| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.996605566870333, | |
| "eval_steps": 500, | |
| "global_step": 1840, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00018683574879227056, | |
| "loss": 1.6008, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.00015132850241545895, | |
| "loss": 1.3205, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.00011594202898550725, | |
| "loss": 1.2633, | |
| "step": 882 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 8.043478260869566e-05, | |
| "loss": 1.2384, | |
| "step": 1176 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 4.492753623188406e-05, | |
| "loss": 1.2013, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 9.420289855072464e-06, | |
| "loss": 1.1515, | |
| "step": 1764 | |
| } | |
| ], | |
| "logging_steps": 294, | |
| "max_steps": 1840, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 2.9916235265212416e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |