| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06465517241379311, | |
| "eval_steps": 500, | |
| "global_step": 300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.021551724137931036, | |
| "grad_norm": 20.742843627929688, | |
| "learning_rate": 1.002155172413793e-06, | |
| "loss": 2.152, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.04310344827586207, | |
| "grad_norm": 7.82145357131958, | |
| "learning_rate": 2.079741379310345e-06, | |
| "loss": 0.677, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.06465517241379311, | |
| "grad_norm": 51.326385498046875, | |
| "learning_rate": 3.157327586206897e-06, | |
| "loss": 0.5383, | |
| "step": 300 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 9280, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 100, | |
| "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 | |
| } | |