| { | |
| "best_metric": 2.340635061264038, | |
| "best_model_checkpoint": "output/enya/checkpoint-28", | |
| "epoch": 2.0, | |
| "global_step": 28, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00010290000000000001, | |
| "loss": 3.4974, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.4300000000000014e-05, | |
| "loss": 3.3404, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0, | |
| "loss": 3.292, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.8410420417785645, | |
| "eval_runtime": 0.6178, | |
| "eval_samples_per_second": 21.042, | |
| "eval_steps_per_second": 3.237, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 5.333506393059682e-05, | |
| "loss": 3.3112, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.00012223363969730684, | |
| "loss": 3.3235, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.340635061264038, | |
| "eval_runtime": 0.9038, | |
| "eval_samples_per_second": 23.236, | |
| "eval_steps_per_second": 3.319, | |
| "step": 28 | |
| } | |
| ], | |
| "max_steps": 28, | |
| "num_train_epochs": 2, | |
| "total_flos": 27958247424000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |