| { | |
| "best_metric": 0.7926267281105991, | |
| "best_model_checkpoint": "videomae-base-finetuned-subset-0401/checkpoint-896", | |
| "epoch": 49.01117117117117, | |
| "eval_steps": 500, | |
| "global_step": 2775, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.7985611510791366e-06, | |
| "loss": 1.6857, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 3.5971223021582732e-06, | |
| "loss": 1.6911, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5.3956834532374105e-06, | |
| "loss": 1.6168, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 7.1942446043165465e-06, | |
| "loss": 1.6689, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 8.992805755395683e-06, | |
| "loss": 1.6048, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_accuracy": 0.08294930875576037, | |
| "eval_loss": 1.6212950944900513, | |
| "eval_runtime": 176.5128, | |
| "eval_samples_per_second": 1.229, | |
| "eval_steps_per_second": 0.159, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.0791366906474821e-05, | |
| "loss": 1.6118, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 1.2589928057553957e-05, | |
| "loss": 1.6008, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 1.4388489208633093e-05, | |
| "loss": 1.5996, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 1.618705035971223e-05, | |
| "loss": 1.6264, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 1.7985611510791367e-05, | |
| "loss": 1.6071, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 1.9784172661870504e-05, | |
| "loss": 1.5891, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_accuracy": 0.28110599078341014, | |
| "eval_loss": 1.5230350494384766, | |
| "eval_runtime": 169.5488, | |
| "eval_samples_per_second": 1.28, | |
| "eval_steps_per_second": 0.165, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 2.1582733812949642e-05, | |
| "loss": 1.5625, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2.3381294964028776e-05, | |
| "loss": 1.5854, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2.5179856115107914e-05, | |
| "loss": 1.6007, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2.697841726618705e-05, | |
| "loss": 1.5949, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 2.8776978417266186e-05, | |
| "loss": 1.4797, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "eval_accuracy": 0.19815668202764977, | |
| "eval_loss": 1.6437386274337769, | |
| "eval_runtime": 169.6444, | |
| "eval_samples_per_second": 1.279, | |
| "eval_steps_per_second": 0.165, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3.0575539568345324e-05, | |
| "loss": 1.5867, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3.237410071942446e-05, | |
| "loss": 1.4592, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 3.41726618705036e-05, | |
| "loss": 1.3124, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 3.597122302158273e-05, | |
| "loss": 1.3075, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 3.776978417266187e-05, | |
| "loss": 1.1932, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 3.956834532374101e-05, | |
| "loss": 1.3999, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "eval_accuracy": 0.7465437788018433, | |
| "eval_loss": 0.9262827634811401, | |
| "eval_runtime": 168.7616, | |
| "eval_samples_per_second": 1.286, | |
| "eval_steps_per_second": 0.166, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.136690647482014e-05, | |
| "loss": 1.2996, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 4.3165467625899284e-05, | |
| "loss": 1.313, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 4.496402877697842e-05, | |
| "loss": 1.2644, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 4.676258992805755e-05, | |
| "loss": 1.1732, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 4.8561151079136694e-05, | |
| "loss": 1.125, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 4.9959951942330803e-05, | |
| "loss": 1.0917, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "eval_accuracy": 0.4930875576036866, | |
| "eval_loss": 1.2307826280593872, | |
| "eval_runtime": 169.9213, | |
| "eval_samples_per_second": 1.277, | |
| "eval_steps_per_second": 0.165, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 4.975971165398479e-05, | |
| "loss": 1.2046, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 4.955947136563877e-05, | |
| "loss": 1.2355, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 4.935923107729276e-05, | |
| "loss": 1.3358, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 4.915899078894674e-05, | |
| "loss": 1.1835, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 4.895875050060073e-05, | |
| "loss": 1.238, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "eval_accuracy": 0.6589861751152074, | |
| "eval_loss": 0.940632700920105, | |
| "eval_runtime": 168.194, | |
| "eval_samples_per_second": 1.29, | |
| "eval_steps_per_second": 0.166, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.875851021225471e-05, | |
| "loss": 1.3625, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 4.8558269923908696e-05, | |
| "loss": 1.2342, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 4.835802963556268e-05, | |
| "loss": 1.0534, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 4.8157789347216665e-05, | |
| "loss": 1.1462, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 4.795754905887065e-05, | |
| "loss": 1.0197, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 4.7757308770524635e-05, | |
| "loss": 1.1525, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "eval_accuracy": 0.7050691244239631, | |
| "eval_loss": 0.8809296488761902, | |
| "eval_runtime": 168.4512, | |
| "eval_samples_per_second": 1.288, | |
| "eval_steps_per_second": 0.166, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 4.755706848217862e-05, | |
| "loss": 1.0159, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 4.7356828193832604e-05, | |
| "loss": 0.9716, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 4.715658790548659e-05, | |
| "loss": 0.9998, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 4.6956347617140574e-05, | |
| "loss": 1.1153, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 4.675610732879456e-05, | |
| "loss": 1.0806, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "eval_accuracy": 0.5944700460829493, | |
| "eval_loss": 1.0089017152786255, | |
| "eval_runtime": 171.2435, | |
| "eval_samples_per_second": 1.267, | |
| "eval_steps_per_second": 0.164, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 4.655586704044854e-05, | |
| "loss": 1.1055, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 4.635562675210253e-05, | |
| "loss": 0.9111, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 4.615538646375651e-05, | |
| "loss": 1.0937, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 4.59551461754105e-05, | |
| "loss": 1.1375, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 4.575490588706448e-05, | |
| "loss": 0.8357, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 4.5554665598718466e-05, | |
| "loss": 0.8483, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "eval_accuracy": 0.5852534562211982, | |
| "eval_loss": 0.9700098037719727, | |
| "eval_runtime": 171.1205, | |
| "eval_samples_per_second": 1.268, | |
| "eval_steps_per_second": 0.164, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 4.535442531037245e-05, | |
| "loss": 0.9293, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 4.5154185022026436e-05, | |
| "loss": 1.1123, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 4.495394473368042e-05, | |
| "loss": 1.0562, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 4.4753704445334405e-05, | |
| "loss": 0.8454, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 4.455346415698839e-05, | |
| "loss": 0.8096, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 4.4353223868642374e-05, | |
| "loss": 0.992, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "eval_accuracy": 0.48847926267281105, | |
| "eval_loss": 1.1879829168319702, | |
| "eval_runtime": 168.7686, | |
| "eval_samples_per_second": 1.286, | |
| "eval_steps_per_second": 0.166, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 4.415298358029636e-05, | |
| "loss": 1.0682, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 4.3952743291950344e-05, | |
| "loss": 0.954, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 4.375250300360433e-05, | |
| "loss": 0.9788, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 4.355226271525831e-05, | |
| "loss": 0.975, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 10.02, | |
| "learning_rate": 4.33520224269123e-05, | |
| "loss": 0.862, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 10.02, | |
| "eval_accuracy": 0.7511520737327189, | |
| "eval_loss": 0.7174272537231445, | |
| "eval_runtime": 168.7207, | |
| "eval_samples_per_second": 1.286, | |
| "eval_steps_per_second": 0.166, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 4.315178213856628e-05, | |
| "loss": 0.7987, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "learning_rate": 4.295154185022027e-05, | |
| "loss": 0.7351, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "learning_rate": 4.275130156187425e-05, | |
| "loss": 0.8315, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "learning_rate": 4.2551061273528236e-05, | |
| "loss": 0.92, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 4.235082098518222e-05, | |
| "loss": 0.6532, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 4.2150580696836206e-05, | |
| "loss": 1.0694, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "eval_accuracy": 0.7142857142857143, | |
| "eval_loss": 0.8598370552062988, | |
| "eval_runtime": 168.9431, | |
| "eval_samples_per_second": 1.284, | |
| "eval_steps_per_second": 0.166, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 4.195034040849019e-05, | |
| "loss": 0.7898, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 4.1750100120144175e-05, | |
| "loss": 0.8624, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 4.154985983179816e-05, | |
| "loss": 0.9415, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 4.1349619543452144e-05, | |
| "loss": 0.806, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 12.02, | |
| "learning_rate": 4.114937925510613e-05, | |
| "loss": 0.8885, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 12.02, | |
| "eval_accuracy": 0.7096774193548387, | |
| "eval_loss": 0.8289774656295776, | |
| "eval_runtime": 169.3457, | |
| "eval_samples_per_second": 1.281, | |
| "eval_steps_per_second": 0.165, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 4.0949138966760114e-05, | |
| "loss": 0.8971, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 4.07488986784141e-05, | |
| "loss": 0.752, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 4.054865839006808e-05, | |
| "loss": 0.9724, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 4.034841810172207e-05, | |
| "loss": 0.9637, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "learning_rate": 4.014817781337605e-05, | |
| "loss": 1.0046, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "learning_rate": 3.994793752503004e-05, | |
| "loss": 0.8965, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "eval_accuracy": 0.7142857142857143, | |
| "eval_loss": 0.8304111361503601, | |
| "eval_runtime": 171.3216, | |
| "eval_samples_per_second": 1.267, | |
| "eval_steps_per_second": 0.163, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 3.974769723668402e-05, | |
| "loss": 0.9904, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 3.9547456948338006e-05, | |
| "loss": 0.9846, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 3.934721665999199e-05, | |
| "loss": 0.9145, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 3.9146976371645976e-05, | |
| "loss": 0.7486, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "learning_rate": 3.894673608329996e-05, | |
| "loss": 0.7721, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "learning_rate": 3.8746495794953945e-05, | |
| "loss": 0.7371, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "eval_accuracy": 0.7695852534562212, | |
| "eval_loss": 0.7009211778640747, | |
| "eval_runtime": 168.9295, | |
| "eval_samples_per_second": 1.285, | |
| "eval_steps_per_second": 0.166, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 3.854625550660793e-05, | |
| "loss": 0.923, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 15.01, | |
| "learning_rate": 3.8346015218261915e-05, | |
| "loss": 0.9008, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 15.01, | |
| "learning_rate": 3.81457749299159e-05, | |
| "loss": 0.7429, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 15.01, | |
| "learning_rate": 3.7945534641569884e-05, | |
| "loss": 0.6912, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 15.02, | |
| "learning_rate": 3.774529435322387e-05, | |
| "loss": 0.6872, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 15.02, | |
| "eval_accuracy": 0.7926267281105991, | |
| "eval_loss": 0.6768301129341125, | |
| "eval_runtime": 170.318, | |
| "eval_samples_per_second": 1.274, | |
| "eval_steps_per_second": 0.164, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 3.754505406487785e-05, | |
| "loss": 0.636, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 16.01, | |
| "learning_rate": 3.734481377653184e-05, | |
| "loss": 0.7347, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 16.01, | |
| "learning_rate": 3.714457348818582e-05, | |
| "loss": 0.7698, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 16.01, | |
| "learning_rate": 3.694433319983981e-05, | |
| "loss": 0.7495, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 16.02, | |
| "learning_rate": 3.674409291149379e-05, | |
| "loss": 0.725, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 16.02, | |
| "learning_rate": 3.6543852623147777e-05, | |
| "loss": 0.6022, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 16.02, | |
| "eval_accuracy": 0.7373271889400922, | |
| "eval_loss": 0.7512706518173218, | |
| "eval_runtime": 168.81, | |
| "eval_samples_per_second": 1.285, | |
| "eval_steps_per_second": 0.166, | |
| "step": 952 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 3.634361233480176e-05, | |
| "loss": 0.8774, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 17.01, | |
| "learning_rate": 3.6143372046455746e-05, | |
| "loss": 0.6907, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 17.01, | |
| "learning_rate": 3.594313175810973e-05, | |
| "loss": 0.6035, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 17.01, | |
| "learning_rate": 3.5742891469763715e-05, | |
| "loss": 0.7363, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 17.02, | |
| "learning_rate": 3.55426511814177e-05, | |
| "loss": 0.9308, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 17.02, | |
| "eval_accuracy": 0.7096774193548387, | |
| "eval_loss": 0.8054620623588562, | |
| "eval_runtime": 169.493, | |
| "eval_samples_per_second": 1.28, | |
| "eval_steps_per_second": 0.165, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 3.5342410893071685e-05, | |
| "loss": 0.73, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 3.514217060472567e-05, | |
| "loss": 0.9107, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 18.01, | |
| "learning_rate": 3.4941930316379654e-05, | |
| "loss": 0.739, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 18.01, | |
| "learning_rate": 3.474169002803364e-05, | |
| "loss": 0.8472, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 18.02, | |
| "learning_rate": 3.454144973968762e-05, | |
| "loss": 0.7395, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 18.02, | |
| "learning_rate": 3.434120945134161e-05, | |
| "loss": 0.4456, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 18.02, | |
| "eval_accuracy": 0.6728110599078341, | |
| "eval_loss": 0.7876001000404358, | |
| "eval_runtime": 172.0864, | |
| "eval_samples_per_second": 1.261, | |
| "eval_steps_per_second": 0.163, | |
| "step": 1064 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 3.414096916299559e-05, | |
| "loss": 0.581, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "learning_rate": 3.394072887464958e-05, | |
| "loss": 1.0824, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "learning_rate": 3.374048858630356e-05, | |
| "loss": 0.6623, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "learning_rate": 3.354024829795755e-05, | |
| "loss": 0.6078, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 19.02, | |
| "learning_rate": 3.334000800961153e-05, | |
| "loss": 0.6867, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 19.02, | |
| "learning_rate": 3.3139767721265516e-05, | |
| "loss": 0.6802, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 19.02, | |
| "eval_accuracy": 0.7235023041474654, | |
| "eval_loss": 0.722358763217926, | |
| "eval_runtime": 170.3701, | |
| "eval_samples_per_second": 1.274, | |
| "eval_steps_per_second": 0.164, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 3.29395274329195e-05, | |
| "loss": 0.6218, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 20.01, | |
| "learning_rate": 3.2739287144573485e-05, | |
| "loss": 0.6368, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 20.01, | |
| "learning_rate": 3.253904685622747e-05, | |
| "loss": 0.7407, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 20.01, | |
| "learning_rate": 3.2338806567881455e-05, | |
| "loss": 0.6189, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 20.02, | |
| "learning_rate": 3.213856627953544e-05, | |
| "loss": 0.7154, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 20.02, | |
| "eval_accuracy": 0.7050691244239631, | |
| "eval_loss": 0.7434002161026001, | |
| "eval_runtime": 168.861, | |
| "eval_samples_per_second": 1.285, | |
| "eval_steps_per_second": 0.166, | |
| "step": 1176 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "learning_rate": 3.1938325991189424e-05, | |
| "loss": 0.6084, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 21.01, | |
| "learning_rate": 3.173808570284341e-05, | |
| "loss": 0.656, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 21.01, | |
| "learning_rate": 3.1537845414497393e-05, | |
| "loss": 0.7274, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 21.01, | |
| "learning_rate": 3.133760512615138e-05, | |
| "loss": 0.5818, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 21.02, | |
| "learning_rate": 3.113736483780536e-05, | |
| "loss": 0.8351, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 21.02, | |
| "learning_rate": 3.0937124549459354e-05, | |
| "loss": 0.503, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 21.02, | |
| "eval_accuracy": 0.695852534562212, | |
| "eval_loss": 0.8345744609832764, | |
| "eval_runtime": 168.411, | |
| "eval_samples_per_second": 1.289, | |
| "eval_steps_per_second": 0.166, | |
| "step": 1232 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "learning_rate": 3.073688426111334e-05, | |
| "loss": 0.5257, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 22.01, | |
| "learning_rate": 3.0536643972767324e-05, | |
| "loss": 0.511, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 22.01, | |
| "learning_rate": 3.0336403684421305e-05, | |
| "loss": 0.6193, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 22.01, | |
| "learning_rate": 3.013616339607529e-05, | |
| "loss": 0.6704, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 22.02, | |
| "learning_rate": 2.9935923107729274e-05, | |
| "loss": 0.7203, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 22.02, | |
| "eval_accuracy": 0.5990783410138248, | |
| "eval_loss": 0.9694386720657349, | |
| "eval_runtime": 169.6323, | |
| "eval_samples_per_second": 1.279, | |
| "eval_steps_per_second": 0.165, | |
| "step": 1288 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "learning_rate": 2.973568281938326e-05, | |
| "loss": 0.605, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "learning_rate": 2.9535442531037244e-05, | |
| "loss": 0.6581, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 23.01, | |
| "learning_rate": 2.9335202242691228e-05, | |
| "loss": 0.5423, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 23.01, | |
| "learning_rate": 2.9134961954345213e-05, | |
| "loss": 0.6137, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 23.02, | |
| "learning_rate": 2.8934721665999198e-05, | |
| "loss": 0.562, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 23.02, | |
| "learning_rate": 2.8734481377653182e-05, | |
| "loss": 0.6799, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 23.02, | |
| "eval_accuracy": 0.7695852534562212, | |
| "eval_loss": 0.647365152835846, | |
| "eval_runtime": 168.7434, | |
| "eval_samples_per_second": 1.286, | |
| "eval_steps_per_second": 0.166, | |
| "step": 1344 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 2.8534241089307167e-05, | |
| "loss": 0.5556, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 24.01, | |
| "learning_rate": 2.833400080096115e-05, | |
| "loss": 0.7249, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 24.01, | |
| "learning_rate": 2.8133760512615136e-05, | |
| "loss": 0.563, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 24.01, | |
| "learning_rate": 2.793352022426912e-05, | |
| "loss": 0.6947, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 24.02, | |
| "learning_rate": 2.7733279935923106e-05, | |
| "loss": 0.8462, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 24.02, | |
| "learning_rate": 2.753303964757709e-05, | |
| "loss": 0.5802, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 24.02, | |
| "eval_accuracy": 0.6359447004608295, | |
| "eval_loss": 0.957251787185669, | |
| "eval_runtime": 168.4758, | |
| "eval_samples_per_second": 1.288, | |
| "eval_steps_per_second": 0.166, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 2.7332799359231075e-05, | |
| "loss": 0.5186, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 25.01, | |
| "learning_rate": 2.713255907088506e-05, | |
| "loss": 0.5462, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 25.01, | |
| "learning_rate": 2.6932318782539044e-05, | |
| "loss": 0.6317, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 25.01, | |
| "learning_rate": 2.673207849419303e-05, | |
| "loss": 0.5265, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 25.02, | |
| "learning_rate": 2.6531838205847014e-05, | |
| "loss": 0.7047, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 25.02, | |
| "eval_accuracy": 0.695852534562212, | |
| "eval_loss": 0.9120410680770874, | |
| "eval_runtime": 168.5578, | |
| "eval_samples_per_second": 1.287, | |
| "eval_steps_per_second": 0.166, | |
| "step": 1456 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "learning_rate": 2.6331597917501e-05, | |
| "loss": 0.5364, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 26.01, | |
| "learning_rate": 2.613135762915499e-05, | |
| "loss": 0.5322, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 26.01, | |
| "learning_rate": 2.5931117340808974e-05, | |
| "loss": 0.897, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 26.01, | |
| "learning_rate": 2.573087705246296e-05, | |
| "loss": 0.4983, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 26.02, | |
| "learning_rate": 2.5530636764116944e-05, | |
| "loss": 0.7582, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 26.02, | |
| "learning_rate": 2.533039647577093e-05, | |
| "loss": 0.6701, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 26.02, | |
| "eval_accuracy": 0.5852534562211982, | |
| "eval_loss": 1.1690046787261963, | |
| "eval_runtime": 169.2732, | |
| "eval_samples_per_second": 1.282, | |
| "eval_steps_per_second": 0.165, | |
| "step": 1512 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "learning_rate": 2.5130156187424913e-05, | |
| "loss": 0.4735, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 27.01, | |
| "learning_rate": 2.4929915899078894e-05, | |
| "loss": 0.6383, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 27.01, | |
| "learning_rate": 2.472967561073288e-05, | |
| "loss": 0.7644, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 27.01, | |
| "learning_rate": 2.4529435322386864e-05, | |
| "loss": 0.6395, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 27.02, | |
| "learning_rate": 2.432919503404085e-05, | |
| "loss": 0.5514, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 27.02, | |
| "eval_accuracy": 0.6866359447004609, | |
| "eval_loss": 0.9173929691314697, | |
| "eval_runtime": 169.8137, | |
| "eval_samples_per_second": 1.278, | |
| "eval_steps_per_second": 0.165, | |
| "step": 1568 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 2.4128954745694833e-05, | |
| "loss": 0.5936, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 2.3928714457348818e-05, | |
| "loss": 0.4936, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 28.01, | |
| "learning_rate": 2.3728474169002803e-05, | |
| "loss": 0.6134, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 28.01, | |
| "learning_rate": 2.3528233880656787e-05, | |
| "loss": 0.654, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 28.02, | |
| "learning_rate": 2.3327993592310772e-05, | |
| "loss": 0.6997, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 28.02, | |
| "learning_rate": 2.3127753303964757e-05, | |
| "loss": 0.538, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 28.02, | |
| "eval_accuracy": 0.6866359447004609, | |
| "eval_loss": 0.854290246963501, | |
| "eval_runtime": 171.1701, | |
| "eval_samples_per_second": 1.268, | |
| "eval_steps_per_second": 0.164, | |
| "step": 1624 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "learning_rate": 2.292751301561874e-05, | |
| "loss": 0.6431, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 29.01, | |
| "learning_rate": 2.272727272727273e-05, | |
| "loss": 0.6269, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 29.01, | |
| "learning_rate": 2.2527032438926714e-05, | |
| "loss": 0.6239, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 29.01, | |
| "learning_rate": 2.23267921505807e-05, | |
| "loss": 0.5901, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 29.02, | |
| "learning_rate": 2.2126551862234683e-05, | |
| "loss": 0.5673, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 29.02, | |
| "learning_rate": 2.1926311573888668e-05, | |
| "loss": 0.7226, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 29.02, | |
| "eval_accuracy": 0.7465437788018433, | |
| "eval_loss": 0.7773527503013611, | |
| "eval_runtime": 170.9184, | |
| "eval_samples_per_second": 1.27, | |
| "eval_steps_per_second": 0.164, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 2.1726071285542653e-05, | |
| "loss": 0.5368, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 30.01, | |
| "learning_rate": 2.1525830997196637e-05, | |
| "loss": 0.6407, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 30.01, | |
| "learning_rate": 2.1325590708850622e-05, | |
| "loss": 0.6071, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 30.01, | |
| "learning_rate": 2.1125350420504607e-05, | |
| "loss": 0.587, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 30.02, | |
| "learning_rate": 2.092511013215859e-05, | |
| "loss": 0.4459, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 30.02, | |
| "eval_accuracy": 0.6359447004608295, | |
| "eval_loss": 0.9134915471076965, | |
| "eval_runtime": 169.6863, | |
| "eval_samples_per_second": 1.279, | |
| "eval_steps_per_second": 0.165, | |
| "step": 1736 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "learning_rate": 2.0724869843812576e-05, | |
| "loss": 0.6281, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 31.01, | |
| "learning_rate": 2.052462955546656e-05, | |
| "loss": 0.5999, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 31.01, | |
| "learning_rate": 2.0324389267120545e-05, | |
| "loss": 0.4052, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 31.01, | |
| "learning_rate": 2.012414897877453e-05, | |
| "loss": 0.7613, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 31.02, | |
| "learning_rate": 1.9923908690428515e-05, | |
| "loss": 0.6318, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 31.02, | |
| "learning_rate": 1.9723668402082503e-05, | |
| "loss": 0.3905, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 31.02, | |
| "eval_accuracy": 0.6728110599078341, | |
| "eval_loss": 0.8585994243621826, | |
| "eval_runtime": 165.9142, | |
| "eval_samples_per_second": 1.308, | |
| "eval_steps_per_second": 0.169, | |
| "step": 1792 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "learning_rate": 1.9523428113736487e-05, | |
| "loss": 0.5, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 32.01, | |
| "learning_rate": 1.9323187825390472e-05, | |
| "loss": 0.4816, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 32.01, | |
| "learning_rate": 1.9122947537044457e-05, | |
| "loss": 0.4979, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 32.01, | |
| "learning_rate": 1.892270724869844e-05, | |
| "loss": 0.6203, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 32.02, | |
| "learning_rate": 1.8722466960352426e-05, | |
| "loss": 0.7071, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 32.02, | |
| "eval_accuracy": 0.7327188940092166, | |
| "eval_loss": 0.7919384837150574, | |
| "eval_runtime": 171.3033, | |
| "eval_samples_per_second": 1.267, | |
| "eval_steps_per_second": 0.163, | |
| "step": 1848 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "learning_rate": 1.852222667200641e-05, | |
| "loss": 0.5632, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "learning_rate": 1.8321986383660396e-05, | |
| "loss": 0.6323, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 33.01, | |
| "learning_rate": 1.812174609531438e-05, | |
| "loss": 0.6151, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 33.01, | |
| "learning_rate": 1.7921505806968365e-05, | |
| "loss": 0.4412, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 33.02, | |
| "learning_rate": 1.772126551862235e-05, | |
| "loss": 0.4863, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 33.02, | |
| "learning_rate": 1.7521025230276334e-05, | |
| "loss": 0.4983, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 33.02, | |
| "eval_accuracy": 0.7511520737327189, | |
| "eval_loss": 0.7506622672080994, | |
| "eval_runtime": 169.3822, | |
| "eval_samples_per_second": 1.281, | |
| "eval_steps_per_second": 0.165, | |
| "step": 1904 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "learning_rate": 1.732078494193032e-05, | |
| "loss": 0.4416, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 34.01, | |
| "learning_rate": 1.7120544653584304e-05, | |
| "loss": 0.5567, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 34.01, | |
| "learning_rate": 1.6920304365238288e-05, | |
| "loss": 0.3794, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 34.01, | |
| "learning_rate": 1.6720064076892273e-05, | |
| "loss": 0.5672, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 34.02, | |
| "learning_rate": 1.6519823788546258e-05, | |
| "loss": 0.4093, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 34.02, | |
| "learning_rate": 1.6319583500200242e-05, | |
| "loss": 0.5654, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 34.02, | |
| "eval_accuracy": 0.7142857142857143, | |
| "eval_loss": 0.767917275428772, | |
| "eval_runtime": 173.7976, | |
| "eval_samples_per_second": 1.249, | |
| "eval_steps_per_second": 0.161, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "learning_rate": 1.6119343211854227e-05, | |
| "loss": 0.3909, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 35.01, | |
| "learning_rate": 1.591910292350821e-05, | |
| "loss": 0.5576, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 35.01, | |
| "learning_rate": 1.5718862635162196e-05, | |
| "loss": 0.4247, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 35.01, | |
| "learning_rate": 1.551862234681618e-05, | |
| "loss": 0.747, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 35.02, | |
| "learning_rate": 1.5318382058470166e-05, | |
| "loss": 0.5569, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 35.02, | |
| "eval_accuracy": 0.7096774193548387, | |
| "eval_loss": 0.8438030481338501, | |
| "eval_runtime": 168.1341, | |
| "eval_samples_per_second": 1.291, | |
| "eval_steps_per_second": 0.167, | |
| "step": 2016 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "learning_rate": 1.511814177012415e-05, | |
| "loss": 0.5796, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 36.01, | |
| "learning_rate": 1.4917901481778135e-05, | |
| "loss": 0.6004, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 36.01, | |
| "learning_rate": 1.471766119343212e-05, | |
| "loss": 0.4482, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 36.01, | |
| "learning_rate": 1.4517420905086104e-05, | |
| "loss": 0.593, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 36.02, | |
| "learning_rate": 1.4317180616740089e-05, | |
| "loss": 0.6642, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 36.02, | |
| "learning_rate": 1.4116940328394074e-05, | |
| "loss": 0.3998, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 36.02, | |
| "eval_accuracy": 0.7188940092165899, | |
| "eval_loss": 0.8691464066505432, | |
| "eval_runtime": 171.2911, | |
| "eval_samples_per_second": 1.267, | |
| "eval_steps_per_second": 0.163, | |
| "step": 2072 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "learning_rate": 1.3916700040048058e-05, | |
| "loss": 0.3557, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 37.01, | |
| "learning_rate": 1.3716459751702043e-05, | |
| "loss": 0.3628, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 37.01, | |
| "learning_rate": 1.3516219463356028e-05, | |
| "loss": 0.335, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 37.01, | |
| "learning_rate": 1.3315979175010012e-05, | |
| "loss": 0.6813, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 37.02, | |
| "learning_rate": 1.3115738886663997e-05, | |
| "loss": 0.5341, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 37.02, | |
| "eval_accuracy": 0.7603686635944701, | |
| "eval_loss": 0.8056049346923828, | |
| "eval_runtime": 172.8523, | |
| "eval_samples_per_second": 1.255, | |
| "eval_steps_per_second": 0.162, | |
| "step": 2128 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "learning_rate": 1.2915498598317982e-05, | |
| "loss": 0.4075, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "learning_rate": 1.2715258309971966e-05, | |
| "loss": 0.5339, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 38.01, | |
| "learning_rate": 1.2515018021625951e-05, | |
| "loss": 0.4681, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 38.01, | |
| "learning_rate": 1.2314777733279936e-05, | |
| "loss": 0.4725, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 38.02, | |
| "learning_rate": 1.211453744493392e-05, | |
| "loss": 0.5588, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 38.02, | |
| "learning_rate": 1.1914297156587905e-05, | |
| "loss": 0.4024, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 38.02, | |
| "eval_accuracy": 0.7880184331797235, | |
| "eval_loss": 0.7070650458335876, | |
| "eval_runtime": 170.228, | |
| "eval_samples_per_second": 1.275, | |
| "eval_steps_per_second": 0.164, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "learning_rate": 1.171405686824189e-05, | |
| "loss": 0.4122, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 39.01, | |
| "learning_rate": 1.1513816579895874e-05, | |
| "loss": 0.3389, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 39.01, | |
| "learning_rate": 1.131357629154986e-05, | |
| "loss": 0.4993, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 39.01, | |
| "learning_rate": 1.1113336003203845e-05, | |
| "loss": 0.5869, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 39.02, | |
| "learning_rate": 1.091309571485783e-05, | |
| "loss": 0.7077, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 39.02, | |
| "learning_rate": 1.0712855426511815e-05, | |
| "loss": 0.5011, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 39.02, | |
| "eval_accuracy": 0.7004608294930875, | |
| "eval_loss": 0.882685661315918, | |
| "eval_runtime": 169.5666, | |
| "eval_samples_per_second": 1.28, | |
| "eval_steps_per_second": 0.165, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 1.05126151381658e-05, | |
| "loss": 0.443, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 40.01, | |
| "learning_rate": 1.0312374849819784e-05, | |
| "loss": 0.5292, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 40.01, | |
| "learning_rate": 1.0112134561473769e-05, | |
| "loss": 0.4058, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 40.01, | |
| "learning_rate": 9.911894273127754e-06, | |
| "loss": 0.5513, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 40.02, | |
| "learning_rate": 9.71165398478174e-06, | |
| "loss": 0.5857, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 40.02, | |
| "eval_accuracy": 0.7096774193548387, | |
| "eval_loss": 0.8525260090827942, | |
| "eval_runtime": 169.961, | |
| "eval_samples_per_second": 1.277, | |
| "eval_steps_per_second": 0.165, | |
| "step": 2296 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "learning_rate": 9.511413696435725e-06, | |
| "loss": 0.6831, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 41.01, | |
| "learning_rate": 9.31117340808971e-06, | |
| "loss": 0.4212, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 41.01, | |
| "learning_rate": 9.110933119743694e-06, | |
| "loss": 0.4343, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 41.01, | |
| "learning_rate": 8.910692831397679e-06, | |
| "loss": 0.3912, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 41.02, | |
| "learning_rate": 8.710452543051663e-06, | |
| "loss": 0.5539, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 41.02, | |
| "learning_rate": 8.510212254705648e-06, | |
| "loss": 0.5619, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 41.02, | |
| "eval_accuracy": 0.7511520737327189, | |
| "eval_loss": 0.8228119611740112, | |
| "eval_runtime": 167.3356, | |
| "eval_samples_per_second": 1.297, | |
| "eval_steps_per_second": 0.167, | |
| "step": 2352 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "learning_rate": 8.309971966359633e-06, | |
| "loss": 0.3721, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 42.01, | |
| "learning_rate": 8.109731678013617e-06, | |
| "loss": 0.332, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 42.01, | |
| "learning_rate": 7.909491389667602e-06, | |
| "loss": 0.5869, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 42.01, | |
| "learning_rate": 7.709251101321587e-06, | |
| "loss": 0.4474, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 42.02, | |
| "learning_rate": 7.509010812975571e-06, | |
| "loss": 0.6052, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 42.02, | |
| "eval_accuracy": 0.7373271889400922, | |
| "eval_loss": 0.8320425152778625, | |
| "eval_runtime": 168.2726, | |
| "eval_samples_per_second": 1.29, | |
| "eval_steps_per_second": 0.166, | |
| "step": 2408 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "learning_rate": 7.308770524629556e-06, | |
| "loss": 0.451, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "learning_rate": 7.108530236283541e-06, | |
| "loss": 0.282, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 43.01, | |
| "learning_rate": 6.908289947937525e-06, | |
| "loss": 0.4565, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 43.01, | |
| "learning_rate": 6.70804965959151e-06, | |
| "loss": 0.6579, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 43.02, | |
| "learning_rate": 6.507809371245495e-06, | |
| "loss": 0.3812, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 43.02, | |
| "learning_rate": 6.307569082899479e-06, | |
| "loss": 0.5124, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 43.02, | |
| "eval_accuracy": 0.7419354838709677, | |
| "eval_loss": 0.8776273131370544, | |
| "eval_runtime": 167.8781, | |
| "eval_samples_per_second": 1.293, | |
| "eval_steps_per_second": 0.167, | |
| "step": 2464 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "learning_rate": 6.107328794553464e-06, | |
| "loss": 0.2933, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 44.01, | |
| "learning_rate": 5.907088506207449e-06, | |
| "loss": 0.3212, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 44.01, | |
| "learning_rate": 5.706848217861433e-06, | |
| "loss": 0.47, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 44.01, | |
| "learning_rate": 5.506607929515419e-06, | |
| "loss": 0.3473, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 44.02, | |
| "learning_rate": 5.306367641169404e-06, | |
| "loss": 0.5966, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 44.02, | |
| "learning_rate": 5.106127352823388e-06, | |
| "loss": 0.3323, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 44.02, | |
| "eval_accuracy": 0.7465437788018433, | |
| "eval_loss": 0.8515135645866394, | |
| "eval_runtime": 169.0764, | |
| "eval_samples_per_second": 1.283, | |
| "eval_steps_per_second": 0.166, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "learning_rate": 4.905887064477374e-06, | |
| "loss": 0.5174, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 45.01, | |
| "learning_rate": 4.7056467761313585e-06, | |
| "loss": 0.405, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 45.01, | |
| "learning_rate": 4.505406487785343e-06, | |
| "loss": 0.5241, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 45.01, | |
| "learning_rate": 4.305166199439328e-06, | |
| "loss": 0.6818, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 45.02, | |
| "learning_rate": 4.1049259110933125e-06, | |
| "loss": 0.5684, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 45.02, | |
| "eval_accuracy": 0.7096774193548387, | |
| "eval_loss": 0.9309377074241638, | |
| "eval_runtime": 169.732, | |
| "eval_samples_per_second": 1.278, | |
| "eval_steps_per_second": 0.165, | |
| "step": 2576 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "learning_rate": 3.904685622747297e-06, | |
| "loss": 0.4354, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 46.01, | |
| "learning_rate": 3.704445334401282e-06, | |
| "loss": 0.3822, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 46.01, | |
| "learning_rate": 3.5042050460552665e-06, | |
| "loss": 0.5717, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 46.01, | |
| "learning_rate": 3.303964757709251e-06, | |
| "loss": 0.2871, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 46.02, | |
| "learning_rate": 3.103724469363236e-06, | |
| "loss": 0.5375, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 46.02, | |
| "learning_rate": 2.9034841810172205e-06, | |
| "loss": 0.4406, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 46.02, | |
| "eval_accuracy": 0.7465437788018433, | |
| "eval_loss": 0.8826016783714294, | |
| "eval_runtime": 169.4846, | |
| "eval_samples_per_second": 1.28, | |
| "eval_steps_per_second": 0.165, | |
| "step": 2632 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "learning_rate": 2.7032438926712056e-06, | |
| "loss": 0.5365, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 47.01, | |
| "learning_rate": 2.5030036043251903e-06, | |
| "loss": 0.3124, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 47.01, | |
| "learning_rate": 2.3027633159791754e-06, | |
| "loss": 0.3491, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 47.01, | |
| "learning_rate": 2.10252302763316e-06, | |
| "loss": 0.4527, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 47.02, | |
| "learning_rate": 1.9022827392871447e-06, | |
| "loss": 0.6164, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 47.02, | |
| "eval_accuracy": 0.695852534562212, | |
| "eval_loss": 0.8993560075759888, | |
| "eval_runtime": 168.0031, | |
| "eval_samples_per_second": 1.292, | |
| "eval_steps_per_second": 0.167, | |
| "step": 2688 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "learning_rate": 1.7020424509411294e-06, | |
| "loss": 0.2574, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "learning_rate": 1.501802162595114e-06, | |
| "loss": 0.2911, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 48.01, | |
| "learning_rate": 1.301561874249099e-06, | |
| "loss": 0.4747, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 48.01, | |
| "learning_rate": 1.1013215859030839e-06, | |
| "loss": 0.4525, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 48.02, | |
| "learning_rate": 9.010812975570685e-07, | |
| "loss": 0.351, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 48.02, | |
| "learning_rate": 7.008410092110533e-07, | |
| "loss": 0.4549, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 48.02, | |
| "eval_accuracy": 0.7188940092165899, | |
| "eval_loss": 0.8699988722801208, | |
| "eval_runtime": 168.7472, | |
| "eval_samples_per_second": 1.286, | |
| "eval_steps_per_second": 0.166, | |
| "step": 2744 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "learning_rate": 5.006007208650381e-07, | |
| "loss": 0.4566, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 49.01, | |
| "learning_rate": 3.003604325190229e-07, | |
| "loss": 0.4441, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 49.01, | |
| "learning_rate": 1.0012014417300761e-07, | |
| "loss": 0.3453, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 49.01, | |
| "eval_accuracy": 0.7188940092165899, | |
| "eval_loss": 0.8821613788604736, | |
| "eval_runtime": 168.772, | |
| "eval_samples_per_second": 1.286, | |
| "eval_steps_per_second": 0.166, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 49.01, | |
| "step": 2775, | |
| "total_flos": 2.7602315185605673e+19, | |
| "train_loss": 0.7408499845298561, | |
| "train_runtime": 29540.8546, | |
| "train_samples_per_second": 0.752, | |
| "train_steps_per_second": 0.094 | |
| }, | |
| { | |
| "epoch": 49.01, | |
| "eval_accuracy": 0.7824074074074074, | |
| "eval_loss": 0.6378526091575623, | |
| "eval_runtime": 176.2386, | |
| "eval_samples_per_second": 1.226, | |
| "eval_steps_per_second": 0.153, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 49.01, | |
| "eval_accuracy": 0.7824074074074074, | |
| "eval_loss": 0.6378525495529175, | |
| "eval_runtime": 181.9628, | |
| "eval_samples_per_second": 1.187, | |
| "eval_steps_per_second": 0.148, | |
| "step": 2775 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 2775, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 500, | |
| "total_flos": 2.7602315185605673e+19, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |