| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.8689655172413793, | |
| "eval_steps": 500, | |
| "global_step": 8, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2206896551724138, | |
| "grad_norm": 27.47037721865609, | |
| "learning_rate": 4.809698831278217e-06, | |
| "loss": 1.337, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.206896551724138, | |
| "grad_norm": 6.066864532197262, | |
| "learning_rate": 1.5432914190872757e-06, | |
| "loss": 0.5322, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.8689655172413793, | |
| "step": 8, | |
| "total_flos": 4168563392512.0, | |
| "train_loss": 0.5126547068357468, | |
| "train_runtime": 418.9467, | |
| "train_samples_per_second": 2.759, | |
| "train_steps_per_second": 0.019 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 8, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4168563392512.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |