| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.009787928221859706, | |
| "eval_steps": 3, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0032626427406199023, | |
| "grad_norm": 0.8083321452140808, | |
| "learning_rate": 2e-05, | |
| "loss": 44.318, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0032626427406199023, | |
| "eval_loss": 11.076703071594238, | |
| "eval_runtime": 1.0679, | |
| "eval_samples_per_second": 121.729, | |
| "eval_steps_per_second": 60.864, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0065252854812398045, | |
| "grad_norm": 0.9225870370864868, | |
| "learning_rate": 4e-05, | |
| "loss": 44.2985, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.009787928221859706, | |
| "grad_norm": 0.8884333968162537, | |
| "learning_rate": 6e-05, | |
| "loss": 44.2889, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009787928221859706, | |
| "eval_loss": 11.076447486877441, | |
| "eval_runtime": 0.2952, | |
| "eval_samples_per_second": 440.406, | |
| "eval_steps_per_second": 220.203, | |
| "step": 3 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2614886400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |