| { | |
| "best_metric": 0.5417714715003967, | |
| "best_model_checkpoint": "DP32/checkpoint-600", | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.841875, | |
| "eval_loss": 0.6350374221801758, | |
| "eval_model_preparation_time": 0.0045, | |
| "eval_runtime": 64.618, | |
| "eval_samples_per_second": 49.522, | |
| "eval_steps_per_second": 6.19, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.925, | |
| "eval_loss": 0.5866522192955017, | |
| "eval_model_preparation_time": 0.0045, | |
| "eval_runtime": 62.9502, | |
| "eval_samples_per_second": 50.834, | |
| "eval_steps_per_second": 6.354, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.94625, | |
| "eval_loss": 0.5532988905906677, | |
| "eval_model_preparation_time": 0.0045, | |
| "eval_runtime": 63.0217, | |
| "eval_samples_per_second": 50.776, | |
| "eval_steps_per_second": 6.347, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.3333333333333335, | |
| "grad_norm": 2.095505475997925, | |
| "learning_rate": 1.818181818181818e-07, | |
| "loss": 0.5872, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9515625, | |
| "eval_loss": 0.5417714715003967, | |
| "eval_model_preparation_time": 0.0045, | |
| "eval_runtime": 62.7241, | |
| "eval_samples_per_second": 51.017, | |
| "eval_steps_per_second": 6.377, | |
| "step": 600 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 600, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.516572596109312e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |