| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.10264635124298316, | |
| "eval_steps": 500, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.9978589232386036e-05, | |
| "loss": 1.004, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.946930129495106e-05, | |
| "loss": 0.9924, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 0.9804379343986511, | |
| "eval_runtime": 113.7555, | |
| "eval_samples_per_second": 92.303, | |
| "eval_steps_per_second": 1.45, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "step": 5, | |
| "total_flos": 3.2496204134744064e+16, | |
| "train_loss": 1.0607661485671998, | |
| "train_runtime": 6671.1002, | |
| "train_samples_per_second": 29.905, | |
| "train_steps_per_second": 0.007 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 48, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 3.2496204134744064e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |