| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 1245, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.40160642570281124, | |
| "grad_norm": 0.8199864625930786, | |
| "learning_rate": 4.001289001637574e-05, | |
| "loss": 0.111, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.8032128514056225, | |
| "grad_norm": 1.4645675420761108, | |
| "learning_rate": 1.3158601414781284e-05, | |
| "loss": 0.0621, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9822658225997456, | |
| "eval_f1": 0.8504214366586991, | |
| "eval_loss": 0.056050822138786316, | |
| "eval_precision": 0.8306709265175719, | |
| "eval_recall": 0.8711340206185567, | |
| "eval_runtime": 19.9833, | |
| "eval_samples_per_second": 213.478, | |
| "eval_steps_per_second": 26.722, | |
| "step": 1245 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1245, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 611004760472832.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 6.68671786179702e-05, | |
| "num_train_epochs": 1, | |
| "per_device_train_batch_size": 16, | |
| "seed": 1 | |
| } | |
| } | |