| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 90537, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 8.568437488910182e-05, | |
| "loss": 0.6812, | |
| "step": 30179 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.4761524796485901, | |
| "eval_runtime": 466.6948, | |
| "eval_samples_per_second": 2327.907, | |
| "eval_steps_per_second": 8.085, | |
| "step": 30179 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6.427552432662622e-05, | |
| "loss": 0.4541, | |
| "step": 60358 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.40283310413360596, | |
| "eval_runtime": 444.5085, | |
| "eval_samples_per_second": 2444.097, | |
| "eval_steps_per_second": 8.488, | |
| "step": 60358 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 4.286667376415061e-05, | |
| "loss": 0.4044, | |
| "step": 90537 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.3708195686340332, | |
| "eval_runtime": 459.9775, | |
| "eval_samples_per_second": 2361.902, | |
| "eval_steps_per_second": 8.203, | |
| "step": 90537 | |
| } | |
| ], | |
| "max_steps": 150895, | |
| "num_train_epochs": 5, | |
| "total_flos": 2.0634769474023252e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |