| { | |
| "best_metric": 0.7834821428571429, | |
| "best_model_checkpoint": "/content/10epcoh1/checkpoint-600", | |
| "epoch": 10.0, | |
| "global_step": 750, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 2.1275, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 1.8422, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4e-05, | |
| "loss": 1.5182, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 5.333333333333333e-05, | |
| "loss": 1.2899, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 1.1166, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 8e-05, | |
| "loss": 0.9772, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 9.333333333333334e-05, | |
| "loss": 1.0362, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6339285714285714, | |
| "eval_loss": 1.1306579113006592, | |
| "eval_runtime": 15.6391, | |
| "eval_samples_per_second": 28.646, | |
| "eval_steps_per_second": 3.581, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 9.925925925925926e-05, | |
| "loss": 1.1734, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 9.777777777777778e-05, | |
| "loss": 0.9443, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 9.62962962962963e-05, | |
| "loss": 0.8425, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 9.481481481481483e-05, | |
| "loss": 0.9121, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 9.333333333333334e-05, | |
| "loss": 0.7943, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 9.185185185185186e-05, | |
| "loss": 0.8326, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 9.037037037037038e-05, | |
| "loss": 0.8621, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 8.888888888888889e-05, | |
| "loss": 0.7188, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7366071428571429, | |
| "eval_loss": 0.7066014409065247, | |
| "eval_runtime": 15.9611, | |
| "eval_samples_per_second": 28.068, | |
| "eval_steps_per_second": 3.509, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 8.740740740740741e-05, | |
| "loss": 0.4786, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 8.592592592592593e-05, | |
| "loss": 0.5607, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 8.444444444444444e-05, | |
| "loss": 0.5072, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 8.296296296296296e-05, | |
| "loss": 0.5531, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 8.148148148148148e-05, | |
| "loss": 0.4221, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 8e-05, | |
| "loss": 0.5585, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 7.851851851851852e-05, | |
| "loss": 0.6219, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7299107142857143, | |
| "eval_loss": 0.7877911925315857, | |
| "eval_runtime": 17.0375, | |
| "eval_samples_per_second": 26.295, | |
| "eval_steps_per_second": 3.287, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 7.703703703703704e-05, | |
| "loss": 0.5331, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 7.555555555555556e-05, | |
| "loss": 0.3028, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 7.407407407407407e-05, | |
| "loss": 0.3088, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 7.25925925925926e-05, | |
| "loss": 0.3205, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 7.111111111111112e-05, | |
| "loss": 0.2972, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 6.962962962962964e-05, | |
| "loss": 0.3062, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 6.814814814814815e-05, | |
| "loss": 0.3865, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.3372, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7767857142857143, | |
| "eval_loss": 0.6498553156852722, | |
| "eval_runtime": 15.0316, | |
| "eval_samples_per_second": 29.804, | |
| "eval_steps_per_second": 3.725, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 6.51851851851852e-05, | |
| "loss": 0.1711, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 6.37037037037037e-05, | |
| "loss": 0.2188, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 6.222222222222222e-05, | |
| "loss": 0.3254, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 6.074074074074074e-05, | |
| "loss": 0.2683, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 5.925925925925926e-05, | |
| "loss": 0.2208, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 5.7777777777777776e-05, | |
| "loss": 0.1729, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "learning_rate": 5.62962962962963e-05, | |
| "loss": 0.2024, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.765625, | |
| "eval_loss": 0.7129976153373718, | |
| "eval_runtime": 15.0955, | |
| "eval_samples_per_second": 29.678, | |
| "eval_steps_per_second": 3.71, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 5.4814814814814817e-05, | |
| "loss": 0.2077, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "learning_rate": 5.333333333333333e-05, | |
| "loss": 0.17, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "learning_rate": 5.185185185185185e-05, | |
| "loss": 0.1838, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.47, | |
| "learning_rate": 5.0370370370370366e-05, | |
| "loss": 0.2272, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 4.888888888888889e-05, | |
| "loss": 0.185, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "learning_rate": 4.740740740740741e-05, | |
| "loss": 0.1832, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 5.87, | |
| "learning_rate": 4.592592592592593e-05, | |
| "loss": 0.1449, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.169, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.7790178571428571, | |
| "eval_loss": 0.756848156452179, | |
| "eval_runtime": 14.9826, | |
| "eval_samples_per_second": 29.901, | |
| "eval_steps_per_second": 3.738, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "learning_rate": 4.296296296296296e-05, | |
| "loss": 0.1311, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 6.27, | |
| "learning_rate": 4.148148148148148e-05, | |
| "loss": 0.1196, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 4e-05, | |
| "loss": 0.12, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "learning_rate": 3.851851851851852e-05, | |
| "loss": 0.1471, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.1104, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "learning_rate": 3.555555555555556e-05, | |
| "loss": 0.1529, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 6.93, | |
| "learning_rate": 3.4074074074074077e-05, | |
| "loss": 0.1375, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.7723214285714286, | |
| "eval_loss": 0.8526908159255981, | |
| "eval_runtime": 15.1218, | |
| "eval_samples_per_second": 29.626, | |
| "eval_steps_per_second": 3.703, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 7.07, | |
| "learning_rate": 3.25925925925926e-05, | |
| "loss": 0.1935, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 3.111111111111111e-05, | |
| "loss": 0.131, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 7.33, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 0.0954, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 7.47, | |
| "learning_rate": 2.814814814814815e-05, | |
| "loss": 0.0971, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 7.6, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 0.1179, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 7.73, | |
| "learning_rate": 2.5185185185185183e-05, | |
| "loss": 0.1074, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 7.87, | |
| "learning_rate": 2.3703703703703707e-05, | |
| "loss": 0.1349, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.0893, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.7834821428571429, | |
| "eval_loss": 0.9136894941329956, | |
| "eval_runtime": 14.9574, | |
| "eval_samples_per_second": 29.952, | |
| "eval_steps_per_second": 3.744, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 8.13, | |
| "learning_rate": 2.074074074074074e-05, | |
| "loss": 0.0898, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 8.27, | |
| "learning_rate": 1.925925925925926e-05, | |
| "loss": 0.1095, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "learning_rate": 1.777777777777778e-05, | |
| "loss": 0.0696, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 8.53, | |
| "learning_rate": 1.62962962962963e-05, | |
| "loss": 0.1215, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 8.67, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 0.1103, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.1112, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 8.93, | |
| "learning_rate": 1.1851851851851853e-05, | |
| "loss": 0.0804, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.7834821428571429, | |
| "eval_loss": 0.9393314719200134, | |
| "eval_runtime": 15.2041, | |
| "eval_samples_per_second": 29.466, | |
| "eval_steps_per_second": 3.683, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 9.07, | |
| "learning_rate": 1.037037037037037e-05, | |
| "loss": 0.1229, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "learning_rate": 8.88888888888889e-06, | |
| "loss": 0.078, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 9.33, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.068, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 5.925925925925927e-06, | |
| "loss": 0.1024, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 4.444444444444445e-06, | |
| "loss": 0.0794, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 9.73, | |
| "learning_rate": 2.9629629629629633e-06, | |
| "loss": 0.0874, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 9.87, | |
| "learning_rate": 1.4814814814814817e-06, | |
| "loss": 0.0562, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.11, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.7723214285714286, | |
| "eval_loss": 0.9582878947257996, | |
| "eval_runtime": 15.0752, | |
| "eval_samples_per_second": 29.718, | |
| "eval_steps_per_second": 3.715, | |
| "step": 750 | |
| } | |
| ], | |
| "max_steps": 750, | |
| "num_train_epochs": 10, | |
| "total_flos": 4.90627722230102e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |