| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.032706459525756335, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006541291905151268, | |
| "grad_norm": 3.538240432739258, | |
| "learning_rate": 1e-05, | |
| "loss": 4.7181, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006541291905151268, | |
| "eval_loss": 4.672138214111328, | |
| "eval_runtime": 146.6651, | |
| "eval_samples_per_second": 1.759, | |
| "eval_steps_per_second": 0.88, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013082583810302535, | |
| "grad_norm": 3.580988883972168, | |
| "learning_rate": 2e-05, | |
| "loss": 4.5791, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.013082583810302535, | |
| "eval_loss": 4.637351989746094, | |
| "eval_runtime": 58.6836, | |
| "eval_samples_per_second": 4.396, | |
| "eval_steps_per_second": 2.198, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.019623875715453803, | |
| "grad_norm": 3.788933515548706, | |
| "learning_rate": 3e-05, | |
| "loss": 4.942, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02616516762060507, | |
| "grad_norm": 3.714500665664673, | |
| "learning_rate": 4e-05, | |
| "loss": 4.7672, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02616516762060507, | |
| "eval_loss": 4.440040588378906, | |
| "eval_runtime": 58.6635, | |
| "eval_samples_per_second": 4.398, | |
| "eval_steps_per_second": 2.199, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.032706459525756335, | |
| "grad_norm": 3.38767671585083, | |
| "learning_rate": 5e-05, | |
| "loss": 4.3828, | |
| "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": 4104787234652160.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |