diff --git "a/checkpoint-1297440/trainer_state.json" "b/checkpoint-1297440/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-1297440/trainer_state.json" @@ -0,0 +1,15365 @@ +{ + "best_metric": 4.010347366333008, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-domain/lstm/1/checkpoints/checkpoint-1297440", + "epoch": 0.025000606015738065, + "eval_steps": 10, + "global_step": 1297440, + "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": 10.8197, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 7.5528, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 7.0561, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 6.988, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 6.9411, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 6.8638, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 6.7072, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 6.6023, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 6.5067, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 6.4371, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 6.3821, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 6.3225, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 6.2538, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989098268236324e-05, + "loss": 6.1921, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988259673485272e-05, + "loss": 6.1397, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.98742107873422e-05, + "loss": 6.0809, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986582483983168e-05, + "loss": 6.0353, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985743889232116e-05, + "loss": 5.995, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984905294481064e-05, + "loss": 5.9573, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.9186, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.8836, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.982391148108281e-05, + "loss": 5.8425, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.981552553357229e-05, + "loss": 5.8192, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 5.783, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 5.7615, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790384069844466e-05, + "loss": 5.7324, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9781998122333946e-05, + "loss": 5.7096, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 5.6814, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 5.6558, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 5.6382, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748470711095595e-05, + "loss": 5.6134, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 5.6064, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 5.5742, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.9723329247367764e-05, + "loss": 5.5654, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.9714943299857244e-05, + "loss": 5.5565, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.9706557352346724e-05, + "loss": 5.5338, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 5.5198, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968980183612942e-05, + "loss": 5.485, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 5.4779, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 5.455, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 5.4511, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 5.4318, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 5.4222, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 5.3904, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 5.4006, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962273063484898e-05, + "loss": 5.3891, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 5.38, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 5.3673, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959762192872862e-05, + "loss": 5.3404, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.95892359812181e-05, + "loss": 5.3316, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958085003370758e-05, + "loss": 5.3344, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957246408619706e-05, + "loss": 5.3189, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956407813868654e-05, + "loss": 5.3073, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 5.2821, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 5.2828, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 5.2693, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 5.2947, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522148401133936e-05, + "loss": 5.2472, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 5.2523, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 5.2467, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 5.2257, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 5.2271, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 5.2106, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 5.1959, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 5.1943, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 5.2108, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944672400995045e-05, + "loss": 5.1835, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 5.1748, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 5.1584, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942156616741889e-05, + "loss": 5.1584, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.941318021990837e-05, + "loss": 5.1685, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404794272397856e-05, + "loss": 5.1638, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396408324887336e-05, + "loss": 5.1502, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388022377376816e-05, + "loss": 5.1576, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379636429866296e-05, + "loss": 5.15, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371250482355776e-05, + "loss": 5.1383, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362864534845256e-05, + "loss": 5.1195, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.935447858733473e-05, + "loss": 5.109, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.934609263982421e-05, + "loss": 5.1061, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337723071117425e-05, + "loss": 5.098, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329353502410634e-05, + "loss": 5.0952, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.9320967554900114e-05, + "loss": 5.0912, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.9312581607389594e-05, + "loss": 5.093, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.9304195659879074e-05, + "loss": 5.0833, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929582609117229e-05, + "loss": 5.0581, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.928744014366177e-05, + "loss": 5.0535, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927905419615125e-05, + "loss": 5.0634, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927066824864073e-05, + "loss": 5.065, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.92622823011302e-05, + "loss": 5.0402, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925391273242342e-05, + "loss": 5.0432, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.92455267849129e-05, + "loss": 5.043, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923714083740238e-05, + "loss": 5.0279, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922875488989185e-05, + "loss": 5.0217, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922036894238133e-05, + "loss": 5.0204, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921198299487081e-05, + "loss": 5.0101, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920359704736029e-05, + "loss": 5.0149, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919521109984978e-05, + "loss": 5.0038, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918684153114299e-05, + "loss": 4.9882, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917845558363247e-05, + "loss": 4.988, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917006963612195e-05, + "loss": 4.9869, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.9161700067415156e-05, + "loss": 4.9838, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.9153314119904636e-05, + "loss": 4.9838, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.9144928172394116e-05, + "loss": 4.9734, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136542224883596e-05, + "loss": 4.9698, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128156277373076e-05, + "loss": 4.9615, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119786708666285e-05, + "loss": 4.9412, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.9111400761155765e-05, + "loss": 4.9458, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.9103014813645245e-05, + "loss": 4.9436, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909462886613473e-05, + "loss": 4.9415, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908624291862421e-05, + "loss": 4.9325, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907785697111369e-05, + "loss": 4.9277, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.90694874024069e-05, + "loss": 4.9212, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906110145489638e-05, + "loss": 4.921, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905271550738586e-05, + "loss": 4.9153, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904432955987534e-05, + "loss": 4.9151, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903594361236482e-05, + "loss": 4.9074, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902757404365803e-05, + "loss": 4.9044, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901918809614751e-05, + "loss": 4.9063, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901080214863699e-05, + "loss": 4.8977, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.900241620112647e-05, + "loss": 4.9033, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994046632419686e-05, + "loss": 4.903, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985660684909166e-05, + "loss": 4.8858, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977274737398646e-05, + "loss": 4.8916, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968888789888125e-05, + "loss": 4.8765, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960502842377605e-05, + "loss": 4.8826, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952116894867085e-05, + "loss": 4.8576, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943730947356565e-05, + "loss": 4.8691, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.893534499984604e-05, + "loss": 4.8542, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892695905233552e-05, + "loss": 4.8566, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918573104825e-05, + "loss": 4.8378, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.891018715731448e-05, + "loss": 4.8689, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890181758860769e-05, + "loss": 4.856, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889343164109717e-05, + "loss": 4.8439, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888504569358665e-05, + "loss": 4.8417, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.8876659746076134e-05, + "loss": 4.8379, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.8868273798565614e-05, + "loss": 4.8464, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885990422985882e-05, + "loss": 4.8405, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.88515182823483e-05, + "loss": 4.8302, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884313233483778e-05, + "loss": 4.8344, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883474638732726e-05, + "loss": 4.8193, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882636043981674e-05, + "loss": 4.8295, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881797449230622e-05, + "loss": 4.8135, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.88095885447957e-05, + "loss": 4.8142, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880120259728518e-05, + "loss": 4.8106, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879283302857839e-05, + "loss": 4.7999, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878444708106787e-05, + "loss": 4.8022, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877606113355735e-05, + "loss": 4.8025, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876767518604683e-05, + "loss": 4.7974, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875928923853632e-05, + "loss": 4.8013, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875091966982953e-05, + "loss": 4.7897, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.75280237197876, + "eval_runtime": 299.9661, + "eval_samples_per_second": 1272.114, + "eval_steps_per_second": 39.754, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.874253372231901e-05, + "loss": 4.7784, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873414777480849e-05, + "loss": 4.7745, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.872576182729797e-05, + "loss": 4.791, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.871739225859118e-05, + "loss": 4.7733, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709006311080657e-05, + "loss": 4.7904, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700620363570137e-05, + "loss": 4.7598, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.8692250794863346e-05, + "loss": 4.7729, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683864847352826e-05, + "loss": 4.7509, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.867549527864604e-05, + "loss": 4.7632, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.866710933113552e-05, + "loss": 4.7606, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.8658723383625e-05, + "loss": 4.765, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865033743611448e-05, + "loss": 4.7602, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.864195148860396e-05, + "loss": 4.7426, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.863356554109344e-05, + "loss": 4.7447, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862517959358292e-05, + "loss": 4.7376, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.86167936460724e-05, + "loss": 4.7349, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.8608407698561874e-05, + "loss": 4.7435, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.8600021751051354e-05, + "loss": 4.7403, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.8591635803540834e-05, + "loss": 4.735, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.8583249856030314e-05, + "loss": 4.7498, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.857488028732352e-05, + "loss": 4.7238, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.856649433981301e-05, + "loss": 4.7326, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.855810839230249e-05, + "loss": 4.7259, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.854972244479197e-05, + "loss": 4.7356, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.854135287608518e-05, + "loss": 4.7115, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.853296692857466e-05, + "loss": 4.7195, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.852458098106414e-05, + "loss": 4.7098, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851619503355362e-05, + "loss": 4.7168, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.85078090860431e-05, + "loss": 4.6981, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.849943951733631e-05, + "loss": 4.7007, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849105356982579e-05, + "loss": 4.7112, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848266762231527e-05, + "loss": 4.7037, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847429805360848e-05, + "loss": 4.7031, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.8465912106097964e-05, + "loss": 4.7096, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.8457526158587444e-05, + "loss": 4.7014, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.8449140211076924e-05, + "loss": 4.7008, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.8440754263566404e-05, + "loss": 4.6825, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.8432368316055884e-05, + "loss": 4.6913, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.8423982368545363e-05, + "loss": 4.6766, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.8415596421034843e-05, + "loss": 4.6862, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840721047352432e-05, + "loss": 4.6825, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.839884090481753e-05, + "loss": 4.6801, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839047133611074e-05, + "loss": 4.6655, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838210176740395e-05, + "loss": 4.681, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.837371581989343e-05, + "loss": 4.6802, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836532987238292e-05, + "loss": 4.6745, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.83569439248724e-05, + "loss": 4.6787, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834855797736188e-05, + "loss": 4.6486, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834017202985136e-05, + "loss": 4.651, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.833178608234084e-05, + "loss": 4.6691, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.832340013483032e-05, + "loss": 4.6566, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.83150141873198e-05, + "loss": 4.6554, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.830662823980928e-05, + "loss": 4.6363, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.829824229229876e-05, + "loss": 4.6432, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.828985634478824e-05, + "loss": 4.6375, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.828147039727771e-05, + "loss": 4.6637, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273100828570926e-05, + "loss": 4.6335, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.8264731259864135e-05, + "loss": 4.6423, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.8256345312353615e-05, + "loss": 4.6469, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8247959364843095e-05, + "loss": 4.6269, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823957341733258e-05, + "loss": 4.6338, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823118746982206e-05, + "loss": 4.6271, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.8222801522311535e-05, + "loss": 4.6169, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.8214415574801015e-05, + "loss": 4.623, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820604600609423e-05, + "loss": 4.6379, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.819767643738744e-05, + "loss": 4.6253, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.818929048987692e-05, + "loss": 4.6127, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.81809045423664e-05, + "loss": 4.6129, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817251859485588e-05, + "loss": 4.6123, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816413264734535e-05, + "loss": 4.6294, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.815574669983483e-05, + "loss": 4.6304, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.814736075232432e-05, + "loss": 4.6192, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.81389748048138e-05, + "loss": 4.6323, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.813058885730328e-05, + "loss": 4.6282, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812220290979276e-05, + "loss": 4.6253, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811383334108597e-05, + "loss": 4.6093, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810544739357545e-05, + "loss": 4.6084, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809706144606493e-05, + "loss": 4.604, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.808867549855441e-05, + "loss": 4.6057, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808028955104389e-05, + "loss": 4.599, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807190360353337e-05, + "loss": 4.6066, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806353403482658e-05, + "loss": 4.6126, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805514808731606e-05, + "loss": 4.6009, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804677851860927e-05, + "loss": 4.5865, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803839257109875e-05, + "loss": 4.5863, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.803000662358823e-05, + "loss": 4.5921, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.802162067607771e-05, + "loss": 4.6047, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801323472856719e-05, + "loss": 4.5861, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.800484878105667e-05, + "loss": 4.592, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.799646283354615e-05, + "loss": 4.5928, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.798807688603563e-05, + "loss": 4.5862, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.797969093852511e-05, + "loss": 4.5809, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.797130499101459e-05, + "loss": 4.5788, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.796291904350407e-05, + "loss": 4.5789, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.7954533095993546e-05, + "loss": 4.5817, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.794616352728676e-05, + "loss": 4.5816, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.793777757977624e-05, + "loss": 4.5663, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792942438987319e-05, + "loss": 4.5732, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792103844236267e-05, + "loss": 4.5696, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.791265249485215e-05, + "loss": 4.5779, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.790426654734163e-05, + "loss": 4.5713, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.7895880599831107e-05, + "loss": 4.5705, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.7887511031124316e-05, + "loss": 4.5683, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.7879125083613796e-05, + "loss": 4.5661, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.7870739136103276e-05, + "loss": 4.5503, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.7862353188592756e-05, + "loss": 4.5529, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.7853967241082236e-05, + "loss": 4.5589, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.7845581293571715e-05, + "loss": 4.5553, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.7837195346061195e-05, + "loss": 4.5532, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.7828809398550675e-05, + "loss": 4.5479, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.7820423451040155e-05, + "loss": 4.5461, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.7812037503529635e-05, + "loss": 4.5483, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.7803651556019115e-05, + "loss": 4.5457, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.7795265608508595e-05, + "loss": 4.5446, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.7786879660998075e-05, + "loss": 4.5474, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.7778493713487555e-05, + "loss": 4.5475, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.7770124144780764e-05, + "loss": 4.5474, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.7761738197270244e-05, + "loss": 4.5426, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.7753352249759724e-05, + "loss": 4.5516, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.7744966302249204e-05, + "loss": 4.5519, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.7736580354738684e-05, + "loss": 4.5364, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.7728194407228164e-05, + "loss": 4.547, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.7719808459717644e-05, + "loss": 4.5356, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771145526981459e-05, + "loss": 4.5435, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770306932230407e-05, + "loss": 4.5182, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769468337479355e-05, + "loss": 4.5362, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768629742728303e-05, + "loss": 4.5191, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767791147977251e-05, + "loss": 4.5269, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766952553226199e-05, + "loss": 4.5137, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766113958475147e-05, + "loss": 4.5434, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765275363724095e-05, + "loss": 4.5355, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764436768973043e-05, + "loss": 4.5269, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.76359817422199e-05, + "loss": 4.52, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762761217351312e-05, + "loss": 4.5235, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.76192262260026e-05, + "loss": 4.5316, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761084027849208e-05, + "loss": 4.5267, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.7602470709785293e-05, + "loss": 4.5219, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.7594084762274773e-05, + "loss": 4.5245, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758569881476425e-05, + "loss": 4.5147, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.757731286725373e-05, + "loss": 4.5282, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.7568926919743206e-05, + "loss": 4.5105, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.7560540972232686e-05, + "loss": 4.5144, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.7552155024722166e-05, + "loss": 4.5098, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.7543769077211646e-05, + "loss": 4.5072, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.7535399508504855e-05, + "loss": 4.5106, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.7527013560994335e-05, + "loss": 4.5094, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.7518627613483815e-05, + "loss": 4.5104, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.7510241665973295e-05, + "loss": 4.5083, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.750185571846278e-05, + "loss": 4.5051, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.473276138305664, + "eval_runtime": 299.3602, + "eval_samples_per_second": 1274.689, + "eval_steps_per_second": 39.835, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.749346977095226e-05, + "loss": 4.4963, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748508382344174e-05, + "loss": 4.4896, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747669787593122e-05, + "loss": 4.5098, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.74683119284207e-05, + "loss": 4.4938, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.745992598091018e-05, + "loss": 4.5152, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.745154003339966e-05, + "loss": 4.4834, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.744315408588914e-05, + "loss": 4.4972, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.743476813837862e-05, + "loss": 4.4806, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.7426382190868095e-05, + "loss": 4.4951, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.7417996243357575e-05, + "loss": 4.4927, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.7409610295847055e-05, + "loss": 4.4959, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.7401224348336535e-05, + "loss": 4.4934, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739285477962975e-05, + "loss": 4.4763, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738446883211923e-05, + "loss": 4.4864, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737608288460871e-05, + "loss": 4.4787, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736769693709819e-05, + "loss": 4.4765, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735931098958767e-05, + "loss": 4.4796, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735092504207715e-05, + "loss": 4.4828, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734253909456663e-05, + "loss": 4.4771, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733416952585984e-05, + "loss": 4.4976, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732578357834932e-05, + "loss": 4.4722, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.73173976308388e-05, + "loss": 4.4783, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.730901168332828e-05, + "loss": 4.4768, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730064211462149e-05, + "loss": 4.4863, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729225616711097e-05, + "loss": 4.4663, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728387021960045e-05, + "loss": 4.4764, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727548427208993e-05, + "loss": 4.4667, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.7267098324579415e-05, + "loss": 4.4724, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.7258712377068895e-05, + "loss": 4.4592, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.7250326429558375e-05, + "loss": 4.4607, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.7241940482047855e-05, + "loss": 4.4708, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.7233554534537335e-05, + "loss": 4.4698, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.722516858702681e-05, + "loss": 4.4695, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721678263951629e-05, + "loss": 4.4709, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720839669200577e-05, + "loss": 4.4652, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720001074449525e-05, + "loss": 4.471, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719165755459219e-05, + "loss": 4.4514, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.718327160708167e-05, + "loss": 4.4671, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.717488565957115e-05, + "loss": 4.4497, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716649971206063e-05, + "loss": 4.4593, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.715811376455011e-05, + "loss": 4.4548, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.714972781703959e-05, + "loss": 4.4587, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714135824833281e-05, + "loss": 4.451, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.713297230082228e-05, + "loss": 4.4519, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712458635331176e-05, + "loss": 4.4604, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711620040580124e-05, + "loss": 4.4539, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710781445829072e-05, + "loss": 4.4566, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.70994285107802e-05, + "loss": 4.4388, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.709104256326968e-05, + "loss": 4.4302, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.708265661575916e-05, + "loss": 4.4497, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.707428704705237e-05, + "loss": 4.4437, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706590109954185e-05, + "loss": 4.4441, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705751515203134e-05, + "loss": 4.4266, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704912920452082e-05, + "loss": 4.4315, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.70407432570103e-05, + "loss": 4.4333, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.7032373688303506e-05, + "loss": 4.4467, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.7024004119596715e-05, + "loss": 4.4254, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015618172086195e-05, + "loss": 4.4361, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.7007232224575675e-05, + "loss": 4.4395, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.6998846277065155e-05, + "loss": 4.4255, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.6990460329554635e-05, + "loss": 4.4296, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.6982074382044115e-05, + "loss": 4.4257, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.6973688434533595e-05, + "loss": 4.4144, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.6965302487023075e-05, + "loss": 4.4278, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.6956916539512555e-05, + "loss": 4.4291, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.6948530592002035e-05, + "loss": 4.4324, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.6940144644491515e-05, + "loss": 4.4124, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.6931758696980995e-05, + "loss": 4.4179, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692338912827421e-05, + "loss": 4.4147, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691503593837115e-05, + "loss": 4.4406, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690664999086063e-05, + "loss": 4.4284, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689826404335011e-05, + "loss": 4.4276, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.688987809583959e-05, + "loss": 4.4402, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688149214832907e-05, + "loss": 4.4381, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687310620081855e-05, + "loss": 4.4311, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.686472025330803e-05, + "loss": 4.42, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.685633430579751e-05, + "loss": 4.4218, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6847964737090725e-05, + "loss": 4.4195, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.6839578789580204e-05, + "loss": 4.4155, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.6831192842069684e-05, + "loss": 4.4156, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.6822806894559164e-05, + "loss": 4.4187, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.6814420947048644e-05, + "loss": 4.4277, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.680603499953812e-05, + "loss": 4.4171, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.67976490520276e-05, + "loss": 4.4073, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678929586212454e-05, + "loss": 4.4018, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678090991461402e-05, + "loss": 4.4119, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.67725239671035e-05, + "loss": 4.4196, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676413801959298e-05, + "loss": 4.4099, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675575207208246e-05, + "loss": 4.4093, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674736612457194e-05, + "loss": 4.4183, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.673898017706142e-05, + "loss": 4.4003, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.67305942295509e-05, + "loss": 4.4078, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.672220828204038e-05, + "loss": 4.4013, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671382233452986e-05, + "loss": 4.4081, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670545276582307e-05, + "loss": 4.4086, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.669706681831255e-05, + "loss": 4.4033, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.668868087080203e-05, + "loss": 4.396, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668029492329151e-05, + "loss": 4.4039, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667192535458472e-05, + "loss": 4.3956, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.66635394070742e-05, + "loss": 4.411, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665515345956368e-05, + "loss": 4.4014, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664676751205316e-05, + "loss": 4.4011, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.6638397943346376e-05, + "loss": 4.3939, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.6630011995835856e-05, + "loss": 4.4029, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.6621626048325336e-05, + "loss": 4.38, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.6613240100814816e-05, + "loss": 4.3871, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.6604854153304296e-05, + "loss": 4.3911, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.6596484584597505e-05, + "loss": 4.3921, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.6588098637086985e-05, + "loss": 4.3852, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.6579712689576465e-05, + "loss": 4.3868, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.6571326742065945e-05, + "loss": 4.3795, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.6562940794555425e-05, + "loss": 4.3884, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.6554571225848634e-05, + "loss": 4.3846, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.6546185278338114e-05, + "loss": 4.3784, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.65377993308276e-05, + "loss": 4.3933, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652941338331708e-05, + "loss": 4.3899, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.652104381461029e-05, + "loss": 4.3906, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651265786709977e-05, + "loss": 4.382, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650427191958925e-05, + "loss": 4.3916, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649588597207873e-05, + "loss": 4.3899, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648750002456821e-05, + "loss": 4.3812, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647911407705769e-05, + "loss": 4.3968, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.64707445083509e-05, + "loss": 4.3766, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.646235856084038e-05, + "loss": 4.3873, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645397261332986e-05, + "loss": 4.3664, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644558666581934e-05, + "loss": 4.3818, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.6437217097112554e-05, + "loss": 4.3637, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6428831149602034e-05, + "loss": 4.3751, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.6420445202091514e-05, + "loss": 4.3626, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.6412059254580994e-05, + "loss": 4.3882, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.64036896858742e-05, + "loss": 4.3794, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.639530373836368e-05, + "loss": 4.3806, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.638691779085316e-05, + "loss": 4.3701, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637853184334264e-05, + "loss": 4.371, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637016227463585e-05, + "loss": 4.3875, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636177632712533e-05, + "loss": 4.3763, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.635339037961481e-05, + "loss": 4.3706, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.634500443210429e-05, + "loss": 4.3818, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633661848459377e-05, + "loss": 4.3697, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632823253708325e-05, + "loss": 4.3763, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.631986296837647e-05, + "loss": 4.3643, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631147702086595e-05, + "loss": 4.3705, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.630309107335542e-05, + "loss": 4.365, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.62947051258449e-05, + "loss": 4.3671, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.628631917833438e-05, + "loss": 4.3623, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.627793323082386e-05, + "loss": 4.3707, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626954728331334e-05, + "loss": 4.3613, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626117771460655e-05, + "loss": 4.3661, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625279176709603e-05, + "loss": 4.3636, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 4.33865213394165, + "eval_runtime": 441.3072, + "eval_samples_per_second": 864.683, + "eval_steps_per_second": 27.022, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624440581958551e-05, + "loss": 4.3604, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623601987207499e-05, + "loss": 4.3506, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.6227650303368205e-05, + "loss": 4.369, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.6219264355857685e-05, + "loss": 4.3514, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.6210878408347165e-05, + "loss": 4.3795, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.6202492460836645e-05, + "loss": 4.3438, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.6194106513326125e-05, + "loss": 4.3578, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.6185720565815605e-05, + "loss": 4.3428, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.6177334618305085e-05, + "loss": 4.3586, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.6168948670794565e-05, + "loss": 4.3574, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.6160562723284045e-05, + "loss": 4.3551, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.6152176775773525e-05, + "loss": 4.3586, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.6143807207066734e-05, + "loss": 4.3401, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.6135421259556214e-05, + "loss": 4.351, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.6127035312045694e-05, + "loss": 4.3465, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.6118649364535174e-05, + "loss": 4.3428, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.6110263417024654e-05, + "loss": 4.3447, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.610187746951414e-05, + "loss": 4.3496, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.609350790080735e-05, + "loss": 4.3474, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.608512195329683e-05, + "loss": 4.3607, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.607673600578631e-05, + "loss": 4.3416, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.606835005827578e-05, + "loss": 4.347, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.6059980489569e-05, + "loss": 4.3458, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.605159454205848e-05, + "loss": 4.357, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.604320859454796e-05, + "loss": 4.3357, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.603482264703743e-05, + "loss": 4.349, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.602643669952691e-05, + "loss": 4.3379, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.601805075201639e-05, + "loss": 4.3401, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.600966480450588e-05, + "loss": 4.3302, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.600129523579909e-05, + "loss": 4.3387, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.599290928828857e-05, + "loss": 4.3396, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598452334077805e-05, + "loss": 4.3455, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.5976153772071257e-05, + "loss": 4.3401, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.5967767824560737e-05, + "loss": 4.3467, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.5959381877050217e-05, + "loss": 4.3372, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.5950995929539696e-05, + "loss": 4.3454, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.5942626360832906e-05, + "loss": 4.3309, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.5934240413322386e-05, + "loss": 4.3403, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.5925854465811865e-05, + "loss": 4.3245, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.5917468518301345e-05, + "loss": 4.3348, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.590908257079083e-05, + "loss": 4.3329, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590069662328031e-05, + "loss": 4.3381, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.589231067576979e-05, + "loss": 4.3287, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.5883941107063e-05, + "loss": 4.3326, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.587555515955248e-05, + "loss": 4.3367, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.586716921204196e-05, + "loss": 4.3318, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585878326453144e-05, + "loss": 4.3347, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585039731702092e-05, + "loss": 4.3238, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.584202774831413e-05, + "loss": 4.3055, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583364180080361e-05, + "loss": 4.3315, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582525585329309e-05, + "loss": 4.3237, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.581686990578257e-05, + "loss": 4.3202, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.580848395827205e-05, + "loss": 4.3154, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.580009801076153e-05, + "loss": 4.3139, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.5791712063251017e-05, + "loss": 4.3124, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.5783326115740497e-05, + "loss": 4.3287, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.577494016822997e-05, + "loss": 4.311, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.576655422071945e-05, + "loss": 4.3166, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.5758201030816395e-05, + "loss": 4.3271, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.5749815083305875e-05, + "loss": 4.3106, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.5741429135795355e-05, + "loss": 4.3112, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.5733043188284835e-05, + "loss": 4.3155, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.5724673619578044e-05, + "loss": 4.2949, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.5716287672067524e-05, + "loss": 4.3137, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.5707901724557004e-05, + "loss": 4.317, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.5699515777046484e-05, + "loss": 4.3153, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.5691129829535963e-05, + "loss": 4.3003, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.5682743882025443e-05, + "loss": 4.3079, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.5674357934514923e-05, + "loss": 4.3011, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.56659719870044e-05, + "loss": 4.3213, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.565758603949388e-05, + "loss": 4.3183, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.564920009198336e-05, + "loss": 4.3176, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.564081414447284e-05, + "loss": 4.3264, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.563242819696232e-05, + "loss": 4.3275, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.562405862825553e-05, + "loss": 4.3244, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.561567268074501e-05, + "loss": 4.3032, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.560728673323449e-05, + "loss": 4.311, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.559890078572397e-05, + "loss": 4.314, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.559051483821345e-05, + "loss": 4.3038, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.558214526950667e-05, + "loss": 4.3121, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557375932199615e-05, + "loss": 4.3044, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556537337448563e-05, + "loss": 4.3161, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.555698742697511e-05, + "loss": 4.3119, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.554860147946459e-05, + "loss": 4.2922, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.554021553195407e-05, + "loss": 4.2975, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553182958444355e-05, + "loss": 4.3057, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552346001573676e-05, + "loss": 4.3102, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551507406822624e-05, + "loss": 4.3024, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.5506704499519446e-05, + "loss": 4.3022, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.5498334930812655e-05, + "loss": 4.3093, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.548994898330214e-05, + "loss": 4.2966, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548156303579162e-05, + "loss": 4.2974, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.54731770882811e-05, + "loss": 4.3008, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546479114077058e-05, + "loss": 4.3037, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.545640519326006e-05, + "loss": 4.3055, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.544801924574954e-05, + "loss": 4.2972, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.543963329823902e-05, + "loss": 4.2868, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.54312473507285e-05, + "loss": 4.3044, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542286140321798e-05, + "loss": 4.2906, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.5414475455707455e-05, + "loss": 4.3115, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.5406089508196934e-05, + "loss": 4.3005, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.5397703560686414e-05, + "loss": 4.2969, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.5389317613175894e-05, + "loss": 4.2904, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.5380931665665374e-05, + "loss": 4.303, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.5372545718154854e-05, + "loss": 4.2778, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.536417614944807e-05, + "loss": 4.2883, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.535579020193755e-05, + "loss": 4.2844, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.534740425442703e-05, + "loss": 4.2919, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.533901830691651e-05, + "loss": 4.2839, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.533064873820972e-05, + "loss": 4.2907, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.53222627906992e-05, + "loss": 4.2825, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.531387684318868e-05, + "loss": 4.281, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.530549089567816e-05, + "loss": 4.2878, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.529710494816764e-05, + "loss": 4.2784, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.528871900065712e-05, + "loss": 4.2965, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.528034943195033e-05, + "loss": 4.2897, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.527196348443981e-05, + "loss": 4.2923, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.5263577536929295e-05, + "loss": 4.2852, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.5255191589418775e-05, + "loss": 4.2916, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.5246805641908255e-05, + "loss": 4.2942, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.5238419694397735e-05, + "loss": 4.2834, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.5230033746887215e-05, + "loss": 4.2964, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.5221647799376694e-05, + "loss": 4.2799, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.5213278230669904e-05, + "loss": 4.2876, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.5204892283159384e-05, + "loss": 4.2749, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.5196506335648863e-05, + "loss": 4.2839, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.5188120388138343e-05, + "loss": 4.2674, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.517975081943155e-05, + "loss": 4.2799, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.517136487192103e-05, + "loss": 4.2688, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516297892441051e-05, + "loss": 4.2891, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515460935570373e-05, + "loss": 4.2817, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.514622340819321e-05, + "loss": 4.2869, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513783746068269e-05, + "loss": 4.2751, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.512945151317217e-05, + "loss": 4.2819, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512106556566164e-05, + "loss": 4.2913, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.511267961815112e-05, + "loss": 4.281, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.51042936706406e-05, + "loss": 4.2796, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.509590772313008e-05, + "loss": 4.2878, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.508752177561956e-05, + "loss": 4.2757, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.507913582810904e-05, + "loss": 4.2866, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.507074988059852e-05, + "loss": 4.2681, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.5062363933088e-05, + "loss": 4.2809, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.505399436438121e-05, + "loss": 4.2736, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.50456084168707e-05, + "loss": 4.2728, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.5037238848163906e-05, + "loss": 4.2764, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.5028852900653386e-05, + "loss": 4.2723, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.5020466953142866e-05, + "loss": 4.2717, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.5012097384436075e-05, + "loss": 4.2718, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.5003711436925555e-05, + "loss": 4.2773, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 4.2552080154418945, + "eval_runtime": 319.5257, + "eval_samples_per_second": 1194.242, + "eval_steps_per_second": 37.321, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.4995325489415035e-05, + "loss": 4.2664, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.4986939541904515e-05, + "loss": 4.2591, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.4978553594393995e-05, + "loss": 4.2786, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.4970167646883475e-05, + "loss": 4.262, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.4961781699372955e-05, + "loss": 4.2869, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.4953395751862435e-05, + "loss": 4.2636, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.4945009804351915e-05, + "loss": 4.2636, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.4936623856841395e-05, + "loss": 4.2536, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.492823790933088e-05, + "loss": 4.2689, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.4919851961820354e-05, + "loss": 4.2739, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.4911466014309834e-05, + "loss": 4.2663, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.4903080066799314e-05, + "loss": 4.2655, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489471049809253e-05, + "loss": 4.2559, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.4886324550582003e-05, + "loss": 4.2643, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.4877938603071483e-05, + "loss": 4.2606, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.486955265556096e-05, + "loss": 4.2521, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486118308685418e-05, + "loss": 4.2591, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485279713934365e-05, + "loss": 4.265, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.484441119183313e-05, + "loss": 4.259, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483602524432262e-05, + "loss": 4.2706, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.48276392968121e-05, + "loss": 4.2611, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481925334930158e-05, + "loss": 4.2641, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481086740179106e-05, + "loss": 4.2603, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480249783308427e-05, + "loss": 4.2708, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479411188557375e-05, + "loss": 4.2509, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478572593806323e-05, + "loss": 4.2617, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477733999055271e-05, + "loss": 4.2549, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476895404304219e-05, + "loss": 4.2512, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.47605844743354e-05, + "loss": 4.2465, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475219852682488e-05, + "loss": 4.2525, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474381257931436e-05, + "loss": 4.2579, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473542663180384e-05, + "loss": 4.261, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472704068429332e-05, + "loss": 4.2595, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.4718654736782804e-05, + "loss": 4.2592, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.4710268789272283e-05, + "loss": 4.2552, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.4701882841761763e-05, + "loss": 4.2593, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.4693496894251243e-05, + "loss": 4.2519, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468514370434818e-05, + "loss": 4.2532, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467675775683766e-05, + "loss": 4.2438, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466837180932714e-05, + "loss": 4.2524, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466000224062035e-05, + "loss": 4.2506, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.465161629310983e-05, + "loss": 4.2569, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464323034559931e-05, + "loss": 4.2475, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463484439808879e-05, + "loss": 4.2509, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462645845057827e-05, + "loss": 4.2599, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461807250306775e-05, + "loss": 4.2489, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.460968655555724e-05, + "loss": 4.2511, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460130060804672e-05, + "loss": 4.2422, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.459291466053619e-05, + "loss": 4.226, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.4584545091829406e-05, + "loss": 4.2535, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.4576159144318886e-05, + "loss": 4.2453, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.4567773196808366e-05, + "loss": 4.2426, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.455938724929784e-05, + "loss": 4.2299, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.455100130178732e-05, + "loss": 4.2367, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.45426153542768e-05, + "loss": 4.2298, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.453422940676628e-05, + "loss": 4.2505, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.452585983805949e-05, + "loss": 4.232, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.4517473890548975e-05, + "loss": 4.2352, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.4509087943038455e-05, + "loss": 4.2498, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.4500701995527935e-05, + "loss": 4.2322, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.4492316048017415e-05, + "loss": 4.2351, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.4483930100506895e-05, + "loss": 4.2398, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.4475544152996375e-05, + "loss": 4.2173, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.4467158205485855e-05, + "loss": 4.2377, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.4458788636779064e-05, + "loss": 4.2358, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.4450402689268544e-05, + "loss": 4.241, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.4442016741758024e-05, + "loss": 4.2238, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.4433630794247504e-05, + "loss": 4.2324, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442526122554071e-05, + "loss": 4.221, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441687527803019e-05, + "loss": 4.2493, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440848933051967e-05, + "loss": 4.2416, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440010338300916e-05, + "loss": 4.2387, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439171743549864e-05, + "loss": 4.2506, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438336424559558e-05, + "loss": 4.2463, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437497829808506e-05, + "loss": 4.2563, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436659235057454e-05, + "loss": 4.2293, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435820640306402e-05, + "loss": 4.2355, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.43498204555535e-05, + "loss": 4.2399, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434143450804298e-05, + "loss": 4.2263, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.4333064939336186e-05, + "loss": 4.2397, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.4324678991825666e-05, + "loss": 4.2311, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.4316293044315146e-05, + "loss": 4.2397, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.4307907096804626e-05, + "loss": 4.2364, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.429952114929411e-05, + "loss": 4.2208, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.429113520178359e-05, + "loss": 4.2323, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.428274925427307e-05, + "loss": 4.2219, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427436330676255e-05, + "loss": 4.2377, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.4265977359252026e-05, + "loss": 4.2301, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.425762416934897e-05, + "loss": 4.2276, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.424925460064218e-05, + "loss": 4.2352, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424086865313166e-05, + "loss": 4.2314, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.423248270562114e-05, + "loss": 4.2204, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422409675811062e-05, + "loss": 4.2248, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.42157108106001e-05, + "loss": 4.2345, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420732486308958e-05, + "loss": 4.2328, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419893891557907e-05, + "loss": 4.2276, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.419055296806855e-05, + "loss": 4.2163, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.418216702055803e-05, + "loss": 4.2287, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.41737810730475e-05, + "loss": 4.2201, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.416539512553698e-05, + "loss": 4.2366, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415700917802646e-05, + "loss": 4.2323, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.414862323051594e-05, + "loss": 4.2253, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414023728300542e-05, + "loss": 4.2207, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413186771429863e-05, + "loss": 4.2345, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412348176678811e-05, + "loss": 4.2045, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411511219808132e-05, + "loss": 4.2191, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.4106726250570805e-05, + "loss": 4.2112, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.4098340303060284e-05, + "loss": 4.2267, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.4089954355549764e-05, + "loss": 4.2112, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.4081584786842974e-05, + "loss": 4.2175, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.4073198839332453e-05, + "loss": 4.2142, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.4064812891821933e-05, + "loss": 4.2116, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.4056426944311413e-05, + "loss": 4.217, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404804099680089e-05, + "loss": 4.2122, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.40396714280941e-05, + "loss": 4.2266, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403128548058358e-05, + "loss": 4.2224, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402289953307306e-05, + "loss": 4.2211, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401451358556254e-05, + "loss": 4.2145, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400612763805202e-05, + "loss": 4.2254, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.39977416905415e-05, + "loss": 4.2216, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398937212183472e-05, + "loss": 4.2146, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.39809861743242e-05, + "loss": 4.2301, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397260022681368e-05, + "loss": 4.2131, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396421427930316e-05, + "loss": 4.2177, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395582833179264e-05, + "loss": 4.2064, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394744238428212e-05, + "loss": 4.2174, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.39390564367716e-05, + "loss": 4.2044, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393067048926108e-05, + "loss": 4.2096, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392228454175056e-05, + "loss": 4.2068, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.391389859424003e-05, + "loss": 4.2207, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.390551264672951e-05, + "loss": 4.2146, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.389714307802273e-05, + "loss": 4.2183, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.388875713051221e-05, + "loss": 4.2066, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388037118300169e-05, + "loss": 4.2178, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387198523549117e-05, + "loss": 4.2242, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.3863599287980647e-05, + "loss": 4.2166, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385524609807759e-05, + "loss": 4.2136, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.384686015056707e-05, + "loss": 4.221, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.383847420305655e-05, + "loss": 4.2098, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.383008825554603e-05, + "loss": 4.2199, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.3821702308035505e-05, + "loss": 4.2044, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.3813316360524985e-05, + "loss": 4.2154, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.3804930413014465e-05, + "loss": 4.2095, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.3796544465503944e-05, + "loss": 4.2094, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378817489679716e-05, + "loss": 4.2098, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.377978894928664e-05, + "loss": 4.2059, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.377140300177612e-05, + "loss": 4.208, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.37630170542656e-05, + "loss": 4.2026, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.375463110675508e-05, + "loss": 4.2163, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 4.199158191680908, + "eval_runtime": 282.6669, + "eval_samples_per_second": 1349.967, + "eval_steps_per_second": 42.187, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.374624515924456e-05, + "loss": 4.2054, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.373785921173404e-05, + "loss": 4.1942, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.372948964302725e-05, + "loss": 4.2161, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.372110369551673e-05, + "loss": 4.2024, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.371271774800621e-05, + "loss": 4.2203, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.370433180049569e-05, + "loss": 4.203, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369594585298517e-05, + "loss": 4.1926, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368755990547465e-05, + "loss": 4.1973, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.367917395796413e-05, + "loss": 4.1995, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.367078801045361e-05, + "loss": 4.21, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.3662418441746825e-05, + "loss": 4.2026, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.3654032494236305e-05, + "loss": 4.2057, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.3645662925529514e-05, + "loss": 4.1958, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.3637276978018994e-05, + "loss": 4.1975, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.3628891030508474e-05, + "loss": 4.203, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.3620505082997954e-05, + "loss": 4.1886, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.3612119135487434e-05, + "loss": 4.1961, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.360374956678064e-05, + "loss": 4.2009, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.359536361927012e-05, + "loss": 4.2005, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.35869776717596e-05, + "loss": 4.2069, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.357859172424908e-05, + "loss": 4.2008, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.357020577673856e-05, + "loss": 4.2031, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.356181982922804e-05, + "loss": 4.1977, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.355345026052126e-05, + "loss": 4.2058, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.354506431301074e-05, + "loss": 4.1899, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.353667836550022e-05, + "loss": 4.206, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.352829241798969e-05, + "loss": 4.1887, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.351990647047917e-05, + "loss": 4.1906, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.351153690177239e-05, + "loss": 4.1877, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.350315095426187e-05, + "loss": 4.1927, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.349476500675134e-05, + "loss": 4.1979, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.3486395438044556e-05, + "loss": 4.198, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.3478009490534036e-05, + "loss": 4.2031, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.3469623543023516e-05, + "loss": 4.2038, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.3461237595512996e-05, + "loss": 4.1907, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.3452851648002476e-05, + "loss": 4.1992, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.3444465700491956e-05, + "loss": 4.1936, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.3436079752981436e-05, + "loss": 4.1918, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.3427693805470916e-05, + "loss": 4.1863, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.3419324236764125e-05, + "loss": 4.1893, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.341095466805734e-05, + "loss": 4.1944, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.3402568720546814e-05, + "loss": 4.1992, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.3394182773036294e-05, + "loss": 4.1858, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.3385796825525774e-05, + "loss": 4.1915, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.3377410878015254e-05, + "loss": 4.1984, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.3369024930504734e-05, + "loss": 4.193, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.3360638982994214e-05, + "loss": 4.1944, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.33522530354837e-05, + "loss": 4.185, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.334386708797318e-05, + "loss": 4.1657, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.333548114046266e-05, + "loss": 4.2, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.332709519295214e-05, + "loss": 4.185, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.331872562424535e-05, + "loss": 4.1865, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331033967673483e-05, + "loss": 4.1781, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.330195372922431e-05, + "loss": 4.1713, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.329356778171379e-05, + "loss": 4.1756, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.3285198213007e-05, + "loss": 4.187, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.327681226549648e-05, + "loss": 4.1765, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.326842631798596e-05, + "loss": 4.1816, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.326004037047544e-05, + "loss": 4.1891, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.325165442296492e-05, + "loss": 4.1763, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.32432684754544e-05, + "loss": 4.177, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.3234882527943885e-05, + "loss": 4.1858, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.322649658043336e-05, + "loss": 4.1647, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.321811063292284e-05, + "loss": 4.1763, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.320972468541232e-05, + "loss": 4.1776, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.32013387379018e-05, + "loss": 4.1867, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.319295279039128e-05, + "loss": 4.1643, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.318459960048822e-05, + "loss": 4.1763, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.31762136529777e-05, + "loss": 4.1648, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.3167827705467176e-05, + "loss": 4.19, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.3159441757956656e-05, + "loss": 4.187, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.315107218924987e-05, + "loss": 4.1821, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.314268624173935e-05, + "loss": 4.1916, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.313430029422883e-05, + "loss": 4.1929, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.312593072552205e-05, + "loss": 4.2012, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.311754477801153e-05, + "loss": 4.1773, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.3109158830501e-05, + "loss": 4.1804, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.310077288299048e-05, + "loss": 4.1813, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.309238693547996e-05, + "loss": 4.1675, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.308400098796944e-05, + "loss": 4.1863, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.307561504045892e-05, + "loss": 4.1753, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.30672290929484e-05, + "loss": 4.1857, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.305884314543788e-05, + "loss": 4.1817, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.305045719792736e-05, + "loss": 4.1654, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.3042087629220577e-05, + "loss": 4.1781, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.3033701681710057e-05, + "loss": 4.1676, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.3025315734199536e-05, + "loss": 4.1832, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.3016929786689016e-05, + "loss": 4.1789, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.3008560217982226e-05, + "loss": 4.1681, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.3000174270471705e-05, + "loss": 4.1866, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.2991788322961185e-05, + "loss": 4.1746, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.2983402375450665e-05, + "loss": 4.1682, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.2975016427940145e-05, + "loss": 4.1705, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.2966630480429625e-05, + "loss": 4.1819, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.2958244532919105e-05, + "loss": 4.1759, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.2949858585408585e-05, + "loss": 4.1796, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.2941472637898065e-05, + "loss": 4.1603, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.2933103069191274e-05, + "loss": 4.1745, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.292473350048449e-05, + "loss": 4.1682, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.291634755297397e-05, + "loss": 4.1823, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.290796160546345e-05, + "loss": 4.1808, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.289957565795293e-05, + "loss": 4.1687, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.289118971044241e-05, + "loss": 4.1718, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.288280376293189e-05, + "loss": 4.1787, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.287441781542136e-05, + "loss": 4.1535, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.286603186791084e-05, + "loss": 4.1639, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.285764592040032e-05, + "loss": 4.1595, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.28492599728898e-05, + "loss": 4.1718, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.284087402537928e-05, + "loss": 4.1629, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.283248807786876e-05, + "loss": 4.1683, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.282411850916198e-05, + "loss": 4.1601, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.281574894045519e-05, + "loss": 4.16, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.280736299294467e-05, + "loss": 4.1672, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.279897704543415e-05, + "loss": 4.159, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.279059109792363e-05, + "loss": 4.1747, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.278222152921684e-05, + "loss": 4.1698, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.277385196051005e-05, + "loss": 4.1712, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.276546601299953e-05, + "loss": 4.1632, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.275708006548901e-05, + "loss": 4.1716, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.2748694117978486e-05, + "loss": 4.1727, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.2740308170467966e-05, + "loss": 4.1607, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.2731922222957446e-05, + "loss": 4.1827, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.272353627544693e-05, + "loss": 4.158, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.271515032793641e-05, + "loss": 4.1668, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.270678075922962e-05, + "loss": 4.1547, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.26983948117191e-05, + "loss": 4.1689, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.269000886420858e-05, + "loss": 4.1516, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.268162291669806e-05, + "loss": 4.1612, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.267323696918754e-05, + "loss": 4.1523, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.266485102167702e-05, + "loss": 4.1747, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.26564650741665e-05, + "loss": 4.1628, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264807912665598e-05, + "loss": 4.1701, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.263970955794919e-05, + "loss": 4.1552, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.263132361043867e-05, + "loss": 4.1686, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.262293766292815e-05, + "loss": 4.1729, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.2614568094221366e-05, + "loss": 4.1671, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.2606182146710846e-05, + "loss": 4.1666, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.2597796199200326e-05, + "loss": 4.1665, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.2589410251689806e-05, + "loss": 4.1616, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.2581024304179286e-05, + "loss": 4.1713, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.2572638356668766e-05, + "loss": 4.156, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.2564252409158246e-05, + "loss": 4.1637, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.2555882840451455e-05, + "loss": 4.1598, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.2547496892940935e-05, + "loss": 4.1584, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.2539110945430415e-05, + "loss": 4.1614, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.2530724997919895e-05, + "loss": 4.1514, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.2522339050409375e-05, + "loss": 4.1684, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.2513969481702584e-05, + "loss": 4.1502, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.250558353419207e-05, + "loss": 4.1685, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 4.158098220825195, + "eval_runtime": 281.9106, + "eval_samples_per_second": 1353.589, + "eval_steps_per_second": 42.301, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.249719758668155e-05, + "loss": 4.1576, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.2488811639171024e-05, + "loss": 4.1452, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.2480425691660504e-05, + "loss": 4.1621, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.2472039744149984e-05, + "loss": 4.1559, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.2463653796639464e-05, + "loss": 4.1668, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.2455267849128943e-05, + "loss": 4.1554, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.2446881901618423e-05, + "loss": 4.1463, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.24384959541079e-05, + "loss": 4.1465, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243011000659738e-05, + "loss": 4.1551, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.242172405908686e-05, + "loss": 4.1617, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241333811157634e-05, + "loss": 4.1561, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240495216406582e-05, + "loss": 4.1535, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239658259535903e-05, + "loss": 4.1536, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238819664784852e-05, + "loss": 4.1485, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.2379810700338e-05, + "loss": 4.1515, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237142475282748e-05, + "loss": 4.1391, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236303880531696e-05, + "loss": 4.1506, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.235465285780644e-05, + "loss": 4.1518, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.234626691029591e-05, + "loss": 4.1529, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233788096278539e-05, + "loss": 4.1595, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.232949501527487e-05, + "loss": 4.159, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232112544656809e-05, + "loss": 4.1523, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.231273949905756e-05, + "loss": 4.1488, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230435355154704e-05, + "loss": 4.1622, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.229598398284026e-05, + "loss": 4.1388, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.228759803532974e-05, + "loss": 4.1611, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227921208781922e-05, + "loss": 4.1441, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.22708261403087e-05, + "loss": 4.1427, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226244019279818e-05, + "loss": 4.1408, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.2254054245287657e-05, + "loss": 4.1497, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.2245668297777137e-05, + "loss": 4.1484, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.2237282350266617e-05, + "loss": 4.1537, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.2228912781559826e-05, + "loss": 4.1534, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.2220526834049306e-05, + "loss": 4.1565, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.2212140886538786e-05, + "loss": 4.1443, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.2203754939028265e-05, + "loss": 4.1553, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.2195368991517745e-05, + "loss": 4.15, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.2186983044007225e-05, + "loss": 4.141, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.2178597096496705e-05, + "loss": 4.1418, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.2170211148986185e-05, + "loss": 4.1433, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.21618415802794e-05, + "loss": 4.145, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.215345563276888e-05, + "loss": 4.1559, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.214506968525836e-05, + "loss": 4.1402, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.213668373774784e-05, + "loss": 4.1437, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.212829779023732e-05, + "loss": 4.1565, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.211992822153053e-05, + "loss": 4.1448, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.211154227402001e-05, + "loss": 4.1541, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210317270531322e-05, + "loss": 4.1427, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.20947867578027e-05, + "loss": 4.1122, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208640081029218e-05, + "loss": 4.1576, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207801486278166e-05, + "loss": 4.1395, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.206962891527114e-05, + "loss": 4.1416, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.2061242967760626e-05, + "loss": 4.1336, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.20528570202501e-05, + "loss": 4.1222, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204447107273958e-05, + "loss": 4.135, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.2036117882836524e-05, + "loss": 4.1398, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.2027731935326004e-05, + "loss": 4.1343, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.2019345987815484e-05, + "loss": 4.133, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.2010960040304964e-05, + "loss": 4.1482, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.2002574092794444e-05, + "loss": 4.1299, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.1994188145283924e-05, + "loss": 4.129, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.19858021977734e-05, + "loss": 4.1437, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197741625026288e-05, + "loss": 4.1167, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.1969030302752363e-05, + "loss": 4.1308, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.1960644355241843e-05, + "loss": 4.1343, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.1952258407731323e-05, + "loss": 4.1456, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.19438724602208e-05, + "loss": 4.1186, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193550289151401e-05, + "loss": 4.1362, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192711694400349e-05, + "loss": 4.1176, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.191873099649297e-05, + "loss": 4.1475, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191034504898245e-05, + "loss": 4.1447, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.190197548027566e-05, + "loss": 4.1403, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189358953276514e-05, + "loss": 4.1431, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188520358525462e-05, + "loss": 4.1485, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.187683401654783e-05, + "loss": 4.1587, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.1868464447841046e-05, + "loss": 4.1342, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.1860078500330526e-05, + "loss": 4.1379, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.1851692552820006e-05, + "loss": 4.1402, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.1843306605309486e-05, + "loss": 4.1234, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.1834920657798966e-05, + "loss": 4.1385, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.1826534710288446e-05, + "loss": 4.1342, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.1818148762777926e-05, + "loss": 4.1401, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.1809762815267406e-05, + "loss": 4.146, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.1801376867756886e-05, + "loss": 4.1245, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.1792990920246366e-05, + "loss": 4.1292, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.1784604972735846e-05, + "loss": 4.1263, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.1776219025225326e-05, + "loss": 4.1419, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.1767849456518535e-05, + "loss": 4.1332, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.1759463509008015e-05, + "loss": 4.1303, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.1751077561497495e-05, + "loss": 4.1295, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.174269161398698e-05, + "loss": 4.1389, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173432204528019e-05, + "loss": 4.1262, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.172593609776967e-05, + "loss": 4.1272, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171755015025915e-05, + "loss": 4.1442, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170916420274863e-05, + "loss": 4.1321, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170079463404184e-05, + "loss": 4.1354, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169242506533505e-05, + "loss": 4.1198, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.168403911782453e-05, + "loss": 4.1304, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167565317031401e-05, + "loss": 4.1271, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166726722280349e-05, + "loss": 4.1376, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165888127529297e-05, + "loss": 4.1377, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.1650511706586184e-05, + "loss": 4.1332, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.1642125759075664e-05, + "loss": 4.1317, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.1633739811565144e-05, + "loss": 4.1347, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.1625353864054624e-05, + "loss": 4.1135, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.161698429534783e-05, + "loss": 4.1237, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.160859834783731e-05, + "loss": 4.1138, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160021240032679e-05, + "loss": 4.1333, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159182645281627e-05, + "loss": 4.1212, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158344050530575e-05, + "loss": 4.1254, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157507093659896e-05, + "loss": 4.1177, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156668498908844e-05, + "loss": 4.1204, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155829904157792e-05, + "loss": 4.1253, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.15499130940674e-05, + "loss": 4.1179, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154152714655688e-05, + "loss": 4.1291, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153314119904636e-05, + "loss": 4.134, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152475525153584e-05, + "loss": 4.1283, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151638568282906e-05, + "loss": 4.1296, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150799973531853e-05, + "loss": 4.1257, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.149963016661175e-05, + "loss": 4.1304, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149124421910123e-05, + "loss": 4.1264, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.14828582715907e-05, + "loss": 4.1359, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147447232408018e-05, + "loss": 4.119, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.146608637656966e-05, + "loss": 4.1279, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.145770042905914e-05, + "loss": 4.116, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.144931448154863e-05, + "loss": 4.1226, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.144092853403811e-05, + "loss": 4.1161, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.1432558965331316e-05, + "loss": 4.1204, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.1424173017820796e-05, + "loss": 4.1134, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.1415787070310276e-05, + "loss": 4.1307, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.1407401122799756e-05, + "loss": 4.1244, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.1399015175289236e-05, + "loss": 4.1284, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.1390645606582445e-05, + "loss": 4.1158, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.1382259659071925e-05, + "loss": 4.1306, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.1373873711561405e-05, + "loss": 4.1308, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.1365487764050885e-05, + "loss": 4.13, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.1357101816540364e-05, + "loss": 4.1286, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.134873224783358e-05, + "loss": 4.1252, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.134034630032306e-05, + "loss": 4.1254, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133196035281254e-05, + "loss": 4.1346, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132357440530202e-05, + "loss": 4.1145, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.13151884577915e-05, + "loss": 4.1238, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.130680251028098e-05, + "loss": 4.1266, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.129841656277046e-05, + "loss": 4.1226, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.129004699406367e-05, + "loss": 4.1144, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128166104655315e-05, + "loss": 4.1143, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127329147784636e-05, + "loss": 4.1302, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126490553033584e-05, + "loss": 4.1136, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125651958282532e-05, + "loss": 4.1298, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 4.127317905426025, + "eval_runtime": 299.4592, + "eval_samples_per_second": 1274.267, + "eval_steps_per_second": 39.822, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.12481336353148e-05, + "loss": 4.1163, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.123974768780428e-05, + "loss": 4.1069, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.1231378119097494e-05, + "loss": 4.1257, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.1222992171586974e-05, + "loss": 4.1134, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.1214606224076454e-05, + "loss": 4.1264, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.1206220276565934e-05, + "loss": 4.1213, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.1197834329055414e-05, + "loss": 4.111, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.118944838154489e-05, + "loss": 4.1096, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.118106243403437e-05, + "loss": 4.1177, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.117267648652385e-05, + "loss": 4.122, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.116430691781706e-05, + "loss": 4.1159, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.1155920970306536e-05, + "loss": 4.1168, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.114755140159975e-05, + "loss": 4.1134, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.113916545408923e-05, + "loss": 4.1129, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.113077950657871e-05, + "loss": 4.1143, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.112239355906819e-05, + "loss": 4.1037, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.111400761155767e-05, + "loss": 4.1105, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.110562166404715e-05, + "loss": 4.1147, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.109723571653663e-05, + "loss": 4.1151, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.108884976902611e-05, + "loss": 4.1173, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.108048020031932e-05, + "loss": 4.1239, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.10720942528088e-05, + "loss": 4.1176, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.106370830529828e-05, + "loss": 4.1123, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.105532235778776e-05, + "loss": 4.1192, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.104693641027724e-05, + "loss": 4.1066, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.103856684157045e-05, + "loss": 4.1211, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.1030180894059936e-05, + "loss": 4.1054, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.1021794946549416e-05, + "loss": 4.1089, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.1013408999038896e-05, + "loss": 4.1069, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.1005039430332105e-05, + "loss": 4.1088, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.0996653482821585e-05, + "loss": 4.1106, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.0988267535311065e-05, + "loss": 4.1163, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.0979881587800545e-05, + "loss": 4.1146, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.0971495640290025e-05, + "loss": 4.1183, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.0963109692779505e-05, + "loss": 4.1061, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.0954723745268985e-05, + "loss": 4.1215, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.094637055536592e-05, + "loss": 4.1146, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.09379846078554e-05, + "loss": 4.1025, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.092959866034489e-05, + "loss": 4.1085, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.092121271283437e-05, + "loss": 4.108, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.091282676532385e-05, + "loss": 4.108, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.090444081781333e-05, + "loss": 4.1158, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.089607124910654e-05, + "loss": 4.1043, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.088768530159602e-05, + "loss": 4.1076, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.08792993540855e-05, + "loss": 4.1189, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.087091340657498e-05, + "loss": 4.1097, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086252745906446e-05, + "loss": 4.1132, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.085414151155394e-05, + "loss": 4.1098, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084575556404342e-05, + "loss": 4.0758, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.08373696165329e-05, + "loss": 4.1238, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.082900004782611e-05, + "loss": 4.103, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082061410031559e-05, + "loss": 4.1099, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.0812228152805074e-05, + "loss": 4.093, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.0803842205294554e-05, + "loss": 4.0891, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.079547263658776e-05, + "loss": 4.0981, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078708668907724e-05, + "loss": 4.1025, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.077870074156672e-05, + "loss": 4.1032, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.0770314794056196e-05, + "loss": 4.096, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.0761928846545676e-05, + "loss": 4.1172, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.0753542899035156e-05, + "loss": 4.0979, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.0745156951524636e-05, + "loss": 4.0938, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.0736771004014116e-05, + "loss": 4.1089, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.0728401435307325e-05, + "loss": 4.0826, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.072003186660054e-05, + "loss": 4.0915, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071164591909002e-05, + "loss": 4.1031, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.07032599715795e-05, + "loss": 4.1099, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.069487402406898e-05, + "loss": 4.0862, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.06865044553622e-05, + "loss": 4.1004, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.067811850785167e-05, + "loss": 4.0848, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.0669748939144886e-05, + "loss": 4.113, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.0661362991634366e-05, + "loss": 4.1081, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.0652977044123846e-05, + "loss": 4.1046, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.064459109661332e-05, + "loss": 4.1079, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.06362051491028e-05, + "loss": 4.1158, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.062781920159228e-05, + "loss": 4.123, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.0619433254081766e-05, + "loss": 4.1011, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.0611063685374975e-05, + "loss": 4.1032, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.0602677737864455e-05, + "loss": 4.1098, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.0594291790353935e-05, + "loss": 4.0896, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.0585905842843415e-05, + "loss": 4.1018, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.0577519895332895e-05, + "loss": 4.104, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.0569133947822375e-05, + "loss": 4.1063, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.0560748000311855e-05, + "loss": 4.1097, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.0552362052801335e-05, + "loss": 4.0936, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.0543992484094544e-05, + "loss": 4.0917, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.0535606536584024e-05, + "loss": 4.0966, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.0527220589073504e-05, + "loss": 4.1079, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.0518834641562984e-05, + "loss": 4.1014, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.0510448694052463e-05, + "loss": 4.0969, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.0502062746541943e-05, + "loss": 4.0968, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049367679903143e-05, + "loss": 4.1062, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.048529085152091e-05, + "loss": 4.0964, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.047692128281412e-05, + "loss": 4.0938, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.046855171410733e-05, + "loss": 4.1095, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.046016576659681e-05, + "loss": 4.0992, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.045177981908629e-05, + "loss": 4.1, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.044339387157577e-05, + "loss": 4.0905, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.043502430286898e-05, + "loss": 4.0936, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.042663835535846e-05, + "loss": 4.0923, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.041825240784794e-05, + "loss": 4.1089, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.040986646033742e-05, + "loss": 4.1011, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.04014805128269e-05, + "loss": 4.1013, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.0393094565316384e-05, + "loss": 4.0991, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038470861780586e-05, + "loss": 4.0983, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.037632267029534e-05, + "loss": 4.0868, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036795310158855e-05, + "loss": 4.0883, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.035958353288176e-05, + "loss": 4.0821, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.035119758537124e-05, + "loss": 4.1003, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.034281163786072e-05, + "loss": 4.0891, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.033444206915393e-05, + "loss": 4.0892, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.032605612164341e-05, + "loss": 4.0825, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.031767017413289e-05, + "loss": 4.0941, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.030928422662237e-05, + "loss": 4.0916, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.030089827911185e-05, + "loss": 4.0843, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.029251233160133e-05, + "loss": 4.1039, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.028412638409081e-05, + "loss": 4.0969, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.027574043658029e-05, + "loss": 4.0946, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.026735448906977e-05, + "loss": 4.0998, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.025896854155925e-05, + "loss": 4.0929, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.025059897285246e-05, + "loss": 4.0941, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.024221302534194e-05, + "loss": 4.1003, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.023382707783142e-05, + "loss": 4.0999, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.02254411303209e-05, + "loss": 4.089, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.021705518281038e-05, + "loss": 4.0962, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.020866923529986e-05, + "loss": 4.0891, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.0200299666593075e-05, + "loss": 4.0915, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.0191913719082555e-05, + "loss": 4.083, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.0183527771572035e-05, + "loss": 4.0869, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.0175141824061515e-05, + "loss": 4.0827, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.0166755876550995e-05, + "loss": 4.0969, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.0158386307844204e-05, + "loss": 4.0914, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.0150000360333684e-05, + "loss": 4.0977, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.0141614412823164e-05, + "loss": 4.0805, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.0133228465312644e-05, + "loss": 4.1042, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.0124842517802124e-05, + "loss": 4.0954, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011647294909533e-05, + "loss": 4.0991, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.010810338038854e-05, + "loss": 4.0948, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.009971743287803e-05, + "loss": 4.0933, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.009133148536751e-05, + "loss": 4.0907, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008294553785699e-05, + "loss": 4.1022, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.007455959034647e-05, + "loss": 4.085, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006617364283595e-05, + "loss": 4.0944, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005778769532543e-05, + "loss": 4.0936, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.004940174781491e-05, + "loss": 4.0885, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.004101580030439e-05, + "loss": 4.0842, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.003262985279387e-05, + "loss": 4.0816, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.002424390528334e-05, + "loss": 4.0969, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.001585795777282e-05, + "loss": 4.0857, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.000748838906604e-05, + "loss": 4.0974, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 4.103384971618652, + "eval_runtime": 298.7004, + "eval_samples_per_second": 1277.504, + "eval_steps_per_second": 39.923, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.999910244155552e-05, + "loss": 4.083, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999071649404499e-05, + "loss": 4.0824, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998233054653448e-05, + "loss": 4.0866, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997394459902396e-05, + "loss": 4.0855, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996555865151344e-05, + "loss": 4.0962, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995717270400292e-05, + "loss": 4.0883, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.99487867564924e-05, + "loss": 4.0799, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994040080898188e-05, + "loss": 4.0807, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993201486147136e-05, + "loss": 4.0822, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992362891396084e-05, + "loss": 4.0949, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991524296645032e-05, + "loss": 4.0832, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.99068570189398e-05, + "loss": 4.0832, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.9898487450233006e-05, + "loss": 4.0923, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.9890101502722486e-05, + "loss": 4.0743, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.9881715555211966e-05, + "loss": 4.08, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.9873329607701446e-05, + "loss": 4.0768, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.9864943660190926e-05, + "loss": 4.0791, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.985657409148414e-05, + "loss": 4.085, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.984818814397362e-05, + "loss": 4.0844, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.98398021964631e-05, + "loss": 4.0822, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983141624895258e-05, + "loss": 4.0963, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.9823030301442055e-05, + "loss": 4.0859, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.9814644353931535e-05, + "loss": 4.0844, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.9806258406421015e-05, + "loss": 4.0822, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.9797872458910495e-05, + "loss": 4.081, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.9789486511399975e-05, + "loss": 4.0876, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.9781116942693184e-05, + "loss": 4.0774, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.9772730995182664e-05, + "loss": 4.08, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.9764345047672144e-05, + "loss": 4.0721, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.975595910016163e-05, + "loss": 4.08, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.974758953145484e-05, + "loss": 4.0764, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.973920358394432e-05, + "loss": 4.0837, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.97308176364338e-05, + "loss": 4.0888, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972243168892328e-05, + "loss": 4.0891, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.971404574141276e-05, + "loss": 4.0804, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.970565979390224e-05, + "loss": 4.0844, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.969727384639172e-05, + "loss": 4.0873, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.96888878988812e-05, + "loss": 4.0738, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968050195137068e-05, + "loss": 4.0761, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967213238266389e-05, + "loss": 4.0772, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966374643515337e-05, + "loss": 4.0798, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.965536048764285e-05, + "loss": 4.0784, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964697454013233e-05, + "loss": 4.0813, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.9638604971425544e-05, + "loss": 4.0805, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.9630219023915024e-05, + "loss": 4.0857, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.9621833076404504e-05, + "loss": 4.0816, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.9613447128893984e-05, + "loss": 4.0821, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960507756018719e-05, + "loss": 4.0797, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959669161267667e-05, + "loss": 4.0451, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958830566516615e-05, + "loss": 4.092, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.957991971765563e-05, + "loss": 4.071, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.957153377014511e-05, + "loss": 4.0813, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956314782263459e-05, + "loss": 4.0672, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.9554761875124066e-05, + "loss": 4.0611, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.9546375927613546e-05, + "loss": 4.0628, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953800635890676e-05, + "loss": 4.072, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.952962041139624e-05, + "loss": 4.0738, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952123446388572e-05, + "loss": 4.0664, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.95128485163752e-05, + "loss": 4.0837, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950446256886468e-05, + "loss": 4.0699, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949607662135416e-05, + "loss": 4.0652, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948769067384364e-05, + "loss": 4.0783, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.947932110513685e-05, + "loss": 4.0553, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.947093515762633e-05, + "loss": 4.0607, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.946254921011581e-05, + "loss": 4.0745, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.945416326260529e-05, + "loss": 4.0792, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.94457936938985e-05, + "loss": 4.0601, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.9437407746387986e-05, + "loss": 4.07, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.9429021798877466e-05, + "loss": 4.057, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.9420635851366946e-05, + "loss": 4.0794, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.9412249903856426e-05, + "loss": 4.081, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.9403863956345906e-05, + "loss": 4.0748, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.9395494387639115e-05, + "loss": 4.0785, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.9387108440128595e-05, + "loss": 4.0852, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.9378722492618075e-05, + "loss": 4.0953, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.9370336545107555e-05, + "loss": 4.0727, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.9361950597597035e-05, + "loss": 4.073, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.9353564650086515e-05, + "loss": 4.0754, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.9345178702575995e-05, + "loss": 4.0677, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.9336792755065475e-05, + "loss": 4.0712, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.9328423186358684e-05, + "loss": 4.0755, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.93200536176519e-05, + "loss": 4.077, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.931166767014138e-05, + "loss": 4.0856, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.930328172263086e-05, + "loss": 4.0626, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.929489577512034e-05, + "loss": 4.0619, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.928650982760982e-05, + "loss": 4.0651, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.92781238800993e-05, + "loss": 4.082, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.926975431139251e-05, + "loss": 4.0761, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926136836388199e-05, + "loss": 4.0638, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925298241637147e-05, + "loss": 4.0664, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924459646886095e-05, + "loss": 4.0742, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923621052135042e-05, + "loss": 4.0679, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922782457383991e-05, + "loss": 4.0622, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.921943862632939e-05, + "loss": 4.0813, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.9211069057622604e-05, + "loss": 4.0725, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.920268311011208e-05, + "loss": 4.0705, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.919429716260156e-05, + "loss": 4.0643, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918591121509104e-05, + "loss": 4.063, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.917752526758052e-05, + "loss": 4.0664, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.916913932007e-05, + "loss": 4.0775, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.916075337255948e-05, + "loss": 4.0727, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.915236742504896e-05, + "loss": 4.0705, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.9143997856342166e-05, + "loss": 4.0741, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.9135611908831646e-05, + "loss": 4.0663, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.9127225961321126e-05, + "loss": 4.066, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.9118840013810606e-05, + "loss": 4.0573, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.9110454066300086e-05, + "loss": 4.0527, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.91020844975933e-05, + "loss": 4.0743, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.909371492888651e-05, + "loss": 4.0635, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.908532898137599e-05, + "loss": 4.0602, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907694303386547e-05, + "loss": 4.0559, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.906855708635495e-05, + "loss": 4.0594, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.906018751764816e-05, + "loss": 4.0686, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.905180157013764e-05, + "loss": 4.0578, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.904341562262712e-05, + "loss": 4.074, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.90350296751166e-05, + "loss": 4.0681, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.902664372760608e-05, + "loss": 4.068, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.901825778009556e-05, + "loss": 4.0687, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.900987183258504e-05, + "loss": 4.0646, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.9001485885074527e-05, + "loss": 4.0676, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.8993099937564007e-05, + "loss": 4.0733, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.8984730368857216e-05, + "loss": 4.07, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.8976344421346696e-05, + "loss": 4.0641, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.8967958473836176e-05, + "loss": 4.0678, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.8959572526325656e-05, + "loss": 4.0622, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.8951202957618865e-05, + "loss": 4.0615, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.8942817010108345e-05, + "loss": 4.0544, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.8934431062597825e-05, + "loss": 4.061, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.8926045115087304e-05, + "loss": 4.0552, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.8917675546380514e-05, + "loss": 4.0692, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.8909289598869994e-05, + "loss": 4.0618, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890090365135948e-05, + "loss": 4.0749, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889253408265269e-05, + "loss": 4.0529, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888414813514217e-05, + "loss": 4.0729, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887576218763165e-05, + "loss": 4.0686, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886737624012113e-05, + "loss": 4.0707, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885899029261061e-05, + "loss": 4.0687, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885060434510009e-05, + "loss": 4.0658, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.884221839758956e-05, + "loss": 4.0671, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883383245007904e-05, + "loss": 4.0745, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882546288137226e-05, + "loss": 4.0557, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.881707693386173e-05, + "loss": 4.0683, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880872374395868e-05, + "loss": 4.0639, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.880033779644816e-05, + "loss": 4.0607, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.879195184893764e-05, + "loss": 4.0612, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.878356590142712e-05, + "loss": 4.0549, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.87751799539166e-05, + "loss": 4.0709, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876679400640608e-05, + "loss": 4.061, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.8758408058895556e-05, + "loss": 4.0689, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 4.0841264724731445, + "eval_runtime": 297.2551, + "eval_samples_per_second": 1283.716, + "eval_steps_per_second": 40.117, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.8750022111385036e-05, + "loss": 4.0512, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.8741636163874516e-05, + "loss": 4.0564, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.8733250216363996e-05, + "loss": 4.057, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.8724864268853476e-05, + "loss": 4.0601, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.8716478321342956e-05, + "loss": 4.0721, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.870810875263617e-05, + "loss": 4.061, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.869972280512565e-05, + "loss": 4.0562, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.869133685761513e-05, + "loss": 4.0545, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.868295091010461e-05, + "loss": 4.0534, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.867456496259409e-05, + "loss": 4.0683, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.86661953938873e-05, + "loss": 4.0584, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.865780944637678e-05, + "loss": 4.0581, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.864943987766999e-05, + "loss": 4.066, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.864105393015947e-05, + "loss": 4.049, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.863266798264895e-05, + "loss": 4.0532, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.862428203513843e-05, + "loss": 4.0497, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.861589608762791e-05, + "loss": 4.0552, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.860751014011739e-05, + "loss": 4.052, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.859912419260687e-05, + "loss": 4.0608, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.8590738245096356e-05, + "loss": 4.0581, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.8582368676389565e-05, + "loss": 4.0695, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.8573982728879045e-05, + "loss": 4.0576, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.8565596781368525e-05, + "loss": 4.0617, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.8557210833858005e-05, + "loss": 4.0556, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.854885764395494e-05, + "loss": 4.0587, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.854047169644442e-05, + "loss": 4.0618, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.85320857489339e-05, + "loss": 4.05, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852369980142338e-05, + "loss": 4.0595, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.851533023271659e-05, + "loss": 4.0461, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.850694428520608e-05, + "loss": 4.0517, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.849855833769556e-05, + "loss": 4.0522, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.849017239018504e-05, + "loss": 4.0565, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.848178644267452e-05, + "loss": 4.0653, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.8473400495164e-05, + "loss": 4.0623, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.846501454765348e-05, + "loss": 4.0555, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.845662860014296e-05, + "loss": 4.0542, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.844824265263244e-05, + "loss": 4.0662, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.843987308392565e-05, + "loss": 4.05, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.843148713641513e-05, + "loss": 4.0498, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.842310118890461e-05, + "loss": 4.0522, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.841471524139409e-05, + "loss": 4.0583, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.84063456726873e-05, + "loss": 4.0541, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.839795972517678e-05, + "loss": 4.054, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.838957377766626e-05, + "loss": 4.0556, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.8381187830155743e-05, + "loss": 4.0592, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.8372801882645223e-05, + "loss": 4.0584, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.8364415935134697e-05, + "loss": 4.057, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.8356029987624177e-05, + "loss": 4.0576, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.834766041891739e-05, + "loss": 4.0223, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.8339274471406866e-05, + "loss": 4.0643, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.8330888523896346e-05, + "loss": 4.0457, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.8322502576385826e-05, + "loss": 4.0584, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.8314116628875305e-05, + "loss": 4.0429, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.8305730681364785e-05, + "loss": 4.0362, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.8297361112657995e-05, + "loss": 4.0382, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.828899154395121e-05, + "loss": 4.0462, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.82806055964407e-05, + "loss": 4.0556, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.827221964893017e-05, + "loss": 4.0376, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.826383370141965e-05, + "loss": 4.0595, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.825544775390913e-05, + "loss": 4.0482, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.824706180639861e-05, + "loss": 4.0352, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823867585888809e-05, + "loss": 4.0544, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.823028991137757e-05, + "loss": 4.0358, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822190396386705e-05, + "loss": 4.0335, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.821351801635653e-05, + "loss": 4.0501, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.820513206884601e-05, + "loss": 4.0538, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.819674612133549e-05, + "loss": 4.0385, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.8188392931432435e-05, + "loss": 4.0445, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.8180006983921915e-05, + "loss": 4.0333, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.8171621036411395e-05, + "loss": 4.0521, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.8163235088900875e-05, + "loss": 4.0575, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.8154849141390355e-05, + "loss": 4.0495, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.8146463193879835e-05, + "loss": 4.0544, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.8138093625173044e-05, + "loss": 4.0601, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.8129707677662524e-05, + "loss": 4.0713, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.8121321730152004e-05, + "loss": 4.0487, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.811295216144521e-05, + "loss": 4.0516, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810456621393469e-05, + "loss": 4.0483, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.809618026642417e-05, + "loss": 4.048, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808779431891365e-05, + "loss": 4.0423, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.807940837140313e-05, + "loss": 4.0536, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.807102242389262e-05, + "loss": 4.0499, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.80626364763821e-05, + "loss": 4.0631, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.805425052887158e-05, + "loss": 4.0378, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.804586458136105e-05, + "loss": 4.0388, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.803747863385053e-05, + "loss": 4.0443, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.802909268634001e-05, + "loss": 4.0512, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.802072311763323e-05, + "loss": 4.053, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.80123371701227e-05, + "loss": 4.0432, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.800396760141592e-05, + "loss": 4.0433, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.79955816539054e-05, + "loss": 4.0517, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.798719570639488e-05, + "loss": 4.0444, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.797880975888436e-05, + "loss": 4.0365, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.797042381137384e-05, + "loss": 4.0567, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.796203786386332e-05, + "loss": 4.0486, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.79536519163528e-05, + "loss": 4.0498, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.794526596884228e-05, + "loss": 4.0394, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.793688002133176e-05, + "loss": 4.0418, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.79285268314287e-05, + "loss": 4.0412, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.7920140883918175e-05, + "loss": 4.0517, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.7911754936407655e-05, + "loss": 4.0548, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.7903368988897135e-05, + "loss": 4.0422, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.7894983041386615e-05, + "loss": 4.0512, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.7886597093876095e-05, + "loss": 4.0445, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.7878211146365575e-05, + "loss": 4.0469, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.7869825198855055e-05, + "loss": 4.032, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.7861439251344535e-05, + "loss": 4.0325, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.785306968263775e-05, + "loss": 4.0447, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.784468373512723e-05, + "loss": 4.0461, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.783629778761671e-05, + "loss": 4.0322, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.782791184010619e-05, + "loss": 4.0346, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.781952589259567e-05, + "loss": 4.0367, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.781115632388888e-05, + "loss": 4.0428, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780277037637836e-05, + "loss": 4.0351, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.779438442886784e-05, + "loss": 4.0513, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.778599848135732e-05, + "loss": 4.0469, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.77776125338468e-05, + "loss": 4.0466, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.776922658633628e-05, + "loss": 4.0413, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.776085701762949e-05, + "loss": 4.0458, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.7752471070118975e-05, + "loss": 4.0439, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.7744085122608455e-05, + "loss": 4.0514, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.7735699175097935e-05, + "loss": 4.0469, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.7727313227587415e-05, + "loss": 4.0393, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.771892728007689e-05, + "loss": 4.0434, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.771054133256637e-05, + "loss": 4.042, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.770215538505585e-05, + "loss": 4.0359, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.769376943754533e-05, + "loss": 4.0346, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768541624764227e-05, + "loss": 4.0381, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.767703030013175e-05, + "loss": 4.0277, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.766864435262123e-05, + "loss": 4.0476, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.766025840511071e-05, + "loss": 4.0372, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.765187245760019e-05, + "loss": 4.0507, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.764348651008967e-05, + "loss": 4.0301, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.763511694138289e-05, + "loss": 4.0484, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.762673099387236e-05, + "loss": 4.0481, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.761834504636184e-05, + "loss": 4.0505, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.760995909885132e-05, + "loss": 4.0428, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.760158953014454e-05, + "loss": 4.0395, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.759320358263401e-05, + "loss": 4.0466, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.758481763512349e-05, + "loss": 4.0499, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.757643168761297e-05, + "loss": 4.0369, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.756804574010245e-05, + "loss": 4.0456, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.755967617139567e-05, + "loss": 4.0434, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.755129022388515e-05, + "loss": 4.0385, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.7542904276374627e-05, + "loss": 4.0384, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.7534518328864107e-05, + "loss": 4.0319, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.7526132381353586e-05, + "loss": 4.0436, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.7517746433843066e-05, + "loss": 4.0394, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.7509360486332546e-05, + "loss": 4.0475, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 4.068387031555176, + "eval_runtime": 296.5826, + "eval_samples_per_second": 1286.626, + "eval_steps_per_second": 40.208, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.7500974538822026e-05, + "loss": 4.0232, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.7492588591311506e-05, + "loss": 4.0345, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.7484202643800986e-05, + "loss": 4.034, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.7475816696290466e-05, + "loss": 4.0388, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.7467430748779946e-05, + "loss": 4.0494, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.7459044801269426e-05, + "loss": 4.0437, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.74506588537589e-05, + "loss": 4.0299, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744227290624838e-05, + "loss": 4.0337, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.7433886958737866e-05, + "loss": 4.0314, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.7425501011227346e-05, + "loss": 4.0395, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.7417115063716826e-05, + "loss": 4.0378, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.7408729116206306e-05, + "loss": 4.0401, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.7400343168695786e-05, + "loss": 4.0427, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.7391957221185266e-05, + "loss": 4.0241, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.7383571273674746e-05, + "loss": 4.0314, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.7375185326164226e-05, + "loss": 4.0218, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.7366799378653706e-05, + "loss": 4.0382, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.7358413431143186e-05, + "loss": 4.032, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.7350027483632666e-05, + "loss": 4.0366, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.734164153612214e-05, + "loss": 4.0333, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.7333271967415355e-05, + "loss": 4.0471, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.7324886019904835e-05, + "loss": 4.0343, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.7316516451198044e-05, + "loss": 4.0415, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.730813050368753e-05, + "loss": 4.0349, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.729974455617701e-05, + "loss": 4.0367, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.729135860866649e-05, + "loss": 4.0388, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.7282972661155963e-05, + "loss": 4.0254, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.7274586713645443e-05, + "loss": 4.0343, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.726620076613492e-05, + "loss": 4.0274, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.72578148186244e-05, + "loss": 4.0304, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.724944524991761e-05, + "loss": 4.0337, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.724107568121083e-05, + "loss": 4.0349, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.723268973370031e-05, + "loss": 4.0354, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722430378618979e-05, + "loss": 4.0451, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.721591783867927e-05, + "loss": 4.0307, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.7207548269972484e-05, + "loss": 4.033, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.7199162322461964e-05, + "loss": 4.0457, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.719077637495144e-05, + "loss": 4.0275, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.718239042744092e-05, + "loss": 4.0288, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.717402085873413e-05, + "loss": 4.0327, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.716563491122361e-05, + "loss": 4.0298, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.715726534251682e-05, + "loss": 4.0338, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.71488793950063e-05, + "loss": 4.0279, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.714049344749578e-05, + "loss": 4.0388, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.713210749998526e-05, + "loss": 4.0316, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.7123721552474735e-05, + "loss": 4.0377, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.711533560496422e-05, + "loss": 4.0328, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.71069496574537e-05, + "loss": 4.0372, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.709856370994318e-05, + "loss": 4.004, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.709017776243266e-05, + "loss": 4.0408, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.708179181492214e-05, + "loss": 4.021, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.707342224621535e-05, + "loss": 4.0366, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.706503629870483e-05, + "loss": 4.0207, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.705665035119431e-05, + "loss": 4.0161, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.704826440368379e-05, + "loss": 4.0154, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.7039894834977e-05, + "loss": 4.025, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.703150888746648e-05, + "loss": 4.0313, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.702313931875969e-05, + "loss": 4.0164, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.7014753371249176e-05, + "loss": 4.0378, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.7006367423738655e-05, + "loss": 4.031, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.6997981476228135e-05, + "loss": 4.0114, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.6989595528717615e-05, + "loss": 4.0303, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.6981209581207095e-05, + "loss": 4.0124, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.6972840012500304e-05, + "loss": 4.0137, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.6964454064989784e-05, + "loss": 4.0294, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.6956068117479264e-05, + "loss": 4.0318, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.6947682169968744e-05, + "loss": 4.014, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.6939296222458224e-05, + "loss": 4.0276, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.6930910274947704e-05, + "loss": 4.0131, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.6922524327437184e-05, + "loss": 4.026, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.6914138379926664e-05, + "loss": 4.0361, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.6905752432416144e-05, + "loss": 4.0298, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.6897366484905624e-05, + "loss": 4.0348, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.6888980537395104e-05, + "loss": 4.0352, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.6880594589884584e-05, + "loss": 4.0509, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.687224139998153e-05, + "loss": 4.0296, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.686385545247101e-05, + "loss": 4.0336, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.685546950496049e-05, + "loss": 4.0224, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.684708355744997e-05, + "loss": 4.026, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683869760993945e-05, + "loss": 4.0229, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.683031166242892e-05, + "loss": 4.0304, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.682194209372214e-05, + "loss": 4.0334, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.681355614621162e-05, + "loss": 4.0403, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.68051701987011e-05, + "loss": 4.0169, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.679678425119058e-05, + "loss": 4.0192, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.678839830368006e-05, + "loss": 4.0215, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.678001235616954e-05, + "loss": 4.0308, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.677162640865902e-05, + "loss": 4.0291, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.67632404611485e-05, + "loss": 4.0235, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.675487089244171e-05, + "loss": 4.0262, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.6746484944931187e-05, + "loss": 4.0272, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.6738098997420667e-05, + "loss": 4.0222, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.6729713049910146e-05, + "loss": 4.0173, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.6721327102399626e-05, + "loss": 4.0342, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.6712957533692836e-05, + "loss": 4.0313, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.6704587964986045e-05, + "loss": 4.0286, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669620201747553e-05, + "loss": 4.0156, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.668781606996501e-05, + "loss": 4.0201, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.667943012245449e-05, + "loss": 4.0222, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.66710605537477e-05, + "loss": 4.0282, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666267460623718e-05, + "loss": 4.0359, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.665428865872666e-05, + "loss": 4.0181, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664590271121614e-05, + "loss": 4.0336, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.663751676370562e-05, + "loss": 4.0248, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.66291308161951e-05, + "loss": 4.0233, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.662076124748831e-05, + "loss": 4.0123, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.661239167878152e-05, + "loss": 4.012, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.6604005731271e-05, + "loss": 4.021, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.6595619783760485e-05, + "loss": 4.0221, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.6587233836249965e-05, + "loss": 4.0132, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.6578847888739445e-05, + "loss": 4.0144, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.6570461941228925e-05, + "loss": 4.0107, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.6562075993718405e-05, + "loss": 4.0246, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.6553690046207885e-05, + "loss": 4.0182, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.6545304098697365e-05, + "loss": 4.0267, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.6536934529990574e-05, + "loss": 4.0254, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.6528548582480054e-05, + "loss": 4.0247, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.6520162634969534e-05, + "loss": 4.0205, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.6511776687459014e-05, + "loss": 4.0283, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.6503390739948494e-05, + "loss": 4.0232, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.6495004792437974e-05, + "loss": 4.0327, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.6486618844927454e-05, + "loss": 4.0248, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.6478232897416934e-05, + "loss": 4.0213, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.6469846949906414e-05, + "loss": 4.021, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.646147738119963e-05, + "loss": 4.0214, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.645309143368911e-05, + "loss": 4.0155, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.644470548617858e-05, + "loss": 4.0141, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.643631953866806e-05, + "loss": 4.0119, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.642794996996128e-05, + "loss": 4.0099, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.641956402245075e-05, + "loss": 4.0279, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.641117807494023e-05, + "loss": 4.0189, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.640279212742971e-05, + "loss": 4.0275, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.639442255872293e-05, + "loss": 4.0131, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.638603661121241e-05, + "loss": 4.0274, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.637765066370189e-05, + "loss": 4.0275, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.636926471619137e-05, + "loss": 4.0251, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636089514748458e-05, + "loss": 4.0235, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.6352509199974056e-05, + "loss": 4.0189, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.6344123252463536e-05, + "loss": 4.0293, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.6335737304953016e-05, + "loss": 4.0315, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.6327351357442496e-05, + "loss": 4.0157, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.6318965409931976e-05, + "loss": 4.0227, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.6310579462421456e-05, + "loss": 4.026, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.6302193514910936e-05, + "loss": 4.0181, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.6293840325007874e-05, + "loss": 4.0177, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.628545437749736e-05, + "loss": 4.015, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.627706842998684e-05, + "loss": 4.0229, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.626868248247632e-05, + "loss": 4.0224, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.62602965349658e-05, + "loss": 4.0258, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 4.0556182861328125, + "eval_runtime": 294.8237, + "eval_samples_per_second": 1294.302, + "eval_steps_per_second": 40.448, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.625191058745528e-05, + "loss": 4.0087, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.624352463994476e-05, + "loss": 4.0123, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.623515507123797e-05, + "loss": 4.0135, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.622676912372745e-05, + "loss": 4.0208, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.621838317621693e-05, + "loss": 4.0275, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.620999722870641e-05, + "loss": 4.0251, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.620161128119589e-05, + "loss": 4.0134, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.619322533368537e-05, + "loss": 4.0155, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.618485576497858e-05, + "loss": 4.0086, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617646981746806e-05, + "loss": 4.0161, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.6168100248761275e-05, + "loss": 4.0232, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.6159714301250754e-05, + "loss": 4.0169, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.6151328353740234e-05, + "loss": 4.0212, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.6142942406229714e-05, + "loss": 4.0049, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.6134556458719194e-05, + "loss": 4.0158, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.6126170511208674e-05, + "loss": 3.9994, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.6117784563698154e-05, + "loss": 4.0193, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.6109398616187634e-05, + "loss": 4.0131, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.6101012668677114e-05, + "loss": 4.0158, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.609262672116659e-05, + "loss": 4.0143, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.608424077365607e-05, + "loss": 4.0316, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.607585482614555e-05, + "loss": 4.0106, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.606746887863503e-05, + "loss": 4.0231, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.605911568873198e-05, + "loss": 4.0141, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.605072974122146e-05, + "loss": 4.0168, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.604236017251467e-05, + "loss": 4.0217, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.603397422500415e-05, + "loss": 4.005, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.602558827749363e-05, + "loss": 4.0119, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.601720232998311e-05, + "loss": 4.0095, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.600881638247259e-05, + "loss": 4.01, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.600043043496206e-05, + "loss": 4.0152, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.599204448745154e-05, + "loss": 4.0175, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598365853994102e-05, + "loss": 4.0107, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.597528897123424e-05, + "loss": 4.0309, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596690302372372e-05, + "loss": 4.0125, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.59585170762132e-05, + "loss": 4.0122, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595013112870268e-05, + "loss": 4.0239, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.594176155999589e-05, + "loss": 4.0058, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.5933375612485366e-05, + "loss": 4.0082, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.5924989664974846e-05, + "loss": 4.0158, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.5916603717464326e-05, + "loss": 4.0092, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.5908217769953806e-05, + "loss": 4.0154, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.5899831822443286e-05, + "loss": 4.014, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.5891462253736495e-05, + "loss": 4.0122, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.5883076306225975e-05, + "loss": 4.0179, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.5874690358715455e-05, + "loss": 4.0166, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.5866304411204935e-05, + "loss": 4.0145, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.5857918463694414e-05, + "loss": 4.0181, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.58495325161839e-05, + "loss": 3.9856, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.584114656867338e-05, + "loss": 4.0158, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.583276062116286e-05, + "loss": 4.0063, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.582439105245607e-05, + "loss": 4.0176, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.581600510494555e-05, + "loss": 4.004, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.580761915743503e-05, + "loss": 3.9942, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.579923320992451e-05, + "loss": 4.0007, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.5790896398825184e-05, + "loss": 4.0054, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.578251045131466e-05, + "loss": 4.0125, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.577412450380414e-05, + "loss": 3.9939, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.5765738556293624e-05, + "loss": 4.0225, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.5757352608783104e-05, + "loss": 4.0126, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.5748966661272584e-05, + "loss": 3.9895, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.5740580713762064e-05, + "loss": 4.013, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.5732194766251544e-05, + "loss": 3.9967, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.572382519754475e-05, + "loss": 3.9944, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.571543925003423e-05, + "loss": 4.0051, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.570705330252371e-05, + "loss": 4.0176, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.569866735501319e-05, + "loss": 3.9954, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.569028140750267e-05, + "loss": 4.0118, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.568189545999215e-05, + "loss": 3.9907, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567350951248163e-05, + "loss": 4.0077, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.566513994377484e-05, + "loss": 4.0146, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.565675399626432e-05, + "loss": 4.0139, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.564836804875381e-05, + "loss": 4.0139, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.563998210124329e-05, + "loss": 4.0171, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.563159615373277e-05, + "loss": 4.033, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.562322658502598e-05, + "loss": 4.0115, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.561484063751546e-05, + "loss": 4.0158, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.560645469000494e-05, + "loss": 4.0029, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.559806874249442e-05, + "loss": 4.0079, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.55896827949839e-05, + "loss": 4.0035, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.558129684747337e-05, + "loss": 4.0099, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.557291089996285e-05, + "loss": 4.0172, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.556452495245233e-05, + "loss": 4.0185, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.555613900494181e-05, + "loss": 4.0034, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.5547769436235026e-05, + "loss": 3.9985, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.553939986752824e-05, + "loss": 3.9984, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.553103029882145e-05, + "loss": 4.0184, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.552264435131093e-05, + "loss": 4.0087, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.551425840380041e-05, + "loss": 4.0023, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.550587245628989e-05, + "loss": 4.0129, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.549748650877937e-05, + "loss": 4.0055, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.5489100561268844e-05, + "loss": 4.0057, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.5480714613758324e-05, + "loss": 4.0015, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.5472328666247804e-05, + "loss": 4.0155, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.5463942718737284e-05, + "loss": 4.0105, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.5455556771226764e-05, + "loss": 4.0132, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.5447170823716244e-05, + "loss": 3.9981, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.5438784876205724e-05, + "loss": 4.0027, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.543041530749894e-05, + "loss": 4.0045, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.542202935998842e-05, + "loss": 4.0113, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.5413676170085365e-05, + "loss": 4.0127, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.5405290222574845e-05, + "loss": 4.0055, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.539690427506432e-05, + "loss": 4.0119, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.53885183275538e-05, + "loss": 4.0084, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.538013238004328e-05, + "loss": 4.0068, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.537174643253276e-05, + "loss": 3.9935, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.536336048502224e-05, + "loss": 3.9987, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.535497453751172e-05, + "loss": 4.0002, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.53465885900012e-05, + "loss": 4.0065, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.5338219021294414e-05, + "loss": 3.9945, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.5329833073783894e-05, + "loss": 3.9941, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.5321447126273373e-05, + "loss": 3.9959, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.5313061178762853e-05, + "loss": 4.0039, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.5304675231252333e-05, + "loss": 4.0028, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.529628928374181e-05, + "loss": 4.0052, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.528790333623129e-05, + "loss": 4.0093, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.52795337675245e-05, + "loss": 4.0112, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527114782001398e-05, + "loss": 4.0029, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.526276187250346e-05, + "loss": 4.0106, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.525437592499294e-05, + "loss": 4.0042, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.524598997748242e-05, + "loss": 4.0158, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.52376040299719e-05, + "loss": 4.0072, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.522921808246138e-05, + "loss": 4.0038, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.522083213495086e-05, + "loss": 4.0029, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.521246256624408e-05, + "loss": 4.0073, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.520407661873356e-05, + "loss": 3.9959, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.519570705002677e-05, + "loss": 3.999, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.518732110251625e-05, + "loss": 3.9898, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.517893515500573e-05, + "loss": 3.9985, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.517054920749521e-05, + "loss": 4.0076, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.516216325998468e-05, + "loss": 4.0019, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.515377731247416e-05, + "loss": 4.0101, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.514539136496364e-05, + "loss": 3.9921, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.513700541745312e-05, + "loss": 4.014, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.5128635848746336e-05, + "loss": 4.0101, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.5120249901235816e-05, + "loss": 4.0129, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.5111863953725296e-05, + "loss": 3.9963, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.5103478006214776e-05, + "loss": 4.0042, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.5095108437507985e-05, + "loss": 4.0148, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.5086722489997465e-05, + "loss": 4.0125, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.5078336542486945e-05, + "loss": 3.9999, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.5069966973780154e-05, + "loss": 3.9993, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.5061581026269634e-05, + "loss": 4.0079, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.5053195078759114e-05, + "loss": 4.0061, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.5044809131248594e-05, + "loss": 3.9989, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.5036423183738074e-05, + "loss": 4.0014, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.5028037236227554e-05, + "loss": 3.9993, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.501965128871704e-05, + "loss": 4.0027, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.501126534120652e-05, + "loss": 4.009, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 4.044368743896484, + "eval_runtime": 292.3137, + "eval_samples_per_second": 1305.416, + "eval_steps_per_second": 40.795, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.500289577249973e-05, + "loss": 3.9939, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.499450982498921e-05, + "loss": 3.9924, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.498612387747869e-05, + "loss": 3.9986, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497773792996817e-05, + "loss": 4.0056, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.496935198245765e-05, + "loss": 4.0017, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.496096603494713e-05, + "loss": 4.0102, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.495258008743661e-05, + "loss": 3.9991, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.494419413992609e-05, + "loss": 3.9955, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.493580819241557e-05, + "loss": 3.9907, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.492742224490504e-05, + "loss": 4.0029, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.491903629739452e-05, + "loss": 4.0048, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.4910650349884e-05, + "loss": 4.0005, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.490226440237349e-05, + "loss": 4.0109, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.489387845486297e-05, + "loss": 3.9829, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.488549250735245e-05, + "loss": 3.9952, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.487710655984193e-05, + "loss": 3.9878, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.486872061233141e-05, + "loss": 4.0023, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.486033466482089e-05, + "loss": 3.9968, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.48519650961141e-05, + "loss": 3.9959, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.484357914860358e-05, + "loss": 3.9942, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.483519320109306e-05, + "loss": 4.0167, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482680725358254e-05, + "loss": 3.9939, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.481842130607202e-05, + "loss": 4.0067, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.4810051737365227e-05, + "loss": 3.9982, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.4801665789854707e-05, + "loss": 4.0031, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.4793279842344187e-05, + "loss": 4.0024, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.478489389483367e-05, + "loss": 3.9865, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.477652432612688e-05, + "loss": 3.9956, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.476813837861636e-05, + "loss": 3.9919, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.475975243110584e-05, + "loss": 3.9919, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.475136648359532e-05, + "loss": 4.0007, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.47429805360848e-05, + "loss": 3.9973, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.473459458857428e-05, + "loss": 3.9948, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.4726208641063755e-05, + "loss": 4.014, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.4717822693553235e-05, + "loss": 3.9947, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.4709436746042715e-05, + "loss": 3.999, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.470106717733593e-05, + "loss": 4.0049, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469268122982541e-05, + "loss": 3.985, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468429528231489e-05, + "loss": 3.9954, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467592571360811e-05, + "loss": 3.9964, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466753976609758e-05, + "loss": 3.9926, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.465915381858706e-05, + "loss": 4.0015, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465076787107654e-05, + "loss": 3.9999, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464238192356602e-05, + "loss": 3.9941, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.46339959760555e-05, + "loss": 4.0012, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.462561002854498e-05, + "loss": 4.002, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.461724045983819e-05, + "loss": 3.9965, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.460885451232767e-05, + "loss": 3.9992, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.460046856481715e-05, + "loss": 3.9714, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.459208261730663e-05, + "loss": 3.9971, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.458369666979611e-05, + "loss": 3.9962, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.4575310722285595e-05, + "loss": 3.9997, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.4566924774775075e-05, + "loss": 3.9873, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.4558538827264555e-05, + "loss": 3.977, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.4550152879754035e-05, + "loss": 3.982, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.4541799689850974e-05, + "loss": 3.9853, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.4533413742340454e-05, + "loss": 4.0008, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.4525027794829933e-05, + "loss": 3.9746, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.4516641847319413e-05, + "loss": 4.0056, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.4508255899808893e-05, + "loss": 3.998, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.449986995229837e-05, + "loss": 3.9768, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449148400478785e-05, + "loss": 3.9968, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.448311443608106e-05, + "loss": 3.9793, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.447474486737428e-05, + "loss": 3.9802, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.446635891986376e-05, + "loss": 3.9845, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.445798935115697e-05, + "loss": 3.9981, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.444960340364645e-05, + "loss": 3.9817, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.444121745613593e-05, + "loss": 3.9948, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.443283150862541e-05, + "loss": 3.9719, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442444556111489e-05, + "loss": 3.9913, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.441605961360437e-05, + "loss": 3.9994, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.440767366609385e-05, + "loss": 3.9997, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.439928771858333e-05, + "loss": 3.9981, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.439090177107281e-05, + "loss": 4.0017, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.438251582356229e-05, + "loss": 4.0137, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.437412987605177e-05, + "loss": 3.9974, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.436574392854125e-05, + "loss": 4.0007, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435735798103073e-05, + "loss": 3.9849, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.434898841232394e-05, + "loss": 3.9917, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.434061884361715e-05, + "loss": 3.9904, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433223289610663e-05, + "loss": 3.9925, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.432384694859611e-05, + "loss": 3.9992, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.431546100108559e-05, + "loss": 4.0048, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.4307075053575065e-05, + "loss": 3.9931, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.4298689106064545e-05, + "loss": 3.9807, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.4290303158554025e-05, + "loss": 3.9851, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.4281917211043505e-05, + "loss": 3.9994, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.4273531263532985e-05, + "loss": 3.9909, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.4265145316022465e-05, + "loss": 3.9897, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.425675936851195e-05, + "loss": 3.9956, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.424838979980516e-05, + "loss": 3.9905, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.424000385229464e-05, + "loss": 3.9876, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.423161790478412e-05, + "loss": 3.9834, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.42232319572736e-05, + "loss": 3.9984, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.421486238856681e-05, + "loss": 3.9975, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.420647644105629e-05, + "loss": 3.9961, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.419809049354577e-05, + "loss": 3.982, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.418970454603525e-05, + "loss": 3.9879, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.418131859852473e-05, + "loss": 3.9905, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.417294902981794e-05, + "loss": 3.9939, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.416456308230742e-05, + "loss": 3.9999, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.4156177134796905e-05, + "loss": 3.9876, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.4147791187286385e-05, + "loss": 3.9966, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.4139405239775865e-05, + "loss": 3.991, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.4131019292265345e-05, + "loss": 3.99, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.4122633344754825e-05, + "loss": 3.9805, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.4114247397244305e-05, + "loss": 3.9824, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.4105877828537514e-05, + "loss": 3.9857, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.4097491881026994e-05, + "loss": 3.9897, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.4089105933516474e-05, + "loss": 3.9773, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.408071998600595e-05, + "loss": 3.9821, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407235041729916e-05, + "loss": 3.9758, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.406396446978864e-05, + "loss": 3.9927, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.405557852227812e-05, + "loss": 3.9861, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.40471925747676e-05, + "loss": 3.9894, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.403880662725708e-05, + "loss": 3.9878, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.40304370585503e-05, + "loss": 3.9944, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.402205111103978e-05, + "loss": 3.9895, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401366516352925e-05, + "loss": 3.9895, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400527921601873e-05, + "loss": 3.9937, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.399689326850821e-05, + "loss": 3.9971, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398850732099769e-05, + "loss": 3.9901, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.398012137348717e-05, + "loss": 3.9897, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397173542597665e-05, + "loss": 3.9887, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.396336585726986e-05, + "loss": 3.9856, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.395497990975934e-05, + "loss": 3.9817, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.3946610341052556e-05, + "loss": 3.9845, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.3938224393542036e-05, + "loss": 3.974, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.392985482483525e-05, + "loss": 3.9845, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.3921468877324725e-05, + "loss": 3.9886, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.3913082929814205e-05, + "loss": 3.9917, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.3904696982303685e-05, + "loss": 3.9914, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.3896311034793165e-05, + "loss": 3.9828, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.3887925087282645e-05, + "loss": 3.9967, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.3879539139772125e-05, + "loss": 3.9941, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.3871153192261605e-05, + "loss": 3.9933, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.3862767244751085e-05, + "loss": 3.987, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.3854381297240565e-05, + "loss": 3.989, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.3845995349730045e-05, + "loss": 3.9975, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.3837609402219525e-05, + "loss": 3.996, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.382923983351274e-05, + "loss": 3.9884, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.382087026480595e-05, + "loss": 3.9846, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.381248431729543e-05, + "loss": 3.9903, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.380409836978491e-05, + "loss": 3.9879, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379571242227439e-05, + "loss": 3.986, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.378732647476387e-05, + "loss": 3.9853, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.377894052725335e-05, + "loss": 3.9844, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.377055457974283e-05, + "loss": 3.9903, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.376216863223231e-05, + "loss": 3.9935, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 4.035999298095703, + "eval_runtime": 293.6392, + "eval_samples_per_second": 1299.524, + "eval_steps_per_second": 40.611, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.375379906352552e-05, + "loss": 3.9852, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.3745413116015e-05, + "loss": 3.9748, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.373702716850448e-05, + "loss": 3.9812, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.372864122099396e-05, + "loss": 3.9947, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.372025527348344e-05, + "loss": 3.988, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.371186932597292e-05, + "loss": 3.9953, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.37034833784624e-05, + "loss": 3.98, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.369509743095188e-05, + "loss": 3.9821, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.3686744241048823e-05, + "loss": 3.9745, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.36783582935383e-05, + "loss": 3.991, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.366997234602778e-05, + "loss": 3.985, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.3661586398517256e-05, + "loss": 3.986, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.365321682981047e-05, + "loss": 3.9952, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.364484726110368e-05, + "loss": 3.9694, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.363646131359317e-05, + "loss": 3.9825, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.362807536608265e-05, + "loss": 3.9682, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.361968941857213e-05, + "loss": 3.9882, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.361130347106161e-05, + "loss": 3.9807, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.360291752355109e-05, + "loss": 3.9865, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.359453157604056e-05, + "loss": 3.9771, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.358614562853004e-05, + "loss": 3.9993, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.357775968101952e-05, + "loss": 3.9825, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.356939011231273e-05, + "loss": 3.9914, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.356100416480221e-05, + "loss": 3.9857, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.355261821729169e-05, + "loss": 3.9894, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.354423226978117e-05, + "loss": 3.9854, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.353584632227065e-05, + "loss": 3.9737, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.352746037476014e-05, + "loss": 3.9844, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.351907442724962e-05, + "loss": 3.9739, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.35106884797391e-05, + "loss": 3.9783, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.350230253222858e-05, + "loss": 3.9827, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.3493916584718057e-05, + "loss": 3.9793, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.3485530637207537e-05, + "loss": 3.9831, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.3477144689697016e-05, + "loss": 3.9974, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.3468758742186496e-05, + "loss": 3.9819, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.346037279467597e-05, + "loss": 3.9892, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.3452003225969185e-05, + "loss": 3.9892, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.3443633657262395e-05, + "loss": 3.9715, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.3435247709751875e-05, + "loss": 3.984, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.3426861762241354e-05, + "loss": 3.9779, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.3418475814730834e-05, + "loss": 3.9773, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.341010624602405e-05, + "loss": 3.9871, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.340172029851353e-05, + "loss": 3.9887, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.339333435100301e-05, + "loss": 3.9757, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.338494840349249e-05, + "loss": 3.9858, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.337656245598197e-05, + "loss": 3.9892, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.336819288727518e-05, + "loss": 3.9802, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.335980693976466e-05, + "loss": 3.9889, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.335142099225414e-05, + "loss": 3.9555, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.334303504474362e-05, + "loss": 3.9805, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.333464909723309e-05, + "loss": 3.9807, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.332626314972257e-05, + "loss": 3.9867, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.331787720221205e-05, + "loss": 3.9733, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.330950763350527e-05, + "loss": 3.9651, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.330112168599475e-05, + "loss": 3.964, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.3292752117287964e-05, + "loss": 3.9674, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.3284366169777444e-05, + "loss": 3.9894, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.327598022226692e-05, + "loss": 3.9638, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.32675942747564e-05, + "loss": 3.9868, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.325920832724588e-05, + "loss": 3.9799, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.325082237973536e-05, + "loss": 3.9688, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.324243643222484e-05, + "loss": 3.9781, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.323405048471432e-05, + "loss": 3.9665, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.3225680916007526e-05, + "loss": 3.9675, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.3217294968497006e-05, + "loss": 3.9705, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.320890902098649e-05, + "loss": 3.9842, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.320052307347597e-05, + "loss": 3.9701, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.319213712596545e-05, + "loss": 3.9752, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.318375117845493e-05, + "loss": 3.9624, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.317536523094441e-05, + "loss": 3.9744, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.316697928343389e-05, + "loss": 3.9867, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.31586097147271e-05, + "loss": 3.9852, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.315022376721658e-05, + "loss": 3.9833, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.314183781970606e-05, + "loss": 3.9844, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.313345187219554e-05, + "loss": 3.999, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.312506592468502e-05, + "loss": 3.982, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.311669635597823e-05, + "loss": 3.9881, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.310831040846771e-05, + "loss": 3.9738, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.309992446095719e-05, + "loss": 3.9769, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.309153851344668e-05, + "loss": 3.9744, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.308315256593616e-05, + "loss": 3.9749, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.307476661842564e-05, + "loss": 3.9869, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.306638067091511e-05, + "loss": 3.9878, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.305799472340459e-05, + "loss": 3.9851, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.3049641533501535e-05, + "loss": 3.9625, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.3041255585991015e-05, + "loss": 3.9698, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.3032869638480495e-05, + "loss": 3.9841, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.3024483690969975e-05, + "loss": 3.9803, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.3016097743459455e-05, + "loss": 3.9737, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.300771179594893e-05, + "loss": 3.9788, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.2999325848438415e-05, + "loss": 3.9763, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.2990939900927895e-05, + "loss": 3.975, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.2982553953417375e-05, + "loss": 3.9732, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.297420076351432e-05, + "loss": 3.9843, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.29658148160038e-05, + "loss": 3.9803, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.295742886849328e-05, + "loss": 3.9825, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.294904292098275e-05, + "loss": 3.9678, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.294065697347223e-05, + "loss": 3.9723, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.293227102596171e-05, + "loss": 3.9777, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.292388507845119e-05, + "loss": 3.9802, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.291549913094067e-05, + "loss": 3.9858, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.290711318343015e-05, + "loss": 3.9764, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.289874361472337e-05, + "loss": 3.9809, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.289035766721285e-05, + "loss": 3.9756, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.288197171970233e-05, + "loss": 3.9782, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.287358577219181e-05, + "loss": 3.9664, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.286523258228875e-05, + "loss": 3.9658, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.2856846634778227e-05, + "loss": 3.9761, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.2848460687267707e-05, + "loss": 3.9753, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.2840074739757186e-05, + "loss": 3.966, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.2831688792246666e-05, + "loss": 3.9662, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.2823302844736146e-05, + "loss": 3.9636, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.2814916897225626e-05, + "loss": 3.9721, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.2806530949715106e-05, + "loss": 3.9737, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.279816138100832e-05, + "loss": 3.974, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.278979181230153e-05, + "loss": 3.9757, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.278140586479101e-05, + "loss": 3.9841, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.277301991728049e-05, + "loss": 3.9745, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.276463396976997e-05, + "loss": 3.9754, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.275624802225945e-05, + "loss": 3.9821, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.274786207474893e-05, + "loss": 3.9808, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.273947612723841e-05, + "loss": 3.9759, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.273109017972789e-05, + "loss": 3.9805, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.27227206110211e-05, + "loss": 3.975, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.271433466351058e-05, + "loss": 3.9709, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.270594871600006e-05, + "loss": 3.9634, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.269757914729327e-05, + "loss": 3.975, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.2689193199782756e-05, + "loss": 3.9656, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.2680823631075965e-05, + "loss": 3.9695, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.2672437683565445e-05, + "loss": 3.9652, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.2664051736054925e-05, + "loss": 3.9787, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.2655665788544405e-05, + "loss": 3.976, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.2647279841033885e-05, + "loss": 3.97, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.2638893893523365e-05, + "loss": 3.9817, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.2630507946012845e-05, + "loss": 3.9799, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.2622121998502325e-05, + "loss": 3.9825, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.2613736050991805e-05, + "loss": 3.9752, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.2605350103481284e-05, + "loss": 3.9703, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.2596964155970764e-05, + "loss": 3.9864, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.258857820846024e-05, + "loss": 3.9747, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.2580192260949724e-05, + "loss": 3.9805, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.257182269224294e-05, + "loss": 3.9692, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.2563436744732413e-05, + "loss": 3.975, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.255505079722189e-05, + "loss": 3.9719, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.254666484971137e-05, + "loss": 3.9711, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.253827890220085e-05, + "loss": 3.9748, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.252989295469033e-05, + "loss": 3.9724, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.252150700717981e-05, + "loss": 3.9773, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.251313743847302e-05, + "loss": 3.9749, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 4.02727746963501, + "eval_runtime": 294.9998, + "eval_samples_per_second": 1293.53, + "eval_steps_per_second": 40.424, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.25047514909625e-05, + "loss": 3.9575, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.249636554345198e-05, + "loss": 3.9652, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.248797959594146e-05, + "loss": 3.9666, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.247959364843094e-05, + "loss": 3.9823, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.247120770092042e-05, + "loss": 3.9738, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.246282175340991e-05, + "loss": 3.9843, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.245443580589939e-05, + "loss": 3.9667, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.244604985838887e-05, + "loss": 3.9678, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243766391087835e-05, + "loss": 3.9631, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.242927796336783e-05, + "loss": 3.9757, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.24208920158573e-05, + "loss": 3.9726, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.241250606834678e-05, + "loss": 3.9734, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.240413649964e-05, + "loss": 3.9795, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.239575055212948e-05, + "loss": 3.9587, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.238736460461895e-05, + "loss": 3.9657, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.237897865710843e-05, + "loss": 3.9579, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.237059270959791e-05, + "loss": 3.9727, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.236220676208739e-05, + "loss": 3.9652, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.235382081457688e-05, + "loss": 3.9733, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.234543486706636e-05, + "loss": 3.9628, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.233704891955584e-05, + "loss": 3.9852, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.232866297204532e-05, + "loss": 3.9697, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.23202770245348e-05, + "loss": 3.973, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.231189107702428e-05, + "loss": 3.9725, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.2303521508317486e-05, + "loss": 3.9799, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.2295135560806966e-05, + "loss": 3.9709, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.2286749613296446e-05, + "loss": 3.962, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.2278363665785926e-05, + "loss": 3.9717, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.2269977718275406e-05, + "loss": 3.9579, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.2261608149568615e-05, + "loss": 3.9636, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.2253238580861824e-05, + "loss": 3.9688, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.224485263335131e-05, + "loss": 3.9674, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.223646668584079e-05, + "loss": 3.9701, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.222808073833027e-05, + "loss": 3.979, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.221969479081975e-05, + "loss": 3.9712, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.221130884330923e-05, + "loss": 3.9755, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220292289579871e-05, + "loss": 3.9748, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.219455332709192e-05, + "loss": 3.9571, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.21861673795814e-05, + "loss": 3.9751, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.217778143207088e-05, + "loss": 3.9644, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.216939548456036e-05, + "loss": 3.9661, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.216100953704984e-05, + "loss": 3.9697, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.215263996834305e-05, + "loss": 3.9747, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.214425402083253e-05, + "loss": 3.9579, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.213586807332201e-05, + "loss": 3.9788, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.2127498504615225e-05, + "loss": 3.9714, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.2119112557104705e-05, + "loss": 3.9698, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.2110726609594184e-05, + "loss": 3.9737, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.2102340662083664e-05, + "loss": 3.9425, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.209395471457314e-05, + "loss": 3.9653, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.208556876706262e-05, + "loss": 3.9745, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.20771828195521e-05, + "loss": 3.9681, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.206879687204158e-05, + "loss": 3.9577, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.2060427303334787e-05, + "loss": 3.954, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.2052057734628e-05, + "loss": 3.9512, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.204367178711748e-05, + "loss": 3.954, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.203528583960696e-05, + "loss": 3.9811, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.202689989209644e-05, + "loss": 3.948, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.201851394458592e-05, + "loss": 3.974, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.20101279970754e-05, + "loss": 3.9662, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.200174204956488e-05, + "loss": 3.9517, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.199335610205436e-05, + "loss": 3.9638, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.198497015454384e-05, + "loss": 3.9555, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.197660058583705e-05, + "loss": 3.9553, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.196823101713026e-05, + "loss": 3.9515, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.195984506961974e-05, + "loss": 3.972, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.1951475500912956e-05, + "loss": 3.9618, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.1943089553402436e-05, + "loss": 3.9583, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.1934703605891916e-05, + "loss": 3.9508, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.1926317658381396e-05, + "loss": 3.9606, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.1917931710870876e-05, + "loss": 3.9744, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.1909545763360356e-05, + "loss": 3.9724, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.1901159815849836e-05, + "loss": 3.9692, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.1892773868339316e-05, + "loss": 3.9718, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.1884387920828796e-05, + "loss": 3.9855, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.1876001973318276e-05, + "loss": 3.9691, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.1867616025807756e-05, + "loss": 3.9734, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.1859230078297236e-05, + "loss": 3.962, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.1850844130786716e-05, + "loss": 3.9665, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.1842458183276196e-05, + "loss": 3.9612, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.1834088614569405e-05, + "loss": 3.9582, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.1825702667058885e-05, + "loss": 3.9737, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.1817316719548365e-05, + "loss": 3.9792, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.180893077203785e-05, + "loss": 3.9733, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.1800544824527324e-05, + "loss": 3.9471, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.1792158877016804e-05, + "loss": 3.9576, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.1783772929506284e-05, + "loss": 3.9696, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.1775386981995764e-05, + "loss": 3.9687, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.1767017413288973e-05, + "loss": 3.9587, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.175863146577845e-05, + "loss": 3.9691, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.175026189707167e-05, + "loss": 3.962, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.174187594956115e-05, + "loss": 3.9611, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173349000205062e-05, + "loss": 3.959, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.17251040545401e-05, + "loss": 3.9741, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.171671810702959e-05, + "loss": 3.9634, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.170833215951907e-05, + "loss": 3.9722, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.169994621200855e-05, + "loss": 3.9543, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.169156026449803e-05, + "loss": 3.9588, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.168317431698751e-05, + "loss": 3.9657, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.167478836947699e-05, + "loss": 3.967, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.16664188007702e-05, + "loss": 3.9712, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.165803285325968e-05, + "loss": 3.9644, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.164966328455289e-05, + "loss": 3.9686, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.164127733704237e-05, + "loss": 3.9622, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.1632907768335576e-05, + "loss": 3.9694, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.1624521820825056e-05, + "loss": 3.9481, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.161613587331454e-05, + "loss": 3.958, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.160774992580402e-05, + "loss": 3.9598, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.15993639782935e-05, + "loss": 3.9601, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.159097803078298e-05, + "loss": 3.9557, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.158259208327246e-05, + "loss": 3.952, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.157420613576194e-05, + "loss": 3.9464, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.156582018825142e-05, + "loss": 3.9651, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.15574342407409e-05, + "loss": 3.9579, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.154904829323038e-05, + "loss": 3.9613, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.154067872452359e-05, + "loss": 3.9641, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.153229277701307e-05, + "loss": 3.9696, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.152390682950255e-05, + "loss": 3.9645, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.151552088199203e-05, + "loss": 3.9591, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.150713493448151e-05, + "loss": 3.9724, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.149874898697099e-05, + "loss": 3.9677, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.149036303946047e-05, + "loss": 3.9593, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.148197709194995e-05, + "loss": 3.9664, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.147360752324316e-05, + "loss": 3.9639, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.146522157573264e-05, + "loss": 3.9629, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.1456852007025856e-05, + "loss": 3.9493, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.1448466059515336e-05, + "loss": 3.9625, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.144008011200481e-05, + "loss": 3.9526, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.1431710543298025e-05, + "loss": 3.9599, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.1423324595787505e-05, + "loss": 3.9487, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.141493864827698e-05, + "loss": 3.972, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.1406552700766465e-05, + "loss": 3.9635, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.1398166753255945e-05, + "loss": 3.9541, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.1389780805745425e-05, + "loss": 3.971, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.1381394858234905e-05, + "loss": 3.9659, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.1373008910724385e-05, + "loss": 3.9699, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.1364639342017594e-05, + "loss": 3.9614, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.1356253394507074e-05, + "loss": 3.9624, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.1347867446996554e-05, + "loss": 3.9721, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.1339481499486034e-05, + "loss": 3.9599, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.1331095551975514e-05, + "loss": 3.9699, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.1322709604464994e-05, + "loss": 3.957, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.13143400357582e-05, + "loss": 3.9675, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.130595408824768e-05, + "loss": 3.9576, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.129756814073716e-05, + "loss": 3.9567, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.128918219322665e-05, + "loss": 3.9614, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.128079624571613e-05, + "loss": 3.9599, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.127241029820561e-05, + "loss": 3.9679, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.126404072949882e-05, + "loss": 3.961, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 4.020936489105225, + "eval_runtime": 291.136, + "eval_samples_per_second": 1310.696, + "eval_steps_per_second": 40.96, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.12556547819883e-05, + "loss": 3.9557, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.124726883447778e-05, + "loss": 3.9575, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.123888288696726e-05, + "loss": 3.9518, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.123049693945674e-05, + "loss": 3.9661, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.122211099194622e-05, + "loss": 3.9601, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.121374142323943e-05, + "loss": 3.9745, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120535547572891e-05, + "loss": 3.9533, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.119696952821839e-05, + "loss": 3.9566, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.1188599959511596e-05, + "loss": 3.9505, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.118021401200108e-05, + "loss": 3.9644, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.117182806449056e-05, + "loss": 3.9546, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.116344211698004e-05, + "loss": 3.9638, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.115505616946952e-05, + "loss": 3.9684, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.1146670221958996e-05, + "loss": 3.947, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.1138284274448476e-05, + "loss": 3.9511, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.1129898326937956e-05, + "loss": 3.95, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.1121528758231165e-05, + "loss": 3.9593, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.1113142810720645e-05, + "loss": 3.9557, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.110477324201386e-05, + "loss": 3.9593, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.109638729450334e-05, + "loss": 3.9521, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.108800134699282e-05, + "loss": 3.9717, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.10796153994823e-05, + "loss": 3.9544, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.107122945197178e-05, + "loss": 3.9623, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.106284350446126e-05, + "loss": 3.9619, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.105445755695074e-05, + "loss": 3.967, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.104607160944022e-05, + "loss": 3.9587, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.10376856619297e-05, + "loss": 3.9513, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.102931609322291e-05, + "loss": 3.9584, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.102093014571239e-05, + "loss": 3.9443, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.101254419820187e-05, + "loss": 3.9555, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.100415825069135e-05, + "loss": 3.955, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.099577230318083e-05, + "loss": 3.9601, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.098738635567031e-05, + "loss": 3.954, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.097900040815979e-05, + "loss": 3.9648, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.0970630839453005e-05, + "loss": 3.9621, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.0962244891942485e-05, + "loss": 3.9602, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.0953858944431965e-05, + "loss": 3.9639, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.0945472996921445e-05, + "loss": 3.9457, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.0937087049410925e-05, + "loss": 3.9642, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.0928701101900405e-05, + "loss": 3.9504, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.0920331533193614e-05, + "loss": 3.9545, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.0911945585683094e-05, + "loss": 3.96, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.0903559638172574e-05, + "loss": 3.962, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.0895173690662054e-05, + "loss": 3.9504, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.088678774315153e-05, + "loss": 3.9621, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.087840179564101e-05, + "loss": 3.9602, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.087001584813049e-05, + "loss": 3.9575, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.08616462794237e-05, + "loss": 3.9634, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.085326033191318e-05, + "loss": 3.9334, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.084487438440266e-05, + "loss": 3.949, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.083648843689214e-05, + "loss": 3.9655, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.082810248938162e-05, + "loss": 3.9579, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.08197165418711e-05, + "loss": 3.9467, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.081133059436058e-05, + "loss": 3.9385, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.080294464685006e-05, + "loss": 3.9443, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.0794591456947e-05, + "loss": 3.9367, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.078620550943648e-05, + "loss": 3.9719, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.077781956192596e-05, + "loss": 3.9369, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.076943361441544e-05, + "loss": 3.9609, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.076104766690493e-05, + "loss": 3.9547, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.075266171939441e-05, + "loss": 3.9433, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.074427577188389e-05, + "loss": 3.9519, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.073588982437337e-05, + "loss": 3.9453, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.072750387686285e-05, + "loss": 3.942, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.0719150686959786e-05, + "loss": 3.9397, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.0710764739449265e-05, + "loss": 3.9628, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.0702378791938745e-05, + "loss": 3.9489, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.0693992844428225e-05, + "loss": 3.9451, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.0685606896917705e-05, + "loss": 3.9368, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.0677220949407185e-05, + "loss": 3.9475, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.0668835001896665e-05, + "loss": 3.9624, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.0660449054386145e-05, + "loss": 3.9639, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.0652063106875625e-05, + "loss": 3.9589, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.064369353816884e-05, + "loss": 3.9595, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.063530759065832e-05, + "loss": 3.9708, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.06269216431478e-05, + "loss": 3.9607, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.061855207444101e-05, + "loss": 3.9586, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.061016612693049e-05, + "loss": 3.9492, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.060178017941997e-05, + "loss": 3.9555, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.059339423190945e-05, + "loss": 3.9483, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.058500828439893e-05, + "loss": 3.9516, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.057662233688841e-05, + "loss": 3.9605, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.056823638937789e-05, + "loss": 3.9672, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.055985044186736e-05, + "loss": 3.9578, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.055148087316058e-05, + "loss": 3.9401, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.0543111304453795e-05, + "loss": 3.9452, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.0534725356943275e-05, + "loss": 3.9545, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.0526339409432755e-05, + "loss": 3.9633, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.0517953461922235e-05, + "loss": 3.945, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.0509600272019173e-05, + "loss": 3.9582, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.0501214324508653e-05, + "loss": 3.9535, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0492828376998133e-05, + "loss": 3.9468, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.0484442429487613e-05, + "loss": 3.9468, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.0476056481977096e-05, + "loss": 3.9599, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.0467670534466576e-05, + "loss": 3.9487, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.0459284586956056e-05, + "loss": 3.961, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.0450898639445536e-05, + "loss": 3.9468, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.0442529070738745e-05, + "loss": 3.9475, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.0434159502031957e-05, + "loss": 3.9524, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.0425773554521437e-05, + "loss": 3.9594, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.0417387607010917e-05, + "loss": 3.958, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.0409001659500397e-05, + "loss": 3.9534, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.0400632090793606e-05, + "loss": 3.9553, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.0392246143283086e-05, + "loss": 3.9515, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.0383860195772566e-05, + "loss": 3.9556, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.037547424826205e-05, + "loss": 3.9361, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.036708830075153e-05, + "loss": 3.946, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.035870235324101e-05, + "loss": 3.9503, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.035031640573049e-05, + "loss": 3.9488, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.0341930458219963e-05, + "loss": 3.9456, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.0333544510709443e-05, + "loss": 3.9421, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.0325158563198926e-05, + "loss": 3.9364, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.0316772615688406e-05, + "loss": 3.9513, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.0308386668177886e-05, + "loss": 3.9441, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.0300000720667366e-05, + "loss": 3.9547, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.0291631151960575e-05, + "loss": 3.95, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.0283245204450055e-05, + "loss": 3.9567, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.0274859256939535e-05, + "loss": 3.9535, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.0266473309429015e-05, + "loss": 3.9498, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.0258087361918498e-05, + "loss": 3.9574, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0249701414407978e-05, + "loss": 3.9562, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.0241315466897458e-05, + "loss": 3.9515, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.0232929519386938e-05, + "loss": 3.9547, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.0224559950680147e-05, + "loss": 3.952, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.0216174003169627e-05, + "loss": 3.9526, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.0207788055659107e-05, + "loss": 3.9418, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.019940210814859e-05, + "loss": 3.944, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.01910325394418e-05, + "loss": 3.9433, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.018266297073501e-05, + "loss": 3.9447, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.017427702322449e-05, + "loss": 3.9359, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.016589107571397e-05, + "loss": 3.9661, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.015752150700718e-05, + "loss": 3.9526, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.014913555949666e-05, + "loss": 3.9484, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.014074961198614e-05, + "loss": 3.9526, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.013236366447562e-05, + "loss": 3.953, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.01239777169651e-05, + "loss": 3.9644, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.011559176945458e-05, + "loss": 3.9537, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.010720582194406e-05, + "loss": 3.9502, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.0098819874433544e-05, + "loss": 3.9598, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.0090433926923024e-05, + "loss": 3.9456, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.0082047979412497e-05, + "loss": 3.9583, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.0073662031901977e-05, + "loss": 3.948, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.0065276084391457e-05, + "loss": 3.9562, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.0056906515684673e-05, + "loss": 3.9506, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.004852056817415e-05, + "loss": 3.9402, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.004013462066363e-05, + "loss": 3.9538, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.003174867315311e-05, + "loss": 3.9491, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.0023379104446325e-05, + "loss": 3.9538, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.00149931569358e-05, + "loss": 3.9493, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.0006607209425282e-05, + "loss": 3.95, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 4.0154290199279785, + "eval_runtime": 291.9948, + "eval_samples_per_second": 1306.842, + "eval_steps_per_second": 40.84, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.9998221261914762e-05, + "loss": 3.9431, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.9989835314404242e-05, + "loss": 3.9379, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.9981449366893722e-05, + "loss": 3.9579, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.9973063419383202e-05, + "loss": 3.9499, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.996467747187268e-05, + "loss": 3.9621, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.995629152436216e-05, + "loss": 3.9431, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.994790557685164e-05, + "loss": 3.9452, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.993951962934112e-05, + "loss": 3.9349, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.9931133681830605e-05, + "loss": 3.9558, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.9922747734320085e-05, + "loss": 3.9436, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.9914361786809565e-05, + "loss": 3.9536, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.9905975839299038e-05, + "loss": 3.9543, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.9897606270592254e-05, + "loss": 3.9423, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.9889220323081734e-05, + "loss": 3.9401, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.988083437557121e-05, + "loss": 3.9389, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.987244842806069e-05, + "loss": 3.9403, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.986406248055017e-05, + "loss": 3.9488, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.985567653303965e-05, + "loss": 3.9464, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.984729058552913e-05, + "loss": 3.9403, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.983890463801861e-05, + "loss": 3.9653, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.983051869050809e-05, + "loss": 3.9418, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.9822149121801303e-05, + "loss": 3.9546, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.9813763174290783e-05, + "loss": 3.9485, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.9805377226780262e-05, + "loss": 3.9561, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.9796991279269742e-05, + "loss": 3.944, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.9788605331759222e-05, + "loss": 3.9458, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.978023576305243e-05, + "loss": 3.9417, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.9771849815541915e-05, + "loss": 3.9417, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.9763463868031395e-05, + "loss": 3.9403, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.9755077920520875e-05, + "loss": 3.9409, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.9746708351814084e-05, + "loss": 3.9509, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.9738322404303564e-05, + "loss": 3.9469, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.9729952835596776e-05, + "loss": 3.9523, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.9721566888086256e-05, + "loss": 3.9523, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.9713180940575736e-05, + "loss": 3.9506, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.9704794993065216e-05, + "loss": 3.9509, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.9696409045554696e-05, + "loss": 3.9413, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.9688023098044176e-05, + "loss": 3.9478, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.9679637150533656e-05, + "loss": 3.9411, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.967126758182687e-05, + "loss": 3.9476, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.966288163431635e-05, + "loss": 3.946, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.965449568680583e-05, + "loss": 3.9508, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.964610973929531e-05, + "loss": 3.9386, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.963772379178479e-05, + "loss": 3.9495, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.9629337844274268e-05, + "loss": 3.9522, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.9620951896763748e-05, + "loss": 3.9504, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.9612565949253225e-05, + "loss": 3.9494, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.9604180001742705e-05, + "loss": 3.924, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.959581043303592e-05, + "loss": 3.9382, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.95874244855254e-05, + "loss": 3.9521, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.9579038538014874e-05, + "loss": 3.947, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.957066896930809e-05, + "loss": 3.9385, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.956228302179757e-05, + "loss": 3.9253, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.9553897074287046e-05, + "loss": 3.9343, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.9545511126776526e-05, + "loss": 3.9264, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.9537125179266006e-05, + "loss": 3.9581, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.9528739231755486e-05, + "loss": 3.9293, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.9520353284244966e-05, + "loss": 3.9466, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.9511967336734446e-05, + "loss": 3.947, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.950358138922393e-05, + "loss": 3.9301, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.949519544171341e-05, + "loss": 3.9414, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.948680949420289e-05, + "loss": 3.9352, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.9478439925496098e-05, + "loss": 3.9279, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.9470053977985578e-05, + "loss": 3.9291, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.9461668030475058e-05, + "loss": 3.9555, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.9453282082964538e-05, + "loss": 3.9431, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.944489613545402e-05, + "loss": 3.9332, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.94365101879435e-05, + "loss": 3.9285, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.942814061923671e-05, + "loss": 3.9371, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.941975467172619e-05, + "loss": 3.9484, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.941136872421567e-05, + "loss": 3.9515, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.940298277670515e-05, + "loss": 3.9456, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.9394613207998363e-05, + "loss": 3.9536, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.9386227260487843e-05, + "loss": 3.9574, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.9377841312977323e-05, + "loss": 3.9492, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.9369471744270532e-05, + "loss": 3.9458, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.9361085796760012e-05, + "loss": 3.9397, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.9352699849249492e-05, + "loss": 3.9484, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.9344313901738972e-05, + "loss": 3.943, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.9335927954228455e-05, + "loss": 3.9402, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.9327542006717935e-05, + "loss": 3.9463, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.9319172438011144e-05, + "loss": 3.9534, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.9310786490500624e-05, + "loss": 3.9508, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.9302400542990104e-05, + "loss": 3.9283, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.9294014595479584e-05, + "loss": 3.9341, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.928562864796906e-05, + "loss": 3.9455, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.927724270045854e-05, + "loss": 3.9521, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.9268873131751756e-05, + "loss": 3.9365, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.926048718424123e-05, + "loss": 3.9468, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.925210123673071e-05, + "loss": 3.9473, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.9243715289220193e-05, + "loss": 3.9374, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.9235329341709673e-05, + "loss": 3.9375, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9226943394199153e-05, + "loss": 3.9442, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.9218557446688633e-05, + "loss": 3.9406, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.9210171499178113e-05, + "loss": 3.9479, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.9201785551667593e-05, + "loss": 3.943, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.9193415982960802e-05, + "loss": 3.9317, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.9185030035450285e-05, + "loss": 3.9451, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.9176660466743494e-05, + "loss": 3.947, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.9168274519232974e-05, + "loss": 3.9437, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.9159888571722454e-05, + "loss": 3.9468, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.9151502624211934e-05, + "loss": 3.9417, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.9143116676701414e-05, + "loss": 3.9436, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.9134747107994627e-05, + "loss": 3.9476, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.9126361160484106e-05, + "loss": 3.9257, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9117975212973586e-05, + "loss": 3.9305, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9109589265463066e-05, + "loss": 3.942, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9101203317952546e-05, + "loss": 3.9413, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.9092817370442026e-05, + "loss": 3.9314, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.9084431422931506e-05, + "loss": 3.9325, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.9076045475420986e-05, + "loss": 3.9313, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.906765952791047e-05, + "loss": 3.941, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.905927358039995e-05, + "loss": 3.9348, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.9050887632889423e-05, + "loss": 3.9396, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.9042501685378903e-05, + "loss": 3.9376, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.9034115737868383e-05, + "loss": 3.9452, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.9025729790357863e-05, + "loss": 3.9454, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.9017343842847346e-05, + "loss": 3.941, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.900899065294429e-05, + "loss": 3.945, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.900060470543377e-05, + "loss": 3.9481, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8992218757923244e-05, + "loss": 3.9353, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.8983832810412724e-05, + "loss": 3.9464, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.8975446862902207e-05, + "loss": 3.9377, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.8967060915391687e-05, + "loss": 3.9492, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.8958674967881167e-05, + "loss": 3.9265, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.8950289020370647e-05, + "loss": 3.9412, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.8941903072860127e-05, + "loss": 3.928, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.893354988295707e-05, + "loss": 3.9323, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.892516393544655e-05, + "loss": 3.9264, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.891677798793603e-05, + "loss": 3.9544, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.8908408419229245e-05, + "loss": 3.9479, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.8900022471718718e-05, + "loss": 3.9358, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.8891636524208198e-05, + "loss": 3.9397, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.8883250576697678e-05, + "loss": 3.9413, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.887486462918716e-05, + "loss": 3.9541, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.886647868167664e-05, + "loss": 3.947, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.885809273416612e-05, + "loss": 3.9353, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.88497067866556e-05, + "loss": 3.9503, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.884132083914508e-05, + "loss": 3.9358, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.883293489163456e-05, + "loss": 3.95, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.882456532292777e-05, + "loss": 3.938, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.8816195754220982e-05, + "loss": 3.9428, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8807809806710462e-05, + "loss": 3.9427, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.8799423859199942e-05, + "loss": 3.9335, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.8791037911689422e-05, + "loss": 3.9434, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.8782651964178902e-05, + "loss": 3.9404, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.8774266016668382e-05, + "loss": 3.9432, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.8765880069157862e-05, + "loss": 3.9409, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.8757494121647342e-05, + "loss": 3.937, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 4.010347366333008, + "eval_runtime": 296.2203, + "eval_samples_per_second": 1288.2, + "eval_steps_per_second": 40.257, + "step": 1297440 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 5.356311808120667e+17, + "trial_name": null, + "trial_params": null +}