| { | |
| "best_metric": 0.9849327674451294, | |
| "best_model_checkpoint": "distilbert-base-uncased_finetuned_text_2_disease/checkpoint-167", | |
| "epoch": 3.0, | |
| "global_step": 501, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0, | |
| "loss": 0.3927, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0, | |
| "loss": 0.3871, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0, | |
| "loss": 0.3545, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0, | |
| "loss": 0.389, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0, | |
| "loss": 0.3796, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0, | |
| "loss": 0.3484, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0, | |
| "loss": 0.3691, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0, | |
| "loss": 0.3773, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0, | |
| "loss": 0.3739, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0, | |
| "loss": 0.3687, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.0, | |
| "loss": 0.3946, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0, | |
| "loss": 0.3614, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0, | |
| "loss": 0.3963, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.0, | |
| "loss": 0.3555, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.0, | |
| "loss": 0.3627, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.0, | |
| "loss": 0.3641, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.984984984984985, | |
| "eval_f1": 0.9849327674451294, | |
| "eval_loss": 0.2975810170173645, | |
| "eval_precision": 0.9865442976554087, | |
| "eval_recall": 0.984984984984985, | |
| "eval_runtime": 3.8994, | |
| "eval_samples_per_second": 170.795, | |
| "eval_steps_per_second": 5.385, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.0, | |
| "loss": 0.3898, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.0, | |
| "loss": 0.3551, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.0, | |
| "loss": 0.3864, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0, | |
| "loss": 0.3539, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.0, | |
| "loss": 0.3792, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.0, | |
| "loss": 0.3929, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.0, | |
| "loss": 0.3688, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.0, | |
| "loss": 0.4244, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.0, | |
| "loss": 0.3677, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.0, | |
| "loss": 0.371, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.0, | |
| "loss": 0.3686, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.0, | |
| "loss": 0.3774, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.0, | |
| "loss": 0.3703, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.0, | |
| "loss": 0.3731, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.0, | |
| "loss": 0.3763, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.0, | |
| "loss": 0.3712, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.0, | |
| "loss": 0.3762, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.984984984984985, | |
| "eval_f1": 0.9849327674451294, | |
| "eval_loss": 0.2975810170173645, | |
| "eval_precision": 0.9865442976554087, | |
| "eval_recall": 0.984984984984985, | |
| "eval_runtime": 3.6994, | |
| "eval_samples_per_second": 180.03, | |
| "eval_steps_per_second": 5.677, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.0, | |
| "loss": 0.3601, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 0.0, | |
| "loss": 0.3885, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 0.0, | |
| "loss": 0.3864, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 0.0, | |
| "loss": 0.3701, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 0.0, | |
| "loss": 0.3744, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 0.0, | |
| "loss": 0.3791, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.0, | |
| "loss": 0.3572, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 0.0, | |
| "loss": 0.3809, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 0.0, | |
| "loss": 0.3796, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 0.0, | |
| "loss": 0.3517, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 0.0, | |
| "loss": 0.3723, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 0.0, | |
| "loss": 0.3895, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 0.0, | |
| "loss": 0.3786, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 0.0, | |
| "loss": 0.3844, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 0.0, | |
| "loss": 0.3575, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 0.0, | |
| "loss": 0.3547, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 0.0, | |
| "loss": 0.3783, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.984984984984985, | |
| "eval_f1": 0.9849327674451294, | |
| "eval_loss": 0.2975810170173645, | |
| "eval_precision": 0.9865442976554087, | |
| "eval_recall": 0.984984984984985, | |
| "eval_runtime": 3.693, | |
| "eval_samples_per_second": 180.342, | |
| "eval_steps_per_second": 5.686, | |
| "step": 501 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 501, | |
| "total_flos": 2118227382190080.0, | |
| "train_loss": 0.374498660454969, | |
| "train_runtime": 306.4673, | |
| "train_samples_per_second": 52.156, | |
| "train_steps_per_second": 1.635 | |
| } | |
| ], | |
| "max_steps": 501, | |
| "num_train_epochs": 3, | |
| "total_flos": 2118227382190080.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |