| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0093770931011385, | |
| "global_step": 3000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.2041, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0505, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.722222222222222e-05, | |
| "loss": 0.036, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.0217, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.0214, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.0181, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "eval_loss": 1.230069875717163, | |
| "eval_runtime": 43.3592, | |
| "eval_samples_per_second": 75.601, | |
| "eval_steps_per_second": 18.912, | |
| "step": 3000 | |
| } | |
| ], | |
| "max_steps": 10000, | |
| "num_train_epochs": 7, | |
| "total_flos": 1.880866314337075e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |