| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 16, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 2.1428571428571428e-05, | |
| "loss": 1.0681, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7422222222222222, | |
| "eval_loss": 0.9125025868415833, | |
| "eval_runtime": 3.1968, | |
| "eval_samples_per_second": 70.383, | |
| "eval_steps_per_second": 2.503, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 16, | |
| "total_flos": 5.0884874272512e+16, | |
| "train_loss": 1.0160289406776428, | |
| "train_runtime": 55.9358, | |
| "train_samples_per_second": 36.202, | |
| "train_steps_per_second": 0.286 | |
| } | |
| ], | |
| "max_steps": 16, | |
| "num_train_epochs": 1, | |
| "total_flos": 5.0884874272512e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |