| { | |
| "best_metric": 4.735376358032227, | |
| "best_model_checkpoint": "../experiments/attribute_minig_mslacerda/run-2/checkpoint-44", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 44, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.009309309309309309, | |
| "eval_f1": 0.0031890660592255125, | |
| "eval_loss": 4.765018939971924, | |
| "eval_precision": 0.002521613832853026, | |
| "eval_recall": 0.004337050805452293, | |
| "eval_runtime": 0.3702, | |
| "eval_samples_per_second": 786.144, | |
| "eval_steps_per_second": 99.956, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.015915915915915915, | |
| "eval_f1": 0.0032154340836012866, | |
| "eval_loss": 4.735376358032227, | |
| "eval_precision": 0.0025547445255474453, | |
| "eval_recall": 0.004337050805452293, | |
| "eval_runtime": 0.3639, | |
| "eval_samples_per_second": 799.64, | |
| "eval_steps_per_second": 101.672, | |
| "step": 44 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 220, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 1.1543805157988705e-05, | |
| "num_train_epochs": 10, | |
| "per_device_train_batch_size": 64, | |
| "warmup_steps": 275, | |
| "weight_decay": 0.2575815946979249 | |
| } | |
| } | |