| { | |
| "best_metric": 0.0011106810998171568, | |
| "best_model_checkpoint": "Result/OffsetTwo_batch16_step2000\\checkpoint-600", | |
| "epoch": 28.571428571428573, | |
| "global_step": 600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.000199, | |
| "loss": 0.6712, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.00019800000000000002, | |
| "loss": 0.7073, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.00019700000000000002, | |
| "loss": 0.3994, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.000196, | |
| "loss": 0.5316, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 0.000195, | |
| "loss": 0.6121, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 0.000194, | |
| "loss": 0.4975, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 0.000193, | |
| "loss": 0.5137, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 0.000192, | |
| "loss": 0.2739, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 0.000191, | |
| "loss": 0.6669, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 0.00019, | |
| "loss": 0.3004, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 0.00018899999999999999, | |
| "loss": 0.1061, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 0.000188, | |
| "loss": 0.2727, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "learning_rate": 0.00018700000000000002, | |
| "loss": 0.0707, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 0.00018600000000000002, | |
| "loss": 0.2655, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 0.00018500000000000002, | |
| "loss": 0.1479, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 7.62, | |
| "learning_rate": 0.00018400000000000003, | |
| "loss": 0.1231, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 8.1, | |
| "learning_rate": 0.000183, | |
| "loss": 0.0183, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "learning_rate": 0.000182, | |
| "loss": 0.0423, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 9.05, | |
| "learning_rate": 0.000181, | |
| "loss": 0.057, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 9.52, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0082, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 9.52, | |
| "eval_accuracy": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.006428680382668972, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.738, | |
| "eval_samples_per_second": 75.879, | |
| "eval_steps_per_second": 9.485, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.00017900000000000001, | |
| "loss": 0.0118, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 10.48, | |
| "learning_rate": 0.00017800000000000002, | |
| "loss": 0.007, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 10.95, | |
| "learning_rate": 0.00017700000000000002, | |
| "loss": 0.0056, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 11.43, | |
| "learning_rate": 0.00017600000000000002, | |
| "loss": 0.0048, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 11.9, | |
| "learning_rate": 0.000175, | |
| "loss": 0.0045, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 12.38, | |
| "learning_rate": 0.000174, | |
| "loss": 0.0042, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 12.86, | |
| "learning_rate": 0.000173, | |
| "loss": 0.004, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 13.33, | |
| "learning_rate": 0.000172, | |
| "loss": 0.0036, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 13.81, | |
| "learning_rate": 0.000171, | |
| "loss": 0.0034, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 14.29, | |
| "learning_rate": 0.00017, | |
| "loss": 0.0032, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 14.76, | |
| "learning_rate": 0.00016900000000000002, | |
| "loss": 0.0031, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 15.24, | |
| "learning_rate": 0.000168, | |
| "loss": 0.0029, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 15.71, | |
| "learning_rate": 0.000167, | |
| "loss": 0.0028, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 16.19, | |
| "learning_rate": 0.000166, | |
| "loss": 0.0027, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 16.67, | |
| "learning_rate": 0.000165, | |
| "loss": 0.0025, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 17.14, | |
| "learning_rate": 0.000164, | |
| "loss": 0.0025, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 17.62, | |
| "learning_rate": 0.000163, | |
| "loss": 0.0024, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 18.1, | |
| "learning_rate": 0.000162, | |
| "loss": 0.0023, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 18.57, | |
| "learning_rate": 0.000161, | |
| "loss": 0.0021, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 19.05, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0021, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 19.05, | |
| "eval_accuracy": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.0019897979218512774, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.713, | |
| "eval_samples_per_second": 78.541, | |
| "eval_steps_per_second": 9.818, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 19.52, | |
| "learning_rate": 0.00015900000000000002, | |
| "loss": 0.002, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 0.00015800000000000002, | |
| "loss": 0.0019, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 20.48, | |
| "learning_rate": 0.00015700000000000002, | |
| "loss": 0.0019, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 20.95, | |
| "learning_rate": 0.00015600000000000002, | |
| "loss": 0.0018, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 21.43, | |
| "learning_rate": 0.000155, | |
| "loss": 0.0017, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 21.9, | |
| "learning_rate": 0.000154, | |
| "loss": 0.0017, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 22.38, | |
| "learning_rate": 0.000153, | |
| "loss": 0.0017, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 22.86, | |
| "learning_rate": 0.000152, | |
| "loss": 0.0016, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 23.33, | |
| "learning_rate": 0.000151, | |
| "loss": 0.0015, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 23.81, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0015, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 24.29, | |
| "learning_rate": 0.00014900000000000002, | |
| "loss": 0.0014, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 24.76, | |
| "learning_rate": 0.000148, | |
| "loss": 0.0014, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 25.24, | |
| "learning_rate": 0.000147, | |
| "loss": 0.0014, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 25.71, | |
| "learning_rate": 0.000146, | |
| "loss": 0.0013, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 26.19, | |
| "learning_rate": 0.000145, | |
| "loss": 0.0013, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 26.67, | |
| "learning_rate": 0.000144, | |
| "loss": 0.0013, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 27.14, | |
| "learning_rate": 0.000143, | |
| "loss": 0.0012, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 27.62, | |
| "learning_rate": 0.000142, | |
| "loss": 0.0012, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 28.1, | |
| "learning_rate": 0.000141, | |
| "loss": 0.0012, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 28.57, | |
| "learning_rate": 0.00014, | |
| "loss": 0.0012, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 28.57, | |
| "eval_accuracy": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.0011106810998171568, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.738, | |
| "eval_samples_per_second": 75.881, | |
| "eval_steps_per_second": 9.485, | |
| "step": 600 | |
| } | |
| ], | |
| "max_steps": 2000, | |
| "num_train_epochs": 96, | |
| "total_flos": 7.287346703356232e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |