| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0005578333751708364, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001115666750341673, | |
| "grad_norm": 9.463600158691406, | |
| "learning_rate": 1e-05, | |
| "loss": 3.2702, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001115666750341673, | |
| "eval_loss": 2.978705644607544, | |
| "eval_runtime": 2471.4616, | |
| "eval_samples_per_second": 6.109, | |
| "eval_steps_per_second": 3.054, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002231333500683346, | |
| "grad_norm": 8.095428466796875, | |
| "learning_rate": 2e-05, | |
| "loss": 3.009, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0002231333500683346, | |
| "eval_loss": 2.904707908630371, | |
| "eval_runtime": 2305.4783, | |
| "eval_samples_per_second": 6.548, | |
| "eval_steps_per_second": 3.274, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0003347000251025019, | |
| "grad_norm": 7.363036632537842, | |
| "learning_rate": 3e-05, | |
| "loss": 2.9917, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0004462667001366692, | |
| "grad_norm": 6.851952075958252, | |
| "learning_rate": 4e-05, | |
| "loss": 2.8645, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0004462667001366692, | |
| "eval_loss": 2.5269322395324707, | |
| "eval_runtime": 2228.0989, | |
| "eval_samples_per_second": 6.776, | |
| "eval_steps_per_second": 3.388, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0005578333751708364, | |
| "grad_norm": 6.211727142333984, | |
| "learning_rate": 5e-05, | |
| "loss": 2.5836, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5541462766780416.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |