| { | |
| "best_metric": 1.4884066581726074, | |
| "best_model_checkpoint": "distilbert_weight_decay_final/checkpoint-3436", | |
| "epoch": 2.0, | |
| "global_step": 3436, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.970896391152503e-05, | |
| "loss": 0.0382, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 1.941792782305006e-05, | |
| "loss": 0.0288, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 1.9126891734575087e-05, | |
| "loss": 0.0306, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": { | |
| "accuracy": 0.7809847198641766 | |
| }, | |
| "eval_f1": { | |
| "f1": 0.7844084064836702 | |
| }, | |
| "eval_loss": 1.8566110134124756, | |
| "eval_runtime": 10.7438, | |
| "eval_samples_per_second": 328.933, | |
| "eval_steps_per_second": 20.57, | |
| "step": 1718 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 1.8835855646100117e-05, | |
| "loss": 0.0764, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 1.8544819557625148e-05, | |
| "loss": 0.073, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 1.825378346915018e-05, | |
| "loss": 0.0856, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": { | |
| "accuracy": 0.7758913412563667 | |
| }, | |
| "eval_f1": { | |
| "f1": 0.7796491207830641 | |
| }, | |
| "eval_loss": 1.4884066581726074, | |
| "eval_runtime": 10.2393, | |
| "eval_samples_per_second": 345.14, | |
| "eval_steps_per_second": 21.583, | |
| "step": 3436 | |
| } | |
| ], | |
| "max_steps": 34360, | |
| "num_train_epochs": 20, | |
| "total_flos": 1564235020691640.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |