| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 75.0, | |
| "eval_steps": 0, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 6.830379822583982, | |
| "learning_rate": 9.558232931726908e-06, | |
| "loss": 0.0035, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "grad_norm": 10.293176098919519, | |
| "learning_rate": 9.076305220883535e-06, | |
| "loss": -0.0866, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "grad_norm": 10.181519439770856, | |
| "learning_rate": 8.594377510040161e-06, | |
| "loss": -0.2709, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "grad_norm": 8.288002183978941, | |
| "learning_rate": 8.112449799196788e-06, | |
| "loss": -0.4316, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "grad_norm": 13.859265195724614, | |
| "learning_rate": 7.630522088353415e-06, | |
| "loss": -0.599, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "grad_norm": 15.553011031817677, | |
| "learning_rate": 7.148594377510041e-06, | |
| "loss": -0.8978, | |
| "step": 72 | |
| } | |
| ], | |
| "logging_steps": 12, | |
| "max_steps": 250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 250, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |