| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.8639999999999999, | |
| "eval_steps": 500, | |
| "global_step": 14, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.128, | |
| "grad_norm": 1.3161825212667742, | |
| "learning_rate": 4.937319780454559e-06, | |
| "loss": 0.2992, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 1.5777814751392776, | |
| "learning_rate": 3.5847093477938955e-06, | |
| "loss": 0.2869, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.3519999999999999, | |
| "grad_norm": 0.9257938979233173, | |
| "learning_rate": 9.412754953531664e-07, | |
| "loss": 0.2915, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.8639999999999999, | |
| "step": 14, | |
| "total_flos": 2452435959808.0, | |
| "train_loss": 0.2740209038768496, | |
| "train_runtime": 132.3716, | |
| "train_samples_per_second": 15.049, | |
| "train_steps_per_second": 0.106 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 14, | |
| "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": 2452435959808.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |