_rate": 2.0927885437474573e-05, + "loss": 3.8953, + "step": 1775616 + }, + { + "epoch": 0.01, + "learning_rate": 2.0919499489964053e-05, + "loss": 3.8994, + "step": 1776128 + }, + { + "epoch": 0.01, + "learning_rate": 2.0911113542453533e-05, + "loss": 3.9064, + "step": 1776640 + }, + { + "epoch": 0.01, + "learning_rate": 2.0902727594943013e-05, + "loss": 3.895, + "step": 1777152 + }, + { + "epoch": 0.01, + "learning_rate": 2.0894341647432492e-05, + "loss": 3.8951, + "step": 1777664 + }, + { + "epoch": 0.01, + "learning_rate": 2.0885955699921972e-05, + "loss": 3.9153, + "step": 1778176 + }, + { + "epoch": 0.01, + "learning_rate": 2.0877569752411452e-05, + "loss": 3.9025, + "step": 1778688 + }, + { + "epoch": 0.01, + "learning_rate": 2.0869183804900932e-05, + "loss": 3.9091, + "step": 1779200 + }, + { + "epoch": 0.01, + "learning_rate": 2.0860797857390412e-05, + "loss": 3.8904, + "step": 1779712 + }, + { + "epoch": 0.01, + "learning_rate": 2.0852411909879892e-05, + "loss": 3.8831, + "step": 1780224 + }, + { + "epoch": 0.01, + "learning_rate": 2.0844042341173105e-05, + "loss": 3.9129, + "step": 1780736 + }, + { + "epoch": 0.01, + "learning_rate": 2.0835656393662585e-05, + "loss": 3.8982, + "step": 1781248 + }, + { + "epoch": 0.01, + "learning_rate": 2.0827270446152065e-05, + "loss": 3.8948, + "step": 1781760 + }, + { + "epoch": 0.01, + "learning_rate": 2.0818884498641545e-05, + "loss": 3.9022, + "step": 1782272 + }, + { + "epoch": 0.01, + "learning_rate": 2.081049855113102e-05, + "loss": 3.8972, + "step": 1782784 + }, + { + "epoch": 0.01, + "learning_rate": 2.08021126036205e-05, + "loss": 3.8847, + "step": 1783296 + }, + { + "epoch": 0.01, + "learning_rate": 2.0793743034913714e-05, + "loss": 3.8971, + "step": 1783808 + }, + { + "epoch": 0.01, + "learning_rate": 2.0785357087403194e-05, + "loss": 3.8926, + "step": 1784320 + }, + { + "epoch": 0.01, + "learning_rate": 2.0776971139892674e-05, + "loss": 3.8935, + "step": 1784832 + }, + { + "epoch": 0.01, + "learning_rate": 2.0768585192382153e-05, + "loss": 3.9081, + "step": 1785344 + }, + { + "epoch": 0.01, + "learning_rate": 2.0760199244871633e-05, + "loss": 3.8948, + "step": 1785856 + }, + { + "epoch": 0.01, + "learning_rate": 2.0751813297361113e-05, + "loss": 3.8931, + "step": 1786368 + }, + { + "epoch": 0.01, + "learning_rate": 2.074346010745806e-05, + "loss": 3.9054, + "step": 1786880 + }, + { + "epoch": 0.01, + "learning_rate": 2.073507415994754e-05, + "loss": 3.8863, + "step": 1787392 + }, + { + "epoch": 0.01, + "learning_rate": 2.072668821243702e-05, + "loss": 3.8946, + "step": 1787904 + }, + { + "epoch": 0.01, + "learning_rate": 2.0718302264926495e-05, + "loss": 3.8962, + "step": 1788416 + }, + { + "epoch": 0.01, + "learning_rate": 2.0709916317415975e-05, + "loss": 3.8934, + "step": 1788928 + }, + { + "epoch": 0.01, + "learning_rate": 2.0701530369905455e-05, + "loss": 3.8968, + "step": 1789440 + }, + { + "epoch": 0.01, + "learning_rate": 2.0693144422394935e-05, + "loss": 3.8944, + "step": 1789952 + }, + { + "epoch": 0.01, + "learning_rate": 2.0684758474884418e-05, + "loss": 3.8784, + "step": 1790464 + }, + { + "epoch": 0.01, + "learning_rate": 2.0676388906177627e-05, + "loss": 3.8912, + "step": 1790976 + }, + { + "epoch": 0.01, + "learning_rate": 2.0668002958667107e-05, + "loss": 3.9119, + "step": 1791488 + }, + { + "epoch": 0.01, + "learning_rate": 2.0659617011156587e-05, + "loss": 3.8904, + "step": 1792000 + }, + { + "epoch": 0.01, + "learning_rate": 2.0651231063646067e-05, + "loss": 3.9136, + "step": 1792512 + }, + { + "epoch": 0.01, + "learning_rate": 2.0642845116135547e-05, + "loss": 3.9049, + "step": 1793024 + }, + { + "epoch": 0.01, + "learning_rate": 2.063447554742876e-05, + "loss": 3.9069, + "step": 1793536 + }, + { + "epoch": 0.01, + "learning_rate": 2.062608959991824e-05, + "loss": 3.8889, + "step": 1794048 + }, + { + "epoch": 0.01, + "learning_rate": 2.061770365240772e-05, + "loss": 3.9052, + "step": 1794560 + }, + { + "epoch": 0.01, + "learning_rate": 2.06093177048972e-05, + "loss": 3.9016, + "step": 1795072 + }, + { + "epoch": 0.01, + "learning_rate": 2.0600931757386676e-05, + "loss": 3.8918, + "step": 1795584 + }, + { + "epoch": 0.01, + "learning_rate": 2.0592545809876156e-05, + "loss": 3.9078, + "step": 1796096 + }, + { + "epoch": 0.01, + "learning_rate": 2.0584159862365636e-05, + "loss": 3.8988, + "step": 1796608 + }, + { + "epoch": 0.01, + "learning_rate": 2.057577391485512e-05, + "loss": 3.9071, + "step": 1797120 + }, + { + "epoch": 0.01, + "learning_rate": 2.05673879673446e-05, + "loss": 3.9053, + "step": 1797632 + }, + { + "epoch": 0.01, + "learning_rate": 2.0559018398637808e-05, + "loss": 3.8825, + "step": 1798144 + }, + { + "epoch": 0.01, + "learning_rate": 2.0550632451127288e-05, + "loss": 3.8845, + "step": 1798656 + }, + { + "epoch": 0.01, + "learning_rate": 2.0542246503616768e-05, + "loss": 3.8912, + "step": 1799168 + }, + { + "epoch": 0.01, + "learning_rate": 2.0533860556106248e-05, + "loss": 3.9023, + "step": 1799680 + }, + { + "epoch": 0.01, + "learning_rate": 2.052549098739946e-05, + "loss": 3.899, + "step": 1800192 + }, + { + "epoch": 0.01, + "learning_rate": 2.051710503988894e-05, + "loss": 3.8961, + "step": 1800704 + }, + { + "epoch": 0.02, + "learning_rate": 2.050871909237842e-05, + "loss": 3.8971, + "step": 1801216 + }, + { + "epoch": 0.02, + "learning_rate": 2.050034952367163e-05, + "loss": 3.8926, + "step": 1801728 + }, + { + "epoch": 0.02, + "learning_rate": 2.049196357616111e-05, + "loss": 3.8944, + "step": 1802240 + }, + { + "epoch": 0.02, + "learning_rate": 2.048357762865059e-05, + "loss": 3.8941, + "step": 1802752 + }, + { + "epoch": 0.02, + "learning_rate": 2.0475191681140073e-05, + "loss": 3.9092, + "step": 1803264 + }, + { + "epoch": 0.02, + "learning_rate": 2.0466805733629553e-05, + "loss": 3.9133, + "step": 1803776 + }, + { + "epoch": 0.02, + "learning_rate": 2.045841978611903e-05, + "loss": 3.8971, + "step": 1804288 + }, + { + "epoch": 0.02, + "learning_rate": 2.045003383860851e-05, + "loss": 3.8911, + "step": 1804800 + }, + { + "epoch": 0.02, + "learning_rate": 2.044164789109799e-05, + "loss": 3.8989, + "step": 1805312 + }, + { + "epoch": 0.02, + "learning_rate": 2.043326194358747e-05, + "loss": 3.8976, + "step": 1805824 + }, + { + "epoch": 0.02, + "learning_rate": 2.042487599607695e-05, + "loss": 3.9088, + "step": 1806336 + }, + { + "epoch": 0.02, + "learning_rate": 2.041649004856643e-05, + "loss": 3.8971, + "step": 1806848 + }, + { + "epoch": 0.02, + "learning_rate": 2.0408104101055912e-05, + "loss": 3.8942, + "step": 1807360 + }, + { + "epoch": 0.02, + "learning_rate": 2.039971815354539e-05, + "loss": 3.9032, + "step": 1807872 + }, + { + "epoch": 0.02, + "learning_rate": 2.039133220603487e-05, + "loss": 3.9042, + "step": 1808384 + }, + { + "epoch": 0.02, + "learning_rate": 2.038296263732808e-05, + "loss": 3.8885, + "step": 1808896 + }, + { + "epoch": 0.02, + "learning_rate": 2.037459306862129e-05, + "loss": 3.8963, + "step": 1809408 + }, + { + "epoch": 0.02, + "learning_rate": 2.0366207121110774e-05, + "loss": 3.8917, + "step": 1809920 + }, + { + "epoch": 0.02, + "learning_rate": 2.0357821173600254e-05, + "loss": 3.8869, + "step": 1810432 + }, + { + "epoch": 0.02, + "learning_rate": 2.0349435226089734e-05, + "loss": 3.8889, + "step": 1810944 + }, + { + "epoch": 0.02, + "learning_rate": 2.034104927857921e-05, + "loss": 3.8971, + "step": 1811456 + }, + { + "epoch": 0.02, + "learning_rate": 2.033266333106869e-05, + "loss": 3.8994, + "step": 1811968 + }, + { + "epoch": 0.02, + "learning_rate": 2.032427738355817e-05, + "loss": 3.8913, + "step": 1812480 + }, + { + "epoch": 0.02, + "learning_rate": 2.031589143604765e-05, + "loss": 3.8924, + "step": 1812992 + }, + { + "epoch": 0.02, + "learning_rate": 2.030750548853713e-05, + "loss": 3.8928, + "step": 1813504 + }, + { + "epoch": 0.02, + "learning_rate": 2.0299119541026614e-05, + "loss": 3.9074, + "step": 1814016 + }, + { + "epoch": 0.02, + "learning_rate": 2.0290733593516094e-05, + "loss": 3.9129, + "step": 1814528 + }, + { + "epoch": 0.02, + "learning_rate": 2.028234764600557e-05, + "loss": 3.9063, + "step": 1815040 + }, + { + "epoch": 0.02, + "learning_rate": 2.0273978077298783e-05, + "loss": 3.8982, + "step": 1815552 + }, + { + "epoch": 0.02, + "learning_rate": 2.0265592129788263e-05, + "loss": 3.8923, + "step": 1816064 + }, + { + "epoch": 0.02, + "learning_rate": 2.0257206182277743e-05, + "loss": 3.9014, + "step": 1816576 + }, + { + "epoch": 0.02, + "learning_rate": 2.0248820234767222e-05, + "loss": 3.885, + "step": 1817088 + }, + { + "epoch": 0.02, + "learning_rate": 2.0240450666060435e-05, + "loss": 3.8982, + "step": 1817600 + }, + { + "epoch": 0.02, + "learning_rate": 2.0232064718549915e-05, + "loss": 3.8974, + "step": 1818112 + }, + { + "epoch": 0.02, + "learning_rate": 2.022367877103939e-05, + "loss": 3.8941, + "step": 1818624 + }, + { + "epoch": 0.02, + "learning_rate": 2.0215309202332604e-05, + "loss": 3.8968, + "step": 1819136 + }, + { + "epoch": 0.02, + "learning_rate": 2.0206923254822084e-05, + "loss": 3.8964, + "step": 1819648 + }, + { + "epoch": 0.02, + "learning_rate": 2.0198537307311567e-05, + "loss": 3.9023, + "step": 1820160 + }, + { + "epoch": 0.02, + "learning_rate": 2.0190151359801044e-05, + "loss": 3.8955, + "step": 1820672 + }, + { + "epoch": 0.02, + "learning_rate": 2.0181765412290524e-05, + "loss": 3.891, + "step": 1821184 + }, + { + "epoch": 0.02, + "learning_rate": 2.0173379464780004e-05, + "loss": 3.9004, + "step": 1821696 + }, + { + "epoch": 0.02, + "learning_rate": 2.0165009896073213e-05, + "loss": 3.9053, + "step": 1822208 + }, + { + "epoch": 0.02, + "learning_rate": 2.0156623948562696e-05, + "loss": 3.9098, + "step": 1822720 + }, + { + "epoch": 0.02, + "learning_rate": 2.0148238001052176e-05, + "loss": 3.8946, + "step": 1823232 + }, + { + "epoch": 0.02, + "learning_rate": 2.0139852053541656e-05, + "loss": 3.9042, + "step": 1823744 + }, + { + "epoch": 0.02, + "learning_rate": 2.0131466106031136e-05, + "loss": 3.901, + "step": 1824256 + }, + { + "epoch": 0.02, + "learning_rate": 2.0123096537324345e-05, + "loss": 3.9079, + "step": 1824768 + }, + { + "epoch": 0.02, + "learning_rate": 2.0114710589813825e-05, + "loss": 3.8974, + "step": 1825280 + }, + { + "epoch": 0.02, + "learning_rate": 2.0106324642303305e-05, + "loss": 3.9022, + "step": 1825792 + }, + { + "epoch": 0.02, + "learning_rate": 2.0097938694792785e-05, + "loss": 3.8951, + "step": 1826304 + }, + { + "epoch": 0.02, + "learning_rate": 2.008955274728227e-05, + "loss": 3.9063, + "step": 1826816 + }, + { + "epoch": 0.02, + "learning_rate": 2.0081183178575477e-05, + "loss": 3.8874, + "step": 1827328 + }, + { + "epoch": 0.02, + "learning_rate": 2.0072797231064957e-05, + "loss": 3.8973, + "step": 1827840 + }, + { + "epoch": 0.02, + "learning_rate": 2.0064411283554437e-05, + "loss": 3.8996, + "step": 1828352 + }, + { + "epoch": 0.02, + "learning_rate": 2.0056025336043917e-05, + "loss": 3.9018, + "step": 1828864 + }, + { + "epoch": 0.02, + "learning_rate": 2.0047639388533397e-05, + "loss": 3.8979, + "step": 1829376 + }, + { + "epoch": 0.02, + "learning_rate": 2.0039253441022877e-05, + "loss": 3.896, + "step": 1829888 + }, + { + "epoch": 0.02, + "learning_rate": 2.003088387231609e-05, + "loss": 3.9067, + "step": 1830400 + }, + { + "epoch": 0.02, + "learning_rate": 2.002249792480557e-05, + "loss": 3.8917, + "step": 1830912 + }, + { + "epoch": 0.02, + "learning_rate": 2.0014111977295046e-05, + "loss": 3.9044, + "step": 1831424 + }, + { + "epoch": 0.03, + "eval_loss": 3.9899399280548096, + "eval_runtime": 306.6027, + "eval_samples_per_second": 1244.578, + "eval_steps_per_second": 38.894, + "step": 1831667 + }, + { + "epoch": 1.0, + "learning_rate": 2.0005726029784526e-05, + "loss": 3.8939, + "step": 1831936 + }, + { + "epoch": 1.0, + "learning_rate": 1.9997340082274006e-05, + "loss": 3.889, + "step": 1832448 + }, + { + "epoch": 1.0, + "learning_rate": 1.9988970513567222e-05, + "loss": 3.8992, + "step": 1832960 + }, + { + "epoch": 1.0, + "learning_rate": 1.99805845660567e-05, + "loss": 3.9004, + "step": 1833472 + }, + { + "epoch": 1.0, + "learning_rate": 1.997219861854618e-05, + "loss": 3.906, + "step": 1833984 + }, + { + "epoch": 1.0, + "learning_rate": 1.996381267103566e-05, + "loss": 3.8937, + "step": 1834496 + }, + { + "epoch": 1.0, + "learning_rate": 1.995542672352514e-05, + "loss": 3.8966, + "step": 1835008 + }, + { + "epoch": 1.0, + "learning_rate": 1.994705715481835e-05, + "loss": 3.8943, + "step": 1835520 + }, + { + "epoch": 1.0, + "learning_rate": 1.993867120730783e-05, + "loss": 3.8944, + "step": 1836032 + }, + { + "epoch": 1.0, + "learning_rate": 1.993028525979731e-05, + "loss": 3.8956, + "step": 1836544 + }, + { + "epoch": 1.0, + "learning_rate": 1.992189931228679e-05, + "loss": 3.9021, + "step": 1837056 + }, + { + "epoch": 1.0, + "learning_rate": 1.991351336477627e-05, + "loss": 3.9063, + "step": 1837568 + }, + { + "epoch": 1.0, + "learning_rate": 1.990514379606948e-05, + "loss": 3.8905, + "step": 1838080 + }, + { + "epoch": 1.0, + "learning_rate": 1.9896774227362692e-05, + "loss": 3.886, + "step": 1838592 + }, + { + "epoch": 1.0, + "learning_rate": 1.9888388279852172e-05, + "loss": 3.9064, + "step": 1839104 + }, + { + "epoch": 1.0, + "learning_rate": 1.9880002332341652e-05, + "loss": 3.8825, + "step": 1839616 + }, + { + "epoch": 1.0, + "learning_rate": 1.9871616384831132e-05, + "loss": 3.8961, + "step": 1840128 + }, + { + "epoch": 1.0, + "learning_rate": 1.9863230437320612e-05, + "loss": 3.8917, + "step": 1840640 + }, + { + "epoch": 1.0, + "learning_rate": 1.9854844489810092e-05, + "loss": 3.8956, + "step": 1841152 + }, + { + "epoch": 1.0, + "learning_rate": 1.9846458542299572e-05, + "loss": 3.9052, + "step": 1841664 + }, + { + "epoch": 1.0, + "learning_rate": 1.9838072594789052e-05, + "loss": 3.9035, + "step": 1842176 + }, + { + "epoch": 1.0, + "learning_rate": 1.9829686647278532e-05, + "loss": 3.9003, + "step": 1842688 + }, + { + "epoch": 1.0, + "learning_rate": 1.9821300699768012e-05, + "loss": 3.8966, + "step": 1843200 + }, + { + "epoch": 1.0, + "learning_rate": 1.9812914752257492e-05, + "loss": 3.8989, + "step": 1843712 + }, + { + "epoch": 1.0, + "learning_rate": 1.98045451835507e-05, + "loss": 3.8953, + "step": 1844224 + }, + { + "epoch": 1.0, + "learning_rate": 1.979615923604018e-05, + "loss": 3.902, + "step": 1844736 + }, + { + "epoch": 1.0, + "learning_rate": 1.978777328852966e-05, + "loss": 3.8883, + "step": 1845248 + }, + { + "epoch": 1.0, + "learning_rate": 1.9779387341019144e-05, + "loss": 3.8899, + "step": 1845760 + }, + { + "epoch": 1.0, + "learning_rate": 1.9771001393508624e-05, + "loss": 3.8975, + "step": 1846272 + }, + { + "epoch": 1.0, + "learning_rate": 1.9762615445998104e-05, + "loss": 3.8931, + "step": 1846784 + }, + { + "epoch": 1.01, + "learning_rate": 1.975422949848758e-05, + "loss": 3.8925, + "step": 1847296 + }, + { + "epoch": 1.01, + "learning_rate": 1.974584355097706e-05, + "loss": 3.9005, + "step": 1847808 + }, + { + "epoch": 1.01, + "learning_rate": 1.9737473982270273e-05, + "loss": 3.9054, + "step": 1848320 + }, + { + "epoch": 1.01, + "learning_rate": 1.9729104413563486e-05, + "loss": 3.9005, + "step": 1848832 + }, + { + "epoch": 1.01, + "learning_rate": 1.9720734844856698e-05, + "loss": 3.8909, + "step": 1849344 + }, + { + "epoch": 1.01, + "learning_rate": 1.9712348897346175e-05, + "loss": 3.9021, + "step": 1849856 + }, + { + "epoch": 1.01, + "learning_rate": 1.9703962949835655e-05, + "loss": 3.9013, + "step": 1850368 + }, + { + "epoch": 1.01, + "learning_rate": 1.9695577002325135e-05, + "loss": 3.8929, + "step": 1850880 + }, + { + "epoch": 1.01, + "learning_rate": 1.9687191054814615e-05, + "loss": 3.8861, + "step": 1851392 + }, + { + "epoch": 1.01, + "learning_rate": 1.9678805107304098e-05, + "loss": 3.8855, + "step": 1851904 + }, + { + "epoch": 1.01, + "learning_rate": 1.9670419159793578e-05, + "loss": 3.8925, + "step": 1852416 + }, + { + "epoch": 1.01, + "learning_rate": 1.9662033212283054e-05, + "loss": 3.905, + "step": 1852928 + }, + { + "epoch": 1.01, + "learning_rate": 1.9653647264772534e-05, + "loss": 3.8874, + "step": 1853440 + }, + { + "epoch": 1.01, + "learning_rate": 1.9645261317262014e-05, + "loss": 3.8914, + "step": 1853952 + }, + { + "epoch": 1.01, + "learning_rate": 1.9636891748555227e-05, + "loss": 3.9095, + "step": 1854464 + }, + { + "epoch": 1.01, + "learning_rate": 1.9628505801044707e-05, + "loss": 3.8945, + "step": 1854976 + }, + { + "epoch": 1.01, + "learning_rate": 1.9620119853534187e-05, + "loss": 3.9049, + "step": 1855488 + }, + { + "epoch": 1.01, + "learning_rate": 1.9611733906023667e-05, + "loss": 3.8888, + "step": 1856000 + }, + { + "epoch": 1.01, + "learning_rate": 1.960336433731688e-05, + "loss": 3.8687, + "step": 1856512 + }, + { + "epoch": 1.01, + "learning_rate": 1.9594994768610088e-05, + "loss": 3.9079, + "step": 1857024 + }, + { + "epoch": 1.01, + "learning_rate": 1.9586608821099568e-05, + "loss": 3.8959, + "step": 1857536 + }, + { + "epoch": 1.01, + "learning_rate": 1.957822287358905e-05, + "loss": 3.8893, + "step": 1858048 + }, + { + "epoch": 1.01, + "learning_rate": 1.9569836926078528e-05, + "loss": 3.894, + "step": 1858560 + }, + { + "epoch": 1.01, + "learning_rate": 1.9561450978568008e-05, + "loss": 3.8916, + "step": 1859072 + }, + { + "epoch": 1.01, + "learning_rate": 1.9553065031057488e-05, + "loss": 3.882, + "step": 1859584 + }, + { + "epoch": 1.01, + "learning_rate": 1.9544679083546968e-05, + "loss": 3.8858, + "step": 1860096 + }, + { + "epoch": 1.01, + "learning_rate": 1.9536293136036448e-05, + "loss": 3.8888, + "step": 1860608 + }, + { + "epoch": 1.01, + "learning_rate": 1.9527907188525928e-05, + "loss": 3.8889, + "step": 1861120 + }, + { + "epoch": 1.01, + "learning_rate": 1.9519521241015408e-05, + "loss": 3.9027, + "step": 1861632 + }, + { + "epoch": 1.01, + "learning_rate": 1.951115167230862e-05, + "loss": 3.8896, + "step": 1862144 + }, + { + "epoch": 1.01, + "learning_rate": 1.95027657247981e-05, + "loss": 3.8884, + "step": 1862656 + }, + { + "epoch": 1.01, + "learning_rate": 1.949437977728758e-05, + "loss": 3.9029, + "step": 1863168 + }, + { + "epoch": 1.01, + "learning_rate": 1.948599382977706e-05, + "loss": 3.8773, + "step": 1863680 + }, + { + "epoch": 1.01, + "learning_rate": 1.9477607882266537e-05, + "loss": 3.8849, + "step": 1864192 + }, + { + "epoch": 1.01, + "learning_rate": 1.9469238313559753e-05, + "loss": 3.8895, + "step": 1864704 + }, + { + "epoch": 1.01, + "learning_rate": 1.9460852366049233e-05, + "loss": 3.8928, + "step": 1865216 + }, + { + "epoch": 1.01, + "learning_rate": 1.945246641853871e-05, + "loss": 3.891, + "step": 1865728 + }, + { + "epoch": 1.01, + "learning_rate": 1.944409684983192e-05, + "loss": 3.8921, + "step": 1866240 + }, + { + "epoch": 1.01, + "learning_rate": 1.94357109023214e-05, + "loss": 3.8691, + "step": 1866752 + }, + { + "epoch": 1.01, + "learning_rate": 1.942732495481088e-05, + "loss": 3.8889, + "step": 1867264 + }, + { + "epoch": 1.01, + "learning_rate": 1.941893900730036e-05, + "loss": 3.9009, + "step": 1867776 + }, + { + "epoch": 1.01, + "learning_rate": 1.941055305978984e-05, + "loss": 3.8857, + "step": 1868288 + }, + { + "epoch": 1.01, + "learning_rate": 1.940216711227932e-05, + "loss": 3.9052, + "step": 1868800 + }, + { + "epoch": 1.01, + "learning_rate": 1.93937811647688e-05, + "loss": 3.8984, + "step": 1869312 + }, + { + "epoch": 1.01, + "learning_rate": 1.938539521725828e-05, + "loss": 3.9083, + "step": 1869824 + }, + { + "epoch": 1.01, + "learning_rate": 1.937700926974776e-05, + "loss": 3.8838, + "step": 1870336 + }, + { + "epoch": 1.01, + "learning_rate": 1.936862332223724e-05, + "loss": 3.8993, + "step": 1870848 + }, + { + "epoch": 1.01, + "learning_rate": 1.9360253753530454e-05, + "loss": 3.8971, + "step": 1871360 + }, + { + "epoch": 1.01, + "learning_rate": 1.9351867806019934e-05, + "loss": 3.8848, + "step": 1871872 + }, + { + "epoch": 1.01, + "learning_rate": 1.9343481858509414e-05, + "loss": 3.9022, + "step": 1872384 + }, + { + "epoch": 1.01, + "learning_rate": 1.933509591099889e-05, + "loss": 3.8906, + "step": 1872896 + }, + { + "epoch": 1.01, + "learning_rate": 1.932670996348837e-05, + "loss": 3.9032, + "step": 1873408 + }, + { + "epoch": 1.01, + "learning_rate": 1.931832401597785e-05, + "loss": 3.8987, + "step": 1873920 + }, + { + "epoch": 1.01, + "learning_rate": 1.930993806846733e-05, + "loss": 3.8748, + "step": 1874432 + }, + { + "epoch": 1.01, + "learning_rate": 1.9301552120956813e-05, + "loss": 3.8829, + "step": 1874944 + }, + { + "epoch": 1.01, + "learning_rate": 1.9293198931053755e-05, + "loss": 3.8852, + "step": 1875456 + }, + { + "epoch": 1.01, + "learning_rate": 1.9284829362346964e-05, + "loss": 3.898, + "step": 1875968 + }, + { + "epoch": 1.01, + "learning_rate": 1.9276459793640177e-05, + "loss": 3.8912, + "step": 1876480 + }, + { + "epoch": 1.01, + "learning_rate": 1.9268073846129657e-05, + "loss": 3.8897, + "step": 1876992 + }, + { + "epoch": 1.02, + "learning_rate": 1.9259687898619137e-05, + "loss": 3.8896, + "step": 1877504 + }, + { + "epoch": 1.02, + "learning_rate": 1.9251301951108617e-05, + "loss": 3.8899, + "step": 1878016 + }, + { + "epoch": 1.02, + "learning_rate": 1.9242916003598096e-05, + "loss": 3.8907, + "step": 1878528 + }, + { + "epoch": 1.02, + "learning_rate": 1.9234530056087576e-05, + "loss": 3.8861, + "step": 1879040 + }, + { + "epoch": 1.02, + "learning_rate": 1.9226144108577056e-05, + "loss": 3.9075, + "step": 1879552 + }, + { + "epoch": 1.02, + "learning_rate": 1.9217758161066536e-05, + "loss": 3.9052, + "step": 1880064 + }, + { + "epoch": 1.02, + "learning_rate": 1.9209372213556016e-05, + "loss": 3.8944, + "step": 1880576 + }, + { + "epoch": 1.02, + "learning_rate": 1.9200986266045496e-05, + "loss": 3.8855, + "step": 1881088 + }, + { + "epoch": 1.02, + "learning_rate": 1.9192600318534976e-05, + "loss": 3.8936, + "step": 1881600 + }, + { + "epoch": 1.02, + "learning_rate": 1.9184214371024456e-05, + "loss": 3.888, + "step": 1882112 + }, + { + "epoch": 1.02, + "learning_rate": 1.9175844802317665e-05, + "loss": 3.9059, + "step": 1882624 + }, + { + "epoch": 1.02, + "learning_rate": 1.9167458854807145e-05, + "loss": 3.8905, + "step": 1883136 + }, + { + "epoch": 1.02, + "learning_rate": 1.9159072907296625e-05, + "loss": 3.8906, + "step": 1883648 + }, + { + "epoch": 1.02, + "learning_rate": 1.915068695978611e-05, + "loss": 3.8967, + "step": 1884160 + }, + { + "epoch": 1.02, + "learning_rate": 1.914230101227559e-05, + "loss": 3.8971, + "step": 1884672 + }, + { + "epoch": 1.02, + "learning_rate": 1.913391506476507e-05, + "loss": 3.8821, + "step": 1885184 + }, + { + "epoch": 1.02, + "learning_rate": 1.9125545496058278e-05, + "loss": 3.8902, + "step": 1885696 + }, + { + "epoch": 1.02, + "learning_rate": 1.9117159548547757e-05, + "loss": 3.8839, + "step": 1886208 + }, + { + "epoch": 1.02, + "learning_rate": 1.9108773601037237e-05, + "loss": 3.8839, + "step": 1886720 + }, + { + "epoch": 1.02, + "learning_rate": 1.9100387653526717e-05, + "loss": 3.8815, + "step": 1887232 + }, + { + "epoch": 1.02, + "learning_rate": 1.9092001706016197e-05, + "loss": 3.8913, + "step": 1887744 + }, + { + "epoch": 1.02, + "learning_rate": 1.908363213730941e-05, + "loss": 3.8922, + "step": 1888256 + }, + { + "epoch": 1.02, + "learning_rate": 1.907524618979889e-05, + "loss": 3.8899, + "step": 1888768 + }, + { + "epoch": 1.02, + "learning_rate": 1.9066860242288366e-05, + "loss": 3.8898, + "step": 1889280 + }, + { + "epoch": 1.02, + "learning_rate": 1.9058474294777846e-05, + "loss": 3.8852, + "step": 1889792 + }, + { + "epoch": 1.02, + "learning_rate": 1.905008834726733e-05, + "loss": 3.9001, + "step": 1890304 + }, + { + "epoch": 1.02, + "learning_rate": 1.9041718778560542e-05, + "loss": 3.9081, + "step": 1890816 + }, + { + "epoch": 1.02, + "learning_rate": 1.903333283105002e-05, + "loss": 3.8994, + "step": 1891328 + }, + { + "epoch": 1.02, + "learning_rate": 1.90249468835395e-05, + "loss": 3.8963, + "step": 1891840 + }, + { + "epoch": 1.02, + "learning_rate": 1.901656093602898e-05, + "loss": 3.8828, + "step": 1892352 + }, + { + "epoch": 1.02, + "learning_rate": 1.900819136732219e-05, + "loss": 3.8947, + "step": 1892864 + }, + { + "epoch": 1.02, + "learning_rate": 1.899980541981167e-05, + "loss": 3.8849, + "step": 1893376 + }, + { + "epoch": 1.02, + "learning_rate": 1.899141947230115e-05, + "loss": 3.8926, + "step": 1893888 + }, + { + "epoch": 1.02, + "learning_rate": 1.898303352479063e-05, + "loss": 3.8842, + "step": 1894400 + }, + { + "epoch": 1.02, + "learning_rate": 1.897464757728011e-05, + "loss": 3.889, + "step": 1894912 + }, + { + "epoch": 1.02, + "learning_rate": 1.896626162976959e-05, + "loss": 3.8937, + "step": 1895424 + }, + { + "epoch": 1.02, + "learning_rate": 1.895787568225907e-05, + "loss": 3.8905, + "step": 1895936 + }, + { + "epoch": 1.02, + "learning_rate": 1.8949506113552283e-05, + "loss": 3.8959, + "step": 1896448 + }, + { + "epoch": 1.02, + "learning_rate": 1.8941120166041763e-05, + "loss": 3.8911, + "step": 1896960 + }, + { + "epoch": 1.02, + "learning_rate": 1.8932734218531243e-05, + "loss": 3.8821, + "step": 1897472 + }, + { + "epoch": 1.02, + "learning_rate": 1.8924364649824452e-05, + "loss": 3.897, + "step": 1897984 + }, + { + "epoch": 1.02, + "learning_rate": 1.8915978702313932e-05, + "loss": 3.8952, + "step": 1898496 + }, + { + "epoch": 1.02, + "learning_rate": 1.8907592754803412e-05, + "loss": 3.9073, + "step": 1899008 + }, + { + "epoch": 1.02, + "learning_rate": 1.8899206807292892e-05, + "loss": 3.8854, + "step": 1899520 + }, + { + "epoch": 1.02, + "learning_rate": 1.8890820859782372e-05, + "loss": 3.9014, + "step": 1900032 + }, + { + "epoch": 1.02, + "learning_rate": 1.8882434912271852e-05, + "loss": 3.8931, + "step": 1900544 + }, + { + "epoch": 1.02, + "learning_rate": 1.8874048964761332e-05, + "loss": 3.9009, + "step": 1901056 + }, + { + "epoch": 1.02, + "learning_rate": 1.8865663017250812e-05, + "loss": 3.8959, + "step": 1901568 + }, + { + "epoch": 1.02, + "learning_rate": 1.8857277069740292e-05, + "loss": 3.8937, + "step": 1902080 + }, + { + "epoch": 1.02, + "learning_rate": 1.88489075010335e-05, + "loss": 3.887, + "step": 1902592 + }, + { + "epoch": 1.02, + "learning_rate": 1.8840521553522984e-05, + "loss": 3.9025, + "step": 1903104 + }, + { + "epoch": 1.02, + "learning_rate": 1.8832135606012464e-05, + "loss": 3.8832, + "step": 1903616 + }, + { + "epoch": 1.02, + "learning_rate": 1.8823749658501944e-05, + "loss": 3.889, + "step": 1904128 + }, + { + "epoch": 1.02, + "learning_rate": 1.8815363710991424e-05, + "loss": 3.8957, + "step": 1904640 + }, + { + "epoch": 1.02, + "learning_rate": 1.8806977763480904e-05, + "loss": 3.9003, + "step": 1905152 + }, + { + "epoch": 1.02, + "learning_rate": 1.879859181597038e-05, + "loss": 3.8892, + "step": 1905664 + }, + { + "epoch": 1.02, + "learning_rate": 1.8790222247263593e-05, + "loss": 3.8902, + "step": 1906176 + }, + { + "epoch": 1.02, + "learning_rate": 1.8781852678556806e-05, + "loss": 3.8972, + "step": 1906688 + }, + { + "epoch": 1.02, + "learning_rate": 1.8773466731046286e-05, + "loss": 3.8918, + "step": 1907200 + }, + { + "epoch": 1.02, + "learning_rate": 1.8765080783535766e-05, + "loss": 3.8977, + "step": 1907712 + }, + { + "epoch": 1.03, + "eval_loss": 3.9879937171936035, + "eval_runtime": 302.2892, + "eval_samples_per_second": 1262.337, + "eval_steps_per_second": 39.449, + "step": 1907987 + }, + { + "epoch": 0.0, + "learning_rate": 1.8756694836025246e-05, + "loss": 3.8743, + "step": 1908224 + }, + { + "epoch": 0.0, + "learning_rate": 1.8748308888514726e-05, + "loss": 3.8882, + "step": 1908736 + }, + { + "epoch": 0.0, + "learning_rate": 1.8739922941004202e-05, + "loss": 3.8913, + "step": 1909248 + }, + { + "epoch": 0.0, + "learning_rate": 1.8731536993493686e-05, + "loss": 3.8946, + "step": 1909760 + }, + { + "epoch": 0.0, + "learning_rate": 1.8723151045983165e-05, + "loss": 3.9014, + "step": 1910272 + }, + { + "epoch": 0.0, + "learning_rate": 1.8714765098472645e-05, + "loss": 3.8885, + "step": 1910784 + }, + { + "epoch": 0.0, + "learning_rate": 1.8706379150962125e-05, + "loss": 3.894, + "step": 1911296 + }, + { + "epoch": 0.0, + "learning_rate": 1.8697993203451605e-05, + "loss": 3.8893, + "step": 1911808 + }, + { + "epoch": 0.0, + "learning_rate": 1.8689607255941085e-05, + "loss": 3.8869, + "step": 1912320 + }, + { + "epoch": 0.0, + "learning_rate": 1.8681221308430562e-05, + "loss": 3.8902, + "step": 1912832 + }, + { + "epoch": 0.0, + "learning_rate": 1.8672835360920042e-05, + "loss": 3.8975, + "step": 1913344 + }, + { + "epoch": 0.0, + "learning_rate": 1.8664449413409525e-05, + "loss": 3.897, + "step": 1913856 + }, + { + "epoch": 0.0, + "learning_rate": 1.8656079844702734e-05, + "loss": 3.8918, + "step": 1914368 + }, + { + "epoch": 0.0, + "learning_rate": 1.8647693897192214e-05, + "loss": 3.8777, + "step": 1914880 + }, + { + "epoch": 0.0, + "learning_rate": 1.8639307949681694e-05, + "loss": 3.8962, + "step": 1915392 + }, + { + "epoch": 0.0, + "learning_rate": 1.8630922002171174e-05, + "loss": 3.882, + "step": 1915904 + }, + { + "epoch": 0.0, + "learning_rate": 1.8622536054660654e-05, + "loss": 3.8911, + "step": 1916416 + }, + { + "epoch": 0.0, + "learning_rate": 1.8614166485953867e-05, + "loss": 3.8892, + "step": 1916928 + }, + { + "epoch": 0.0, + "learning_rate": 1.8605780538443347e-05, + "loss": 3.888, + "step": 1917440 + }, + { + "epoch": 0.0, + "learning_rate": 1.8597394590932826e-05, + "loss": 3.8981, + "step": 1917952 + }, + { + "epoch": 0.0, + "learning_rate": 1.8589008643422306e-05, + "loss": 3.9013, + "step": 1918464 + }, + { + "epoch": 0.0, + "learning_rate": 1.8580622695911786e-05, + "loss": 3.8963, + "step": 1918976 + }, + { + "epoch": 0.0, + "learning_rate": 1.8572236748401266e-05, + "loss": 3.8905, + "step": 1919488 + }, + { + "epoch": 0.0, + "learning_rate": 1.8563850800890746e-05, + "loss": 3.8901, + "step": 1920000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8555464853380226e-05, + "loss": 3.8944, + "step": 1920512 + }, + { + "epoch": 0.0, + "learning_rate": 1.8547078905869706e-05, + "loss": 3.8898, + "step": 1921024 + }, + { + "epoch": 0.0, + "learning_rate": 1.8538692958359186e-05, + "loss": 3.8901, + "step": 1921536 + }, + { + "epoch": 0.0, + "learning_rate": 1.8530307010848666e-05, + "loss": 3.8873, + "step": 1922048 + }, + { + "epoch": 0.0, + "learning_rate": 1.8521921063338146e-05, + "loss": 3.8875, + "step": 1922560 + }, + { + "epoch": 0.0, + "learning_rate": 1.8513551494631355e-05, + "loss": 3.8941, + "step": 1923072 + }, + { + "epoch": 0.01, + "learning_rate": 1.850516554712084e-05, + "loss": 3.8817, + "step": 1923584 + }, + { + "epoch": 0.01, + "learning_rate": 1.849677959961032e-05, + "loss": 3.8986, + "step": 1924096 + }, + { + "epoch": 0.01, + "learning_rate": 1.84883936520998e-05, + "loss": 3.8982, + "step": 1924608 + }, + { + "epoch": 0.01, + "learning_rate": 1.8480024083393008e-05, + "loss": 3.898, + "step": 1925120 + }, + { + "epoch": 0.01, + "learning_rate": 1.8471638135882487e-05, + "loss": 3.8884, + "step": 1925632 + }, + { + "epoch": 0.01, + "learning_rate": 1.84632685671757e-05, + "loss": 3.8962, + "step": 1926144 + }, + { + "epoch": 0.01, + "learning_rate": 1.845488261966518e-05, + "loss": 3.8921, + "step": 1926656 + }, + { + "epoch": 0.01, + "learning_rate": 1.844649667215466e-05, + "loss": 3.8876, + "step": 1927168 + }, + { + "epoch": 0.01, + "learning_rate": 1.843811072464414e-05, + "loss": 3.8838, + "step": 1927680 + }, + { + "epoch": 0.01, + "learning_rate": 1.842972477713362e-05, + "loss": 3.8801, + "step": 1928192 + }, + { + "epoch": 0.01, + "learning_rate": 1.842135520842683e-05, + "loss": 3.8883, + "step": 1928704 + }, + { + "epoch": 0.01, + "learning_rate": 1.841296926091631e-05, + "loss": 3.8947, + "step": 1929216 + }, + { + "epoch": 0.01, + "learning_rate": 1.840458331340579e-05, + "loss": 3.8859, + "step": 1929728 + }, + { + "epoch": 0.01, + "learning_rate": 1.8396197365895272e-05, + "loss": 3.8867, + "step": 1930240 + }, + { + "epoch": 0.01, + "learning_rate": 1.838781141838475e-05, + "loss": 3.9007, + "step": 1930752 + }, + { + "epoch": 0.01, + "learning_rate": 1.837942547087423e-05, + "loss": 3.8906, + "step": 1931264 + }, + { + "epoch": 0.01, + "learning_rate": 1.837103952336371e-05, + "loss": 3.8992, + "step": 1931776 + }, + { + "epoch": 0.01, + "learning_rate": 1.836265357585319e-05, + "loss": 3.8841, + "step": 1932288 + }, + { + "epoch": 0.01, + "learning_rate": 1.835426762834267e-05, + "loss": 3.8641, + "step": 1932800 + }, + { + "epoch": 0.01, + "learning_rate": 1.834588168083215e-05, + "loss": 3.9057, + "step": 1933312 + }, + { + "epoch": 0.01, + "learning_rate": 1.833751211212536e-05, + "loss": 3.8868, + "step": 1933824 + }, + { + "epoch": 0.01, + "learning_rate": 1.832912616461484e-05, + "loss": 3.8905, + "step": 1934336 + }, + { + "epoch": 0.01, + "learning_rate": 1.832074021710432e-05, + "loss": 3.886, + "step": 1934848 + }, + { + "epoch": 0.01, + "learning_rate": 1.83123542695938e-05, + "loss": 3.8884, + "step": 1935360 + }, + { + "epoch": 0.01, + "learning_rate": 1.8303968322083277e-05, + "loss": 3.8776, + "step": 1935872 + }, + { + "epoch": 0.01, + "learning_rate": 1.8295582374572757e-05, + "loss": 3.88, + "step": 1936384 + }, + { + "epoch": 0.01, + "learning_rate": 1.828719642706224e-05, + "loss": 3.8826, + "step": 1936896 + }, + { + "epoch": 0.01, + "learning_rate": 1.827881047955172e-05, + "loss": 3.8836, + "step": 1937408 + }, + { + "epoch": 0.01, + "learning_rate": 1.827044091084493e-05, + "loss": 3.8983, + "step": 1937920 + }, + { + "epoch": 0.01, + "learning_rate": 1.826205496333441e-05, + "loss": 3.883, + "step": 1938432 + }, + { + "epoch": 0.01, + "learning_rate": 1.825366901582389e-05, + "loss": 3.8817, + "step": 1938944 + }, + { + "epoch": 0.01, + "learning_rate": 1.824528306831337e-05, + "loss": 3.9023, + "step": 1939456 + }, + { + "epoch": 0.01, + "learning_rate": 1.823689712080285e-05, + "loss": 3.8683, + "step": 1939968 + }, + { + "epoch": 0.01, + "learning_rate": 1.8228511173292333e-05, + "loss": 3.8785, + "step": 1940480 + }, + { + "epoch": 0.01, + "learning_rate": 1.8220141604585542e-05, + "loss": 3.8888, + "step": 1940992 + }, + { + "epoch": 0.01, + "learning_rate": 1.8211755657075022e-05, + "loss": 3.8885, + "step": 1941504 + }, + { + "epoch": 0.01, + "learning_rate": 1.8203369709564502e-05, + "loss": 3.8817, + "step": 1942016 + }, + { + "epoch": 0.01, + "learning_rate": 1.8194983762053982e-05, + "loss": 3.8876, + "step": 1942528 + }, + { + "epoch": 0.01, + "learning_rate": 1.818659781454346e-05, + "loss": 3.8661, + "step": 1943040 + }, + { + "epoch": 0.01, + "learning_rate": 1.8178228245836674e-05, + "loss": 3.8776, + "step": 1943552 + }, + { + "epoch": 0.01, + "learning_rate": 1.8169842298326154e-05, + "loss": 3.8992, + "step": 1944064 + }, + { + "epoch": 0.01, + "learning_rate": 1.8161456350815634e-05, + "loss": 3.8817, + "step": 1944576 + }, + { + "epoch": 0.01, + "learning_rate": 1.815307040330511e-05, + "loss": 3.8979, + "step": 1945088 + }, + { + "epoch": 0.01, + "learning_rate": 1.814468445579459e-05, + "loss": 3.8938, + "step": 1945600 + }, + { + "epoch": 0.01, + "learning_rate": 1.8136314887087803e-05, + "loss": 3.9036, + "step": 1946112 + }, + { + "epoch": 0.01, + "learning_rate": 1.8127928939577283e-05, + "loss": 3.8789, + "step": 1946624 + }, + { + "epoch": 0.01, + "learning_rate": 1.8119542992066763e-05, + "loss": 3.8926, + "step": 1947136 + }, + { + "epoch": 0.01, + "learning_rate": 1.8111157044556243e-05, + "loss": 3.8896, + "step": 1947648 + }, + { + "epoch": 0.01, + "learning_rate": 1.8102771097045723e-05, + "loss": 3.8774, + "step": 1948160 + }, + { + "epoch": 0.01, + "learning_rate": 1.8094385149535203e-05, + "loss": 3.8996, + "step": 1948672 + }, + { + "epoch": 0.01, + "learning_rate": 1.8085999202024683e-05, + "loss": 3.8877, + "step": 1949184 + }, + { + "epoch": 0.01, + "learning_rate": 1.8077613254514163e-05, + "loss": 3.8924, + "step": 1949696 + }, + { + "epoch": 0.01, + "learning_rate": 1.8069243685807375e-05, + "loss": 3.8961, + "step": 1950208 + }, + { + "epoch": 0.01, + "learning_rate": 1.8060874117100585e-05, + "loss": 3.875, + "step": 1950720 + }, + { + "epoch": 0.01, + "learning_rate": 1.8052488169590064e-05, + "loss": 3.8766, + "step": 1951232 + }, + { + "epoch": 0.01, + "learning_rate": 1.8044102222079544e-05, + "loss": 3.8812, + "step": 1951744 + }, + { + "epoch": 0.01, + "learning_rate": 1.8035716274569024e-05, + "loss": 3.8902, + "step": 1952256 + }, + { + "epoch": 0.01, + "learning_rate": 1.8027330327058504e-05, + "loss": 3.8884, + "step": 1952768 + }, + { + "epoch": 0.01, + "learning_rate": 1.8018944379547988e-05, + "loss": 3.8814, + "step": 1953280 + }, + { + "epoch": 0.02, + "learning_rate": 1.8010558432037464e-05, + "loss": 3.8829, + "step": 1953792 + }, + { + "epoch": 0.02, + "learning_rate": 1.8002172484526944e-05, + "loss": 3.889, + "step": 1954304 + }, + { + "epoch": 0.02, + "learning_rate": 1.7993802915820157e-05, + "loss": 3.8811, + "step": 1954816 + }, + { + "epoch": 0.02, + "learning_rate": 1.7985416968309637e-05, + "loss": 3.8814, + "step": 1955328 + }, + { + "epoch": 0.02, + "learning_rate": 1.7977031020799117e-05, + "loss": 3.9021, + "step": 1955840 + }, + { + "epoch": 0.02, + "learning_rate": 1.7968645073288597e-05, + "loss": 3.8968, + "step": 1956352 + }, + { + "epoch": 0.02, + "learning_rate": 1.796027550458181e-05, + "loss": 3.8934, + "step": 1956864 + }, + { + "epoch": 0.02, + "learning_rate": 1.795188955707129e-05, + "loss": 3.879, + "step": 1957376 + }, + { + "epoch": 0.02, + "learning_rate": 1.7943503609560766e-05, + "loss": 3.888, + "step": 1957888 + }, + { + "epoch": 0.02, + "learning_rate": 1.7935117662050246e-05, + "loss": 3.8817, + "step": 1958400 + }, + { + "epoch": 0.02, + "learning_rate": 1.7926748093343458e-05, + "loss": 3.9018, + "step": 1958912 + }, + { + "epoch": 0.02, + "learning_rate": 1.7918362145832938e-05, + "loss": 3.8879, + "step": 1959424 + }, + { + "epoch": 0.02, + "learning_rate": 1.7909976198322418e-05, + "loss": 3.8835, + "step": 1959936 + }, + { + "epoch": 0.02, + "learning_rate": 1.7901590250811898e-05, + "loss": 3.8895, + "step": 1960448 + }, + { + "epoch": 0.02, + "learning_rate": 1.7893204303301378e-05, + "loss": 3.8963, + "step": 1960960 + }, + { + "epoch": 0.02, + "learning_rate": 1.7884834734594587e-05, + "loss": 3.8776, + "step": 1961472 + }, + { + "epoch": 0.02, + "learning_rate": 1.787644878708407e-05, + "loss": 3.8872, + "step": 1961984 + }, + { + "epoch": 0.02, + "learning_rate": 1.786806283957355e-05, + "loss": 3.8756, + "step": 1962496 + }, + { + "epoch": 0.02, + "learning_rate": 1.785967689206303e-05, + "loss": 3.8819, + "step": 1963008 + }, + { + "epoch": 0.02, + "learning_rate": 1.785129094455251e-05, + "loss": 3.8795, + "step": 1963520 + }, + { + "epoch": 0.02, + "learning_rate": 1.784290499704199e-05, + "loss": 3.883, + "step": 1964032 + }, + { + "epoch": 0.02, + "learning_rate": 1.78345354283352e-05, + "loss": 3.8859, + "step": 1964544 + }, + { + "epoch": 0.02, + "learning_rate": 1.782614948082468e-05, + "loss": 3.8887, + "step": 1965056 + }, + { + "epoch": 0.02, + "learning_rate": 1.781776353331416e-05, + "loss": 3.8808, + "step": 1965568 + }, + { + "epoch": 0.02, + "learning_rate": 1.7809377585803642e-05, + "loss": 3.88, + "step": 1966080 + }, + { + "epoch": 0.02, + "learning_rate": 1.780100801709685e-05, + "loss": 3.8963, + "step": 1966592 + }, + { + "epoch": 0.02, + "learning_rate": 1.779262206958633e-05, + "loss": 3.9003, + "step": 1967104 + }, + { + "epoch": 0.02, + "learning_rate": 1.778423612207581e-05, + "loss": 3.8909, + "step": 1967616 + }, + { + "epoch": 0.02, + "learning_rate": 1.777585017456529e-05, + "loss": 3.8945, + "step": 1968128 + }, + { + "epoch": 0.02, + "learning_rate": 1.776746422705477e-05, + "loss": 3.8799, + "step": 1968640 + }, + { + "epoch": 0.02, + "learning_rate": 1.7759094658347984e-05, + "loss": 3.89, + "step": 1969152 + }, + { + "epoch": 0.02, + "learning_rate": 1.7750708710837464e-05, + "loss": 3.8835, + "step": 1969664 + }, + { + "epoch": 0.02, + "learning_rate": 1.7742322763326944e-05, + "loss": 3.8814, + "step": 1970176 + }, + { + "epoch": 0.02, + "learning_rate": 1.773393681581642e-05, + "loss": 3.8826, + "step": 1970688 + }, + { + "epoch": 0.02, + "learning_rate": 1.77255508683059e-05, + "loss": 3.8848, + "step": 1971200 + }, + { + "epoch": 0.02, + "learning_rate": 1.7717181299599113e-05, + "loss": 3.887, + "step": 1971712 + }, + { + "epoch": 0.02, + "learning_rate": 1.7708795352088593e-05, + "loss": 3.8836, + "step": 1972224 + }, + { + "epoch": 0.02, + "learning_rate": 1.7700409404578073e-05, + "loss": 3.89, + "step": 1972736 + }, + { + "epoch": 0.02, + "learning_rate": 1.7692023457067553e-05, + "loss": 3.8882, + "step": 1973248 + }, + { + "epoch": 0.02, + "learning_rate": 1.7683637509557033e-05, + "loss": 3.8797, + "step": 1973760 + }, + { + "epoch": 0.02, + "learning_rate": 1.7675251562046513e-05, + "loss": 3.8891, + "step": 1974272 + }, + { + "epoch": 0.02, + "learning_rate": 1.7666881993339725e-05, + "loss": 3.895, + "step": 1974784 + }, + { + "epoch": 0.02, + "learning_rate": 1.7658496045829205e-05, + "loss": 3.8982, + "step": 1975296 + }, + { + "epoch": 0.02, + "learning_rate": 1.7650110098318685e-05, + "loss": 3.8824, + "step": 1975808 + }, + { + "epoch": 0.02, + "learning_rate": 1.7641724150808165e-05, + "loss": 3.8973, + "step": 1976320 + }, + { + "epoch": 0.02, + "learning_rate": 1.7633338203297645e-05, + "loss": 3.8914, + "step": 1976832 + }, + { + "epoch": 0.02, + "learning_rate": 1.7624952255787125e-05, + "loss": 3.8952, + "step": 1977344 + }, + { + "epoch": 0.02, + "learning_rate": 1.76165663082766e-05, + "loss": 3.8914, + "step": 1977856 + }, + { + "epoch": 0.02, + "learning_rate": 1.760818036076608e-05, + "loss": 3.887, + "step": 1978368 + }, + { + "epoch": 0.02, + "learning_rate": 1.7599810792059297e-05, + "loss": 3.886, + "step": 1978880 + }, + { + "epoch": 0.02, + "learning_rate": 1.7591441223352506e-05, + "loss": 3.8956, + "step": 1979392 + }, + { + "epoch": 0.02, + "learning_rate": 1.7583055275841986e-05, + "loss": 3.8752, + "step": 1979904 + }, + { + "epoch": 0.02, + "learning_rate": 1.7574669328331466e-05, + "loss": 3.8885, + "step": 1980416 + }, + { + "epoch": 0.02, + "learning_rate": 1.7566283380820946e-05, + "loss": 3.8923, + "step": 1980928 + }, + { + "epoch": 0.02, + "learning_rate": 1.7557897433310426e-05, + "loss": 3.8938, + "step": 1981440 + }, + { + "epoch": 0.02, + "learning_rate": 1.7549511485799906e-05, + "loss": 3.8847, + "step": 1981952 + }, + { + "epoch": 0.02, + "learning_rate": 1.7541125538289386e-05, + "loss": 3.8849, + "step": 1982464 + }, + { + "epoch": 0.02, + "learning_rate": 1.7532755969582595e-05, + "loss": 3.894, + "step": 1982976 + }, + { + "epoch": 0.02, + "learning_rate": 1.7524386400875808e-05, + "loss": 3.8883, + "step": 1983488 + }, + { + "epoch": 0.02, + "learning_rate": 1.7516000453365288e-05, + "loss": 3.8925, + "step": 1984000 + }, + { + "epoch": 0.03, + "eval_loss": 3.9862301349639893, + "eval_runtime": 291.0925, + "eval_samples_per_second": 1310.893, + "eval_steps_per_second": 40.966, + "step": 1984307 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 8.193761142752175e+17, + "trial_name": null, + "trial_params": null +}