| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.973293768545994, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 8e-08, | |
| "loss": 0.6853, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.6e-07, | |
| "loss": 0.6856, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 2.4e-07, | |
| "loss": 0.6901, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.2e-07, | |
| "loss": 0.6933, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4e-07, | |
| "loss": 0.6836, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.8e-07, | |
| "loss": 0.6823, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 5.6e-07, | |
| "loss": 0.6894, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 6.4e-07, | |
| "loss": 0.6857, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 7.2e-07, | |
| "loss": 0.6775, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 8e-07, | |
| "loss": 0.6846, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 8.799999999999999e-07, | |
| "loss": 0.68, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 9.6e-07, | |
| "loss": 0.6751, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.04e-06, | |
| "loss": 0.6803, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.12e-06, | |
| "loss": 0.6812, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1.2e-06, | |
| "loss": 0.6866, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.28e-06, | |
| "loss": 0.667, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5742942050520059, | |
| "eval_f1": 0.364794714487966, | |
| "eval_loss": 0.6554083824157715, | |
| "eval_precision": 0.28714710252600295, | |
| "eval_recall": 0.5, | |
| "eval_runtime": 10.606, | |
| "eval_samples_per_second": 253.819, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 1.3600000000000001e-06, | |
| "loss": 0.6922, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 1.44e-06, | |
| "loss": 0.64, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 1.5199999999999998e-06, | |
| "loss": 0.5834, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 1.6e-06, | |
| "loss": 0.4636, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 1.6799999999999998e-06, | |
| "loss": 0.3717, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 1.7599999999999999e-06, | |
| "loss": 0.3508, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 1.84e-06, | |
| "loss": 0.2926, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 1.92e-06, | |
| "loss": 0.2967, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 2e-06, | |
| "loss": 0.2973, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 2.08e-06, | |
| "loss": 0.2747, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 2.16e-06, | |
| "loss": 0.3057, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 2.24e-06, | |
| "loss": 0.284, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 2.32e-06, | |
| "loss": 0.3063, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 2.4e-06, | |
| "loss": 0.2705, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 2.48e-06, | |
| "loss": 0.2598, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 2.56e-06, | |
| "loss": 0.246, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 2.64e-06, | |
| "loss": 0.2556, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8904160475482912, | |
| "eval_f1": 0.8873658539006881, | |
| "eval_loss": 0.27534565329551697, | |
| "eval_precision": 0.889704946803928, | |
| "eval_recall": 0.885514947090843, | |
| "eval_runtime": 10.6052, | |
| "eval_samples_per_second": 253.837, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 2.7200000000000002e-06, | |
| "loss": 0.2643, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 2.8e-06, | |
| "loss": 0.2734, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 2.88e-06, | |
| "loss": 0.2294, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 2.96e-06, | |
| "loss": 0.2289, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 3.0399999999999997e-06, | |
| "loss": 0.2494, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 3.1199999999999998e-06, | |
| "loss": 0.222, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 3.2e-06, | |
| "loss": 0.2603, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 3.2799999999999995e-06, | |
| "loss": 0.265, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 3.3599999999999996e-06, | |
| "loss": 0.2482, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 3.4399999999999997e-06, | |
| "loss": 0.2623, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 3.5199999999999998e-06, | |
| "loss": 0.2411, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 3.6e-06, | |
| "loss": 0.2331, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 3.68e-06, | |
| "loss": 0.2301, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 3.7599999999999996e-06, | |
| "loss": 0.2105, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 3.84e-06, | |
| "loss": 0.2282, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 3.92e-06, | |
| "loss": 0.2357, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 4e-06, | |
| "loss": 0.2191, | |
| "step": 500 | |
| } | |
| ], | |
| "max_steps": 840, | |
| "num_train_epochs": 5, | |
| "total_flos": 7162006012003440, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |