| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 7.319391634980988, | |
| "eval_steps": 500, | |
| "global_step": 672, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.928909952606635e-05, | |
| "loss": 1.7844, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 9.85781990521327e-05, | |
| "loss": 1.0308, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.00014786729857819904, | |
| "loss": 0.832, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 0.0001971563981042654, | |
| "loss": 0.7868, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 0.0001948230322239831, | |
| "loss": 0.7672, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 0.00018932910723718966, | |
| "loss": 0.7315, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 0.0001838351822503962, | |
| "loss": 0.6889, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 0.00017834125726360275, | |
| "loss": 0.6646, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 5.18, | |
| "learning_rate": 0.00017284733227680932, | |
| "loss": 0.6056, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "learning_rate": 0.00016735340729001586, | |
| "loss": 0.5724, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 6.26, | |
| "learning_rate": 0.0001618594823032224, | |
| "loss": 0.5251, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 0.00015636555731642895, | |
| "loss": 0.4665, | |
| "step": 624 | |
| } | |
| ], | |
| "logging_steps": 52, | |
| "max_steps": 2104, | |
| "num_train_epochs": 8, | |
| "save_steps": 500, | |
| "total_flos": 3.682319674638336e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |