| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 7.2727272727272725, | |
| "eval_steps": 500, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3825, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.00017777777777777779, | |
| "loss": 1.3445, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 0.00015555555555555556, | |
| "loss": 1.2422, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 1.1453, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 0.00011111111111111112, | |
| "loss": 1.0282, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 8.888888888888889e-05, | |
| "loss": 0.916, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.8523, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.7692, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.7215, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 7.27, | |
| "learning_rate": 0.0, | |
| "loss": 0.7469, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 20, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 6503533432012800.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |