| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.992, | |
| "global_step": 31, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.8387096774193554e-05, | |
| "loss": 3.5576, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 9.67741935483871e-06, | |
| "loss": 3.2766, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_accuracy": 0.03723577235772358, | |
| "eval_loss": 3.0587494373321533, | |
| "eval_runtime": 2.0061, | |
| "eval_samples_per_second": 49.847, | |
| "eval_steps_per_second": 1.994, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "step": 31, | |
| "total_flos": 938904995758080.0, | |
| "train_loss": 3.260736426999492, | |
| "train_runtime": 119.8588, | |
| "train_samples_per_second": 8.343, | |
| "train_steps_per_second": 0.259 | |
| } | |
| ], | |
| "max_steps": 31, | |
| "num_train_epochs": 1, | |
| "total_flos": 938904995758080.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |