| { | |
| "best_metric": 0.7818181818181819, | |
| "best_model_checkpoint": "resnet-50-finetuned\\checkpoint-1190", | |
| "epoch": 100.0, | |
| "global_step": 1400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.5714285714285714e-06, | |
| "loss": 1.7972, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.11363636363636363, | |
| "eval_loss": 1.800904393196106, | |
| "eval_runtime": 5.5218, | |
| "eval_samples_per_second": 79.685, | |
| "eval_steps_per_second": 1.268, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 7.142857142857143e-06, | |
| "loss": 1.7991, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.16136363636363638, | |
| "eval_loss": 1.7934340238571167, | |
| "eval_runtime": 3.2902, | |
| "eval_samples_per_second": 133.73, | |
| "eval_steps_per_second": 2.128, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1.0714285714285714e-05, | |
| "loss": 1.7925, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 1.7871, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.2, | |
| "eval_loss": 1.78143310546875, | |
| "eval_runtime": 3.2024, | |
| "eval_samples_per_second": 137.395, | |
| "eval_steps_per_second": 2.186, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 1.785714285714286e-05, | |
| "loss": 1.7813, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.20909090909090908, | |
| "eval_loss": 1.7663880586624146, | |
| "eval_runtime": 3.3082, | |
| "eval_samples_per_second": 133.005, | |
| "eval_steps_per_second": 2.116, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 2.1428571428571428e-05, | |
| "loss": 1.7673, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.7602, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.2772727272727273, | |
| "eval_loss": 1.7464295625686646, | |
| "eval_runtime": 3.3301, | |
| "eval_samples_per_second": 132.128, | |
| "eval_steps_per_second": 2.102, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 1.7455, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.2840909090909091, | |
| "eval_loss": 1.726538896560669, | |
| "eval_runtime": 3.2579, | |
| "eval_samples_per_second": 135.057, | |
| "eval_steps_per_second": 2.149, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 6.43, | |
| "learning_rate": 3.2142857142857144e-05, | |
| "loss": 1.7321, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.2727272727272727, | |
| "eval_loss": 1.7056454420089722, | |
| "eval_runtime": 3.2693, | |
| "eval_samples_per_second": 134.587, | |
| "eval_steps_per_second": 2.141, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 1.7215, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 7.86, | |
| "learning_rate": 3.928571428571429e-05, | |
| "loss": 1.706, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.3068181818181818, | |
| "eval_loss": 1.6843111515045166, | |
| "eval_runtime": 3.2827, | |
| "eval_samples_per_second": 134.038, | |
| "eval_steps_per_second": 2.132, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 1.6891, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.325, | |
| "eval_loss": 1.6573911905288696, | |
| "eval_runtime": 3.1775, | |
| "eval_samples_per_second": 138.473, | |
| "eval_steps_per_second": 2.203, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 9.29, | |
| "learning_rate": 4.642857142857143e-05, | |
| "loss": 1.6751, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6524, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.3090909090909091, | |
| "eval_loss": 1.6302080154418945, | |
| "eval_runtime": 3.3459, | |
| "eval_samples_per_second": 131.503, | |
| "eval_steps_per_second": 2.092, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 10.71, | |
| "learning_rate": 4.960317460317461e-05, | |
| "loss": 1.6348, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.3613636363636364, | |
| "eval_loss": 1.5982272624969482, | |
| "eval_runtime": 3.2269, | |
| "eval_samples_per_second": 136.356, | |
| "eval_steps_per_second": 2.169, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 11.43, | |
| "learning_rate": 4.9206349206349204e-05, | |
| "loss": 1.611, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.39545454545454545, | |
| "eval_loss": 1.556486964225769, | |
| "eval_runtime": 3.2229, | |
| "eval_samples_per_second": 136.521, | |
| "eval_steps_per_second": 2.172, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 12.14, | |
| "learning_rate": 4.880952380952381e-05, | |
| "loss": 1.5891, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 12.86, | |
| "learning_rate": 4.841269841269841e-05, | |
| "loss": 1.5673, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.41363636363636364, | |
| "eval_loss": 1.516886591911316, | |
| "eval_runtime": 3.2733, | |
| "eval_samples_per_second": 134.423, | |
| "eval_steps_per_second": 2.139, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 13.57, | |
| "learning_rate": 4.801587301587302e-05, | |
| "loss": 1.5239, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.509090909090909, | |
| "eval_loss": 1.4703104496002197, | |
| "eval_runtime": 3.2812, | |
| "eval_samples_per_second": 134.096, | |
| "eval_steps_per_second": 2.133, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 14.29, | |
| "learning_rate": 4.761904761904762e-05, | |
| "loss": 1.5131, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 4.722222222222222e-05, | |
| "loss": 1.4698, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.5363636363636364, | |
| "eval_loss": 1.4071372747421265, | |
| "eval_runtime": 3.3595, | |
| "eval_samples_per_second": 130.973, | |
| "eval_steps_per_second": 2.084, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 15.71, | |
| "learning_rate": 4.682539682539683e-05, | |
| "loss": 1.4277, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.5886363636363636, | |
| "eval_loss": 1.3305206298828125, | |
| "eval_runtime": 3.3151, | |
| "eval_samples_per_second": 132.725, | |
| "eval_steps_per_second": 2.112, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 16.43, | |
| "learning_rate": 4.642857142857143e-05, | |
| "loss": 1.3798, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.6068181818181818, | |
| "eval_loss": 1.250695824623108, | |
| "eval_runtime": 3.348, | |
| "eval_samples_per_second": 131.42, | |
| "eval_steps_per_second": 2.091, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 17.14, | |
| "learning_rate": 4.603174603174603e-05, | |
| "loss": 1.355, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 17.86, | |
| "learning_rate": 4.563492063492064e-05, | |
| "loss": 1.2858, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.6409090909090909, | |
| "eval_loss": 1.1516846418380737, | |
| "eval_runtime": 3.35, | |
| "eval_samples_per_second": 131.342, | |
| "eval_steps_per_second": 2.09, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 18.57, | |
| "learning_rate": 4.523809523809524e-05, | |
| "loss": 1.2543, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.6659090909090909, | |
| "eval_loss": 1.0930873155593872, | |
| "eval_runtime": 3.4597, | |
| "eval_samples_per_second": 127.177, | |
| "eval_steps_per_second": 2.023, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 19.29, | |
| "learning_rate": 4.4841269841269846e-05, | |
| "loss": 1.2006, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 1.1696, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.675, | |
| "eval_loss": 1.012363314628601, | |
| "eval_runtime": 3.3077, | |
| "eval_samples_per_second": 133.023, | |
| "eval_steps_per_second": 2.116, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 20.71, | |
| "learning_rate": 4.404761904761905e-05, | |
| "loss": 1.1124, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.6931818181818182, | |
| "eval_loss": 0.954047679901123, | |
| "eval_runtime": 3.3411, | |
| "eval_samples_per_second": 131.693, | |
| "eval_steps_per_second": 2.095, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 21.43, | |
| "learning_rate": 4.3650793650793655e-05, | |
| "loss": 1.059, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.7022727272727273, | |
| "eval_loss": 0.9010851979255676, | |
| "eval_runtime": 3.6911, | |
| "eval_samples_per_second": 119.205, | |
| "eval_steps_per_second": 1.896, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 22.14, | |
| "learning_rate": 4.3253968253968256e-05, | |
| "loss": 1.0318, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 22.86, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 1.0006, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.7090909090909091, | |
| "eval_loss": 0.8692610859870911, | |
| "eval_runtime": 3.4254, | |
| "eval_samples_per_second": 128.451, | |
| "eval_steps_per_second": 2.044, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 23.57, | |
| "learning_rate": 4.2460317460317464e-05, | |
| "loss": 0.9606, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.6977272727272728, | |
| "eval_loss": 0.8458234667778015, | |
| "eval_runtime": 3.7789, | |
| "eval_samples_per_second": 116.436, | |
| "eval_steps_per_second": 1.852, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 24.29, | |
| "learning_rate": 4.2063492063492065e-05, | |
| "loss": 0.9541, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.9146, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.7227272727272728, | |
| "eval_loss": 0.8226051926612854, | |
| "eval_runtime": 3.375, | |
| "eval_samples_per_second": 130.371, | |
| "eval_steps_per_second": 2.074, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 25.71, | |
| "learning_rate": 4.126984126984127e-05, | |
| "loss": 0.8864, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.7159090909090909, | |
| "eval_loss": 0.8187159895896912, | |
| "eval_runtime": 3.4251, | |
| "eval_samples_per_second": 128.462, | |
| "eval_steps_per_second": 2.044, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 26.43, | |
| "learning_rate": 4.0873015873015874e-05, | |
| "loss": 0.8864, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.7227272727272728, | |
| "eval_loss": 0.7862333655357361, | |
| "eval_runtime": 3.3921, | |
| "eval_samples_per_second": 129.714, | |
| "eval_steps_per_second": 2.064, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 27.14, | |
| "learning_rate": 4.047619047619048e-05, | |
| "loss": 0.8447, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 27.86, | |
| "learning_rate": 4.007936507936508e-05, | |
| "loss": 0.8458, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.7295454545454545, | |
| "eval_loss": 0.7686573266983032, | |
| "eval_runtime": 3.4126, | |
| "eval_samples_per_second": 128.935, | |
| "eval_steps_per_second": 2.051, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 28.57, | |
| "learning_rate": 3.968253968253968e-05, | |
| "loss": 0.8337, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.747409999370575, | |
| "eval_runtime": 3.4047, | |
| "eval_samples_per_second": 129.233, | |
| "eval_steps_per_second": 2.056, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 29.29, | |
| "learning_rate": 3.928571428571429e-05, | |
| "loss": 0.8107, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.7943, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.7454545454545455, | |
| "eval_loss": 0.7368342876434326, | |
| "eval_runtime": 3.4657, | |
| "eval_samples_per_second": 126.957, | |
| "eval_steps_per_second": 2.02, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 30.71, | |
| "learning_rate": 3.84920634920635e-05, | |
| "loss": 0.7884, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.7454545454545455, | |
| "eval_loss": 0.7331739068031311, | |
| "eval_runtime": 3.4308, | |
| "eval_samples_per_second": 128.249, | |
| "eval_steps_per_second": 2.04, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 31.43, | |
| "learning_rate": 3.809523809523809e-05, | |
| "loss": 0.7495, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.725, | |
| "eval_loss": 0.7354092597961426, | |
| "eval_runtime": 3.3899, | |
| "eval_samples_per_second": 129.796, | |
| "eval_steps_per_second": 2.065, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 32.14, | |
| "learning_rate": 3.76984126984127e-05, | |
| "loss": 0.78, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 32.86, | |
| "learning_rate": 3.730158730158731e-05, | |
| "loss": 0.7503, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.7477272727272727, | |
| "eval_loss": 0.7180919051170349, | |
| "eval_runtime": 3.3351, | |
| "eval_samples_per_second": 131.931, | |
| "eval_steps_per_second": 2.099, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 33.57, | |
| "learning_rate": 3.690476190476191e-05, | |
| "loss": 0.7358, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.7477272727272727, | |
| "eval_loss": 0.7007948160171509, | |
| "eval_runtime": 3.4029, | |
| "eval_samples_per_second": 129.301, | |
| "eval_steps_per_second": 2.057, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 34.29, | |
| "learning_rate": 3.650793650793651e-05, | |
| "loss": 0.7605, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "learning_rate": 3.611111111111111e-05, | |
| "loss": 0.7229, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.740909090909091, | |
| "eval_loss": 0.6959581971168518, | |
| "eval_runtime": 3.6574, | |
| "eval_samples_per_second": 120.304, | |
| "eval_steps_per_second": 1.914, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 35.71, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 0.7114, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.7431818181818182, | |
| "eval_loss": 0.6837091445922852, | |
| "eval_runtime": 3.6041, | |
| "eval_samples_per_second": 122.083, | |
| "eval_steps_per_second": 1.942, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 36.43, | |
| "learning_rate": 3.5317460317460324e-05, | |
| "loss": 0.7075, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.740909090909091, | |
| "eval_loss": 0.6922788023948669, | |
| "eval_runtime": 3.3849, | |
| "eval_samples_per_second": 129.987, | |
| "eval_steps_per_second": 2.068, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 37.14, | |
| "learning_rate": 3.492063492063492e-05, | |
| "loss": 0.6915, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 37.86, | |
| "learning_rate": 3.4523809523809526e-05, | |
| "loss": 0.682, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.7431818181818182, | |
| "eval_loss": 0.6930937767028809, | |
| "eval_runtime": 3.4683, | |
| "eval_samples_per_second": 126.864, | |
| "eval_steps_per_second": 2.018, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 38.57, | |
| "learning_rate": 3.412698412698413e-05, | |
| "loss": 0.6626, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.740909090909091, | |
| "eval_loss": 0.6872156262397766, | |
| "eval_runtime": 3.3949, | |
| "eval_samples_per_second": 129.605, | |
| "eval_steps_per_second": 2.062, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 39.29, | |
| "learning_rate": 3.3730158730158734e-05, | |
| "loss": 0.6708, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.6688, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.6758830547332764, | |
| "eval_runtime": 3.2304, | |
| "eval_samples_per_second": 136.208, | |
| "eval_steps_per_second": 2.167, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 40.71, | |
| "learning_rate": 3.2936507936507936e-05, | |
| "loss": 0.655, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.7340909090909091, | |
| "eval_loss": 0.7006358504295349, | |
| "eval_runtime": 3.3002, | |
| "eval_samples_per_second": 133.326, | |
| "eval_steps_per_second": 2.121, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 41.43, | |
| "learning_rate": 3.253968253968254e-05, | |
| "loss": 0.6533, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.6774057149887085, | |
| "eval_runtime": 3.351, | |
| "eval_samples_per_second": 131.303, | |
| "eval_steps_per_second": 2.089, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 42.14, | |
| "learning_rate": 3.2142857142857144e-05, | |
| "loss": 0.6488, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 42.86, | |
| "learning_rate": 3.1746031746031745e-05, | |
| "loss": 0.6215, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.7454545454545455, | |
| "eval_loss": 0.6663152575492859, | |
| "eval_runtime": 3.4833, | |
| "eval_samples_per_second": 126.317, | |
| "eval_steps_per_second": 2.01, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 43.57, | |
| "learning_rate": 3.134920634920635e-05, | |
| "loss": 0.6267, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.7545454545454545, | |
| "eval_loss": 0.6608263850212097, | |
| "eval_runtime": 3.375, | |
| "eval_samples_per_second": 130.371, | |
| "eval_steps_per_second": 2.074, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 44.29, | |
| "learning_rate": 3.095238095238095e-05, | |
| "loss": 0.6383, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "learning_rate": 3.055555555555556e-05, | |
| "loss": 0.6122, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.7477272727272727, | |
| "eval_loss": 0.6523904800415039, | |
| "eval_runtime": 3.3102, | |
| "eval_samples_per_second": 132.923, | |
| "eval_steps_per_second": 2.115, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 45.71, | |
| "learning_rate": 3.0158730158730158e-05, | |
| "loss": 0.6047, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.7477272727272727, | |
| "eval_loss": 0.6757220029830933, | |
| "eval_runtime": 3.3012, | |
| "eval_samples_per_second": 133.286, | |
| "eval_steps_per_second": 2.12, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 46.43, | |
| "learning_rate": 2.9761904761904762e-05, | |
| "loss": 0.6135, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.7431818181818182, | |
| "eval_loss": 0.6492685675621033, | |
| "eval_runtime": 3.4379, | |
| "eval_samples_per_second": 127.986, | |
| "eval_steps_per_second": 2.036, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 47.14, | |
| "learning_rate": 2.9365079365079366e-05, | |
| "loss": 0.6145, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 47.86, | |
| "learning_rate": 2.8968253968253974e-05, | |
| "loss": 0.5805, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.6503338813781738, | |
| "eval_runtime": 3.383, | |
| "eval_samples_per_second": 130.064, | |
| "eval_steps_per_second": 2.069, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 48.57, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 0.6124, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.7454545454545455, | |
| "eval_loss": 0.6626009941101074, | |
| "eval_runtime": 3.5236, | |
| "eval_samples_per_second": 124.873, | |
| "eval_steps_per_second": 1.987, | |
| "step": 686 | |
| }, | |
| { | |
| "epoch": 49.29, | |
| "learning_rate": 2.8174603174603175e-05, | |
| "loss": 0.6079, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.5826, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.7522727272727273, | |
| "eval_loss": 0.6511955857276917, | |
| "eval_runtime": 3.2723, | |
| "eval_samples_per_second": 134.464, | |
| "eval_steps_per_second": 2.139, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 50.71, | |
| "learning_rate": 2.7380952380952383e-05, | |
| "loss": 0.5698, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.7477272727272727, | |
| "eval_loss": 0.6589775085449219, | |
| "eval_runtime": 3.4253, | |
| "eval_samples_per_second": 128.455, | |
| "eval_steps_per_second": 2.044, | |
| "step": 714 | |
| }, | |
| { | |
| "epoch": 51.43, | |
| "learning_rate": 2.6984126984126984e-05, | |
| "loss": 0.5721, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.7454545454545455, | |
| "eval_loss": 0.6558127403259277, | |
| "eval_runtime": 3.2646, | |
| "eval_samples_per_second": 134.777, | |
| "eval_steps_per_second": 2.144, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 52.14, | |
| "learning_rate": 2.6587301587301588e-05, | |
| "loss": 0.5912, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 52.86, | |
| "learning_rate": 2.6190476190476192e-05, | |
| "loss": 0.5569, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.7454545454545455, | |
| "eval_loss": 0.6654322743415833, | |
| "eval_runtime": 3.2932, | |
| "eval_samples_per_second": 133.609, | |
| "eval_steps_per_second": 2.126, | |
| "step": 742 | |
| }, | |
| { | |
| "epoch": 53.57, | |
| "learning_rate": 2.5793650793650796e-05, | |
| "loss": 0.573, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.7545454545454545, | |
| "eval_loss": 0.636202335357666, | |
| "eval_runtime": 3.3271, | |
| "eval_samples_per_second": 132.247, | |
| "eval_steps_per_second": 2.104, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 54.29, | |
| "learning_rate": 2.5396825396825397e-05, | |
| "loss": 0.5816, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.543, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.7636363636363637, | |
| "eval_loss": 0.6368376016616821, | |
| "eval_runtime": 3.2054, | |
| "eval_samples_per_second": 137.267, | |
| "eval_steps_per_second": 2.184, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 55.71, | |
| "learning_rate": 2.4603174603174602e-05, | |
| "loss": 0.5494, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.759090909090909, | |
| "eval_loss": 0.6263792514801025, | |
| "eval_runtime": 3.2663, | |
| "eval_samples_per_second": 134.71, | |
| "eval_steps_per_second": 2.143, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 56.43, | |
| "learning_rate": 2.4206349206349206e-05, | |
| "loss": 0.5598, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.7681818181818182, | |
| "eval_loss": 0.627074658870697, | |
| "eval_runtime": 3.4193, | |
| "eval_samples_per_second": 128.683, | |
| "eval_steps_per_second": 2.047, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 57.14, | |
| "learning_rate": 2.380952380952381e-05, | |
| "loss": 0.5655, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 57.86, | |
| "learning_rate": 2.3412698412698414e-05, | |
| "loss": 0.5412, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.7522727272727273, | |
| "eval_loss": 0.6506673693656921, | |
| "eval_runtime": 3.2684, | |
| "eval_samples_per_second": 134.623, | |
| "eval_steps_per_second": 2.142, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 58.57, | |
| "learning_rate": 2.3015873015873015e-05, | |
| "loss": 0.5512, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.7568181818181818, | |
| "eval_loss": 0.6446354985237122, | |
| "eval_runtime": 3.3303, | |
| "eval_samples_per_second": 132.119, | |
| "eval_steps_per_second": 2.102, | |
| "step": 826 | |
| }, | |
| { | |
| "epoch": 59.29, | |
| "learning_rate": 2.261904761904762e-05, | |
| "loss": 0.5217, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.5504, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.7727272727272727, | |
| "eval_loss": 0.6208813190460205, | |
| "eval_runtime": 3.2503, | |
| "eval_samples_per_second": 135.372, | |
| "eval_steps_per_second": 2.154, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 60.71, | |
| "learning_rate": 2.1825396825396827e-05, | |
| "loss": 0.5304, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_accuracy": 0.7568181818181818, | |
| "eval_loss": 0.6428102850914001, | |
| "eval_runtime": 3.4103, | |
| "eval_samples_per_second": 129.021, | |
| "eval_steps_per_second": 2.053, | |
| "step": 854 | |
| }, | |
| { | |
| "epoch": 61.43, | |
| "learning_rate": 2.1428571428571428e-05, | |
| "loss": 0.5238, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.7613636363636364, | |
| "eval_loss": 0.6323724985122681, | |
| "eval_runtime": 3.2991, | |
| "eval_samples_per_second": 133.368, | |
| "eval_steps_per_second": 2.122, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 62.14, | |
| "learning_rate": 2.1031746031746032e-05, | |
| "loss": 0.5344, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 62.86, | |
| "learning_rate": 2.0634920634920636e-05, | |
| "loss": 0.5298, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_accuracy": 0.7568181818181818, | |
| "eval_loss": 0.6347512006759644, | |
| "eval_runtime": 3.2796, | |
| "eval_samples_per_second": 134.162, | |
| "eval_steps_per_second": 2.134, | |
| "step": 882 | |
| }, | |
| { | |
| "epoch": 63.57, | |
| "learning_rate": 2.023809523809524e-05, | |
| "loss": 0.4965, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.7545454545454545, | |
| "eval_loss": 0.6351690292358398, | |
| "eval_runtime": 3.394, | |
| "eval_samples_per_second": 129.639, | |
| "eval_steps_per_second": 2.062, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 64.29, | |
| "learning_rate": 1.984126984126984e-05, | |
| "loss": 0.5338, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "learning_rate": 1.9444444444444445e-05, | |
| "loss": 0.5188, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_accuracy": 0.7704545454545455, | |
| "eval_loss": 0.6352004408836365, | |
| "eval_runtime": 3.3712, | |
| "eval_samples_per_second": 130.519, | |
| "eval_steps_per_second": 2.076, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 65.71, | |
| "learning_rate": 1.9047619047619046e-05, | |
| "loss": 0.5081, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.7681818181818182, | |
| "eval_loss": 0.6369162201881409, | |
| "eval_runtime": 3.3987, | |
| "eval_samples_per_second": 129.462, | |
| "eval_steps_per_second": 2.06, | |
| "step": 924 | |
| }, | |
| { | |
| "epoch": 66.43, | |
| "learning_rate": 1.8650793650793654e-05, | |
| "loss": 0.4725, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_accuracy": 0.775, | |
| "eval_loss": 0.6235827207565308, | |
| "eval_runtime": 3.2862, | |
| "eval_samples_per_second": 133.893, | |
| "eval_steps_per_second": 2.13, | |
| "step": 938 | |
| }, | |
| { | |
| "epoch": 67.14, | |
| "learning_rate": 1.8253968253968254e-05, | |
| "loss": 0.52, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 67.86, | |
| "learning_rate": 1.785714285714286e-05, | |
| "loss": 0.4977, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.7681818181818182, | |
| "eval_loss": 0.621067225933075, | |
| "eval_runtime": 3.3453, | |
| "eval_samples_per_second": 131.527, | |
| "eval_steps_per_second": 2.092, | |
| "step": 952 | |
| }, | |
| { | |
| "epoch": 68.57, | |
| "learning_rate": 1.746031746031746e-05, | |
| "loss": 0.5118, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_accuracy": 0.7568181818181818, | |
| "eval_loss": 0.6289528012275696, | |
| "eval_runtime": 3.3375, | |
| "eval_samples_per_second": 131.834, | |
| "eval_steps_per_second": 2.097, | |
| "step": 966 | |
| }, | |
| { | |
| "epoch": 69.29, | |
| "learning_rate": 1.7063492063492063e-05, | |
| "loss": 0.5001, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.4876, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.7636363636363637, | |
| "eval_loss": 0.6366029381752014, | |
| "eval_runtime": 3.2398, | |
| "eval_samples_per_second": 135.809, | |
| "eval_steps_per_second": 2.161, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 70.71, | |
| "learning_rate": 1.626984126984127e-05, | |
| "loss": 0.49, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_accuracy": 0.7727272727272727, | |
| "eval_loss": 0.6185997128486633, | |
| "eval_runtime": 3.2603, | |
| "eval_samples_per_second": 134.958, | |
| "eval_steps_per_second": 2.147, | |
| "step": 994 | |
| }, | |
| { | |
| "epoch": 71.43, | |
| "learning_rate": 1.5873015873015872e-05, | |
| "loss": 0.4912, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.7727272727272727, | |
| "eval_loss": 0.6244505643844604, | |
| "eval_runtime": 3.3698, | |
| "eval_samples_per_second": 130.572, | |
| "eval_steps_per_second": 2.077, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 72.14, | |
| "learning_rate": 1.5476190476190476e-05, | |
| "loss": 0.4971, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 72.86, | |
| "learning_rate": 1.5079365079365079e-05, | |
| "loss": 0.4774, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_accuracy": 0.7727272727272727, | |
| "eval_loss": 0.6223783493041992, | |
| "eval_runtime": 3.4233, | |
| "eval_samples_per_second": 128.533, | |
| "eval_steps_per_second": 2.045, | |
| "step": 1022 | |
| }, | |
| { | |
| "epoch": 73.57, | |
| "learning_rate": 1.4682539682539683e-05, | |
| "loss": 0.4972, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_accuracy": 0.7454545454545455, | |
| "eval_loss": 0.6407915353775024, | |
| "eval_runtime": 3.2294, | |
| "eval_samples_per_second": 136.25, | |
| "eval_steps_per_second": 2.168, | |
| "step": 1036 | |
| }, | |
| { | |
| "epoch": 74.29, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 0.4663, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.4973, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_accuracy": 0.7795454545454545, | |
| "eval_loss": 0.6241269707679749, | |
| "eval_runtime": 3.4141, | |
| "eval_samples_per_second": 128.879, | |
| "eval_steps_per_second": 2.05, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 75.71, | |
| "learning_rate": 1.3492063492063492e-05, | |
| "loss": 0.4807, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_accuracy": 0.7727272727272727, | |
| "eval_loss": 0.6188752055168152, | |
| "eval_runtime": 3.372, | |
| "eval_samples_per_second": 130.487, | |
| "eval_steps_per_second": 2.076, | |
| "step": 1064 | |
| }, | |
| { | |
| "epoch": 76.43, | |
| "learning_rate": 1.3095238095238096e-05, | |
| "loss": 0.4845, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_accuracy": 0.775, | |
| "eval_loss": 0.6290163397789001, | |
| "eval_runtime": 3.37, | |
| "eval_samples_per_second": 130.564, | |
| "eval_steps_per_second": 2.077, | |
| "step": 1078 | |
| }, | |
| { | |
| "epoch": 77.14, | |
| "learning_rate": 1.2698412698412699e-05, | |
| "loss": 0.4699, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 77.86, | |
| "learning_rate": 1.2301587301587301e-05, | |
| "loss": 0.4874, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_accuracy": 0.7772727272727272, | |
| "eval_loss": 0.6192808747291565, | |
| "eval_runtime": 3.365, | |
| "eval_samples_per_second": 130.758, | |
| "eval_steps_per_second": 2.08, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 78.57, | |
| "learning_rate": 1.1904761904761905e-05, | |
| "loss": 0.4898, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_accuracy": 0.775, | |
| "eval_loss": 0.643506646156311, | |
| "eval_runtime": 3.4199, | |
| "eval_samples_per_second": 128.66, | |
| "eval_steps_per_second": 2.047, | |
| "step": 1106 | |
| }, | |
| { | |
| "epoch": 79.29, | |
| "learning_rate": 1.1507936507936508e-05, | |
| "loss": 0.4844, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.4904, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_accuracy": 0.7613636363636364, | |
| "eval_loss": 0.6483902931213379, | |
| "eval_runtime": 3.373, | |
| "eval_samples_per_second": 130.448, | |
| "eval_steps_per_second": 2.075, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 80.71, | |
| "learning_rate": 1.0714285714285714e-05, | |
| "loss": 0.4702, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_accuracy": 0.7727272727272727, | |
| "eval_loss": 0.6238275170326233, | |
| "eval_runtime": 3.5076, | |
| "eval_samples_per_second": 125.441, | |
| "eval_steps_per_second": 1.996, | |
| "step": 1134 | |
| }, | |
| { | |
| "epoch": 81.43, | |
| "learning_rate": 1.0317460317460318e-05, | |
| "loss": 0.4802, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_accuracy": 0.7727272727272727, | |
| "eval_loss": 0.6386602520942688, | |
| "eval_runtime": 3.3979, | |
| "eval_samples_per_second": 129.491, | |
| "eval_steps_per_second": 2.06, | |
| "step": 1148 | |
| }, | |
| { | |
| "epoch": 82.14, | |
| "learning_rate": 9.92063492063492e-06, | |
| "loss": 0.4529, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 82.86, | |
| "learning_rate": 9.523809523809523e-06, | |
| "loss": 0.4635, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_accuracy": 0.7704545454545455, | |
| "eval_loss": 0.6206506490707397, | |
| "eval_runtime": 3.4119, | |
| "eval_samples_per_second": 128.961, | |
| "eval_steps_per_second": 2.052, | |
| "step": 1162 | |
| }, | |
| { | |
| "epoch": 83.57, | |
| "learning_rate": 9.126984126984127e-06, | |
| "loss": 0.4457, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_accuracy": 0.7659090909090909, | |
| "eval_loss": 0.6249757409095764, | |
| "eval_runtime": 3.4328, | |
| "eval_samples_per_second": 128.174, | |
| "eval_steps_per_second": 2.039, | |
| "step": 1176 | |
| }, | |
| { | |
| "epoch": 84.29, | |
| "learning_rate": 8.73015873015873e-06, | |
| "loss": 0.4665, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.4697, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_accuracy": 0.7818181818181819, | |
| "eval_loss": 0.611347496509552, | |
| "eval_runtime": 3.4099, | |
| "eval_samples_per_second": 129.037, | |
| "eval_steps_per_second": 2.053, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 85.71, | |
| "learning_rate": 7.936507936507936e-06, | |
| "loss": 0.4359, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_accuracy": 0.7659090909090909, | |
| "eval_loss": 0.637219250202179, | |
| "eval_runtime": 3.369, | |
| "eval_samples_per_second": 130.603, | |
| "eval_steps_per_second": 2.078, | |
| "step": 1204 | |
| }, | |
| { | |
| "epoch": 86.43, | |
| "learning_rate": 7.5396825396825394e-06, | |
| "loss": 0.4876, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_accuracy": 0.759090909090909, | |
| "eval_loss": 0.6338838338851929, | |
| "eval_runtime": 3.4298, | |
| "eval_samples_per_second": 128.286, | |
| "eval_steps_per_second": 2.041, | |
| "step": 1218 | |
| }, | |
| { | |
| "epoch": 87.14, | |
| "learning_rate": 7.142857142857143e-06, | |
| "loss": 0.4816, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 87.86, | |
| "learning_rate": 6.746031746031746e-06, | |
| "loss": 0.4574, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_accuracy": 0.7545454545454545, | |
| "eval_loss": 0.6318604946136475, | |
| "eval_runtime": 3.5206, | |
| "eval_samples_per_second": 124.979, | |
| "eval_steps_per_second": 1.988, | |
| "step": 1232 | |
| }, | |
| { | |
| "epoch": 88.57, | |
| "learning_rate": 6.349206349206349e-06, | |
| "loss": 0.4633, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_accuracy": 0.7727272727272727, | |
| "eval_loss": 0.6072612404823303, | |
| "eval_runtime": 3.6356, | |
| "eval_samples_per_second": 121.025, | |
| "eval_steps_per_second": 1.925, | |
| "step": 1246 | |
| }, | |
| { | |
| "epoch": 89.29, | |
| "learning_rate": 5.9523809523809525e-06, | |
| "loss": 0.4459, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.4548, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_accuracy": 0.7704545454545455, | |
| "eval_loss": 0.6304746866226196, | |
| "eval_runtime": 3.4518, | |
| "eval_samples_per_second": 127.471, | |
| "eval_steps_per_second": 2.028, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 90.71, | |
| "learning_rate": 5.158730158730159e-06, | |
| "loss": 0.4527, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_accuracy": 0.7681818181818182, | |
| "eval_loss": 0.6324154734611511, | |
| "eval_runtime": 3.5884, | |
| "eval_samples_per_second": 122.617, | |
| "eval_steps_per_second": 1.951, | |
| "step": 1274 | |
| }, | |
| { | |
| "epoch": 91.43, | |
| "learning_rate": 4.7619047619047615e-06, | |
| "loss": 0.4311, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_accuracy": 0.7795454545454545, | |
| "eval_loss": 0.6228455901145935, | |
| "eval_runtime": 3.543, | |
| "eval_samples_per_second": 124.187, | |
| "eval_steps_per_second": 1.976, | |
| "step": 1288 | |
| }, | |
| { | |
| "epoch": 92.14, | |
| "learning_rate": 4.365079365079365e-06, | |
| "loss": 0.4641, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 92.86, | |
| "learning_rate": 3.968253968253968e-06, | |
| "loss": 0.4499, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_accuracy": 0.7636363636363637, | |
| "eval_loss": 0.6188679337501526, | |
| "eval_runtime": 3.6596, | |
| "eval_samples_per_second": 120.231, | |
| "eval_steps_per_second": 1.913, | |
| "step": 1302 | |
| }, | |
| { | |
| "epoch": 93.57, | |
| "learning_rate": 3.5714285714285714e-06, | |
| "loss": 0.4333, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_accuracy": 0.7727272727272727, | |
| "eval_loss": 0.6302651166915894, | |
| "eval_runtime": 3.5367, | |
| "eval_samples_per_second": 124.41, | |
| "eval_steps_per_second": 1.979, | |
| "step": 1316 | |
| }, | |
| { | |
| "epoch": 94.29, | |
| "learning_rate": 3.1746031746031746e-06, | |
| "loss": 0.4647, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "learning_rate": 2.777777777777778e-06, | |
| "loss": 0.4526, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_accuracy": 0.7704545454545455, | |
| "eval_loss": 0.6163169145584106, | |
| "eval_runtime": 3.5271, | |
| "eval_samples_per_second": 124.747, | |
| "eval_steps_per_second": 1.985, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 95.71, | |
| "learning_rate": 2.3809523809523808e-06, | |
| "loss": 0.4709, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_accuracy": 0.7659090909090909, | |
| "eval_loss": 0.618194580078125, | |
| "eval_runtime": 3.4856, | |
| "eval_samples_per_second": 126.234, | |
| "eval_steps_per_second": 2.008, | |
| "step": 1344 | |
| }, | |
| { | |
| "epoch": 96.43, | |
| "learning_rate": 1.984126984126984e-06, | |
| "loss": 0.4451, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_accuracy": 0.7818181818181819, | |
| "eval_loss": 0.6048444509506226, | |
| "eval_runtime": 3.4925, | |
| "eval_samples_per_second": 125.984, | |
| "eval_steps_per_second": 2.004, | |
| "step": 1358 | |
| }, | |
| { | |
| "epoch": 97.14, | |
| "learning_rate": 1.5873015873015873e-06, | |
| "loss": 0.4617, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 97.86, | |
| "learning_rate": 1.1904761904761904e-06, | |
| "loss": 0.4174, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_accuracy": 0.7659090909090909, | |
| "eval_loss": 0.6300343871116638, | |
| "eval_runtime": 3.4255, | |
| "eval_samples_per_second": 128.45, | |
| "eval_steps_per_second": 2.044, | |
| "step": 1372 | |
| }, | |
| { | |
| "epoch": 98.57, | |
| "learning_rate": 7.936507936507937e-07, | |
| "loss": 0.4832, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_accuracy": 0.7704545454545455, | |
| "eval_loss": 0.6194254159927368, | |
| "eval_runtime": 3.5142, | |
| "eval_samples_per_second": 125.206, | |
| "eval_steps_per_second": 1.992, | |
| "step": 1386 | |
| }, | |
| { | |
| "epoch": 99.29, | |
| "learning_rate": 3.9682539682539683e-07, | |
| "loss": 0.4501, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.4508, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_accuracy": 0.7795454545454545, | |
| "eval_loss": 0.6144731640815735, | |
| "eval_runtime": 3.5121, | |
| "eval_samples_per_second": 125.28, | |
| "eval_steps_per_second": 1.993, | |
| "step": 1400 | |
| } | |
| ], | |
| "max_steps": 1400, | |
| "num_train_epochs": 100, | |
| "total_flos": 7.496586164267827e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |