| { | |
| "best_metric": 2.429492235183716, | |
| "best_model_checkpoint": "output/system-of-a-down/checkpoint-34", | |
| "epoch": 2.0, | |
| "global_step": 34, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.000109940736055617, | |
| "loss": 2.6172, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.982671888105512e-05, | |
| "loss": 2.7188, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.6324050628611986e-06, | |
| "loss": 2.6973, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.4792027473449707, | |
| "eval_runtime": 1.1308, | |
| "eval_samples_per_second": 22.108, | |
| "eval_steps_per_second": 3.537, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 1.0275104488948473e-05, | |
| "loss": 2.5817, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 6.227039054081748e-05, | |
| "loss": 2.6768, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.00011929601172133719, | |
| "loss": 2.3346, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.429492235183716, | |
| "eval_runtime": 1.1473, | |
| "eval_samples_per_second": 21.791, | |
| "eval_steps_per_second": 3.487, | |
| "step": 34 | |
| } | |
| ], | |
| "max_steps": 51, | |
| "num_train_epochs": 3, | |
| "total_flos": 35013132288000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |