| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 73632, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.5323, | |
| "step": 24544 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.83015792154865, | |
| "eval_loss": 0.44308236241340637, | |
| "eval_runtime": 99.9144, | |
| "eval_samples_per_second": 98.234, | |
| "eval_steps_per_second": 12.281, | |
| "step": 24544 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.3447, | |
| "step": 49088 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8352521650534895, | |
| "eval_loss": 0.47252869606018066, | |
| "eval_runtime": 99.9537, | |
| "eval_samples_per_second": 98.195, | |
| "eval_steps_per_second": 12.276, | |
| "step": 49088 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.2267, | |
| "step": 73632 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8367804381049414, | |
| "eval_loss": 0.5887367129325867, | |
| "eval_runtime": 100.2091, | |
| "eval_samples_per_second": 97.945, | |
| "eval_steps_per_second": 12.244, | |
| "step": 73632 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 73632, | |
| "total_flos": 3.099754961058632e+17, | |
| "train_loss": 0.3679132374511082, | |
| "train_runtime": 35553.178, | |
| "train_samples_per_second": 33.136, | |
| "train_steps_per_second": 2.071 | |
| } | |
| ], | |
| "max_steps": 73632, | |
| "num_train_epochs": 3, | |
| "total_flos": 3.099754961058632e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |