| { | |
| "best_metric": 2.5190556049346924, | |
| "best_model_checkpoint": "output/nirvana/checkpoint-35", | |
| "epoch": 1.0, | |
| "global_step": 35, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00013040646433810595, | |
| "loss": 2.8877, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00011137140040750913, | |
| "loss": 2.7784, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 8.386493606940316e-05, | |
| "loss": 2.2959, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 5.3335063930596836e-05, | |
| "loss": 2.5076, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.5828599592490882e-05, | |
| "loss": 2.4917, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 6.793535661894054e-06, | |
| "loss": 2.4772, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.6382, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.5190556049346924, | |
| "eval_runtime": 2.4884, | |
| "eval_samples_per_second": 22.504, | |
| "eval_steps_per_second": 2.813, | |
| "step": 35 | |
| } | |
| ], | |
| "max_steps": 35, | |
| "num_train_epochs": 1, | |
| "total_flos": 36319592448000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |