| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 5228, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.7651109410864575, | |
| "grad_norm": 2.158221483230591, | |
| "learning_rate": 8.337605994872807e-07, | |
| "loss": 1.2573, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.5302218821729152, | |
| "grad_norm": 2.2398524284362793, | |
| "learning_rate": 6.365608361269966e-07, | |
| "loss": 0.9101, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.295332823259373, | |
| "grad_norm": 1.444738507270813, | |
| "learning_rate": 4.3936107276671263e-07, | |
| "loss": 0.7317, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.06044376434583, | |
| "grad_norm": 1.4855622053146362, | |
| "learning_rate": 2.421613094064287e-07, | |
| "loss": 0.6212, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.8255547054322876, | |
| "grad_norm": 2.0333640575408936, | |
| "learning_rate": 4.4961546046144744e-08, | |
| "loss": 0.5799, | |
| "step": 5000 | |
| } | |
| ], | |
| "logging_steps": 1000, | |
| "max_steps": 5228, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.551619884777472e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |