| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 747, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9472099821124733, | |
| "eval_f1": 0.5949084412684235, | |
| "eval_loss": 0.25175559520721436, | |
| "eval_precision": 0.5244094488188976, | |
| "eval_recall": 0.6873065015479877, | |
| "eval_runtime": 2.6615, | |
| "eval_samples_per_second": 318.997, | |
| "eval_steps_per_second": 40.203, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9473844945682998, | |
| "eval_f1": 0.5956873315363881, | |
| "eval_loss": 0.2594073712825775, | |
| "eval_precision": 0.5274463007159904, | |
| "eval_recall": 0.6842105263157895, | |
| "eval_runtime": 2.6621, | |
| "eval_samples_per_second": 318.925, | |
| "eval_steps_per_second": 40.194, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 2.0080321285140563, | |
| "grad_norm": 0.15671595931053162, | |
| "learning_rate": 5.926980687011047e-07, | |
| "loss": 0.0134, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9474281226822564, | |
| "eval_f1": 0.5947888589398024, | |
| "eval_loss": 0.2625073194503784, | |
| "eval_precision": 0.5266507557677009, | |
| "eval_recall": 0.6831785345717234, | |
| "eval_runtime": 3.0901, | |
| "eval_samples_per_second": 274.748, | |
| "eval_steps_per_second": 34.627, | |
| "step": 747 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 747, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 134021308141506.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 1.7924917300393731e-06, | |
| "weight_decay": 7.731086067996299e-05 | |
| } | |
| } | |