| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 477, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.7114, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5633802816901409, | |
| "eval_loss": 0.6923297047615051, | |
| "eval_runtime": 2.3107, | |
| "eval_samples_per_second": 30.726, | |
| "eval_steps_per_second": 3.895, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.7141, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5633802816901409, | |
| "eval_loss": 0.6894838809967041, | |
| "eval_runtime": 2.3191, | |
| "eval_samples_per_second": 30.616, | |
| "eval_steps_per_second": 3.881, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.7063, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.5633802816901409, | |
| "eval_loss": 0.6930345296859741, | |
| "eval_runtime": 2.3253, | |
| "eval_samples_per_second": 30.534, | |
| "eval_steps_per_second": 3.87, | |
| "step": 477 | |
| } | |
| ], | |
| "max_steps": 795, | |
| "num_train_epochs": 5, | |
| "total_flos": 1775329247139840.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |