| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07233273056057866, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014466546112115732, | |
| "grad_norm": 24.54901885986328, | |
| "learning_rate": 1e-05, | |
| "loss": 6.9424, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014466546112115732, | |
| "eval_loss": 6.801471710205078, | |
| "eval_runtime": 102.9452, | |
| "eval_samples_per_second": 1.137, | |
| "eval_steps_per_second": 0.573, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.028933092224231464, | |
| "grad_norm": 24.030302047729492, | |
| "learning_rate": 2e-05, | |
| "loss": 6.7073, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.028933092224231464, | |
| "eval_loss": 6.572765350341797, | |
| "eval_runtime": 1.5554, | |
| "eval_samples_per_second": 75.224, | |
| "eval_steps_per_second": 37.933, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0433996383363472, | |
| "grad_norm": 23.519948959350586, | |
| "learning_rate": 3e-05, | |
| "loss": 6.4229, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05786618444846293, | |
| "grad_norm": 23.52826499938965, | |
| "learning_rate": 4e-05, | |
| "loss": 6.0355, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05786618444846293, | |
| "eval_loss": 5.332284450531006, | |
| "eval_runtime": 1.555, | |
| "eval_samples_per_second": 75.239, | |
| "eval_steps_per_second": 37.941, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07233273056057866, | |
| "grad_norm": 22.894739151000977, | |
| "learning_rate": 5e-05, | |
| "loss": 5.4023, | |
| "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": 1000194661416960.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |