| { | |
| "best_global_step": 626, | |
| "best_metric": 1.4388868808746338, | |
| "best_model_checkpoint": "classifier-clinc-MBbase-distilled/run-2/checkpoint-626", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 626, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8722580645161291, | |
| "eval_loss": 3.1264944076538086, | |
| "eval_runtime": 8.742, | |
| "eval_samples_per_second": 354.61, | |
| "eval_steps_per_second": 11.096, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 1.5974440894568689, | |
| "grad_norm": 19.63718605041504, | |
| "learning_rate": 1.2028753993610226e-05, | |
| "loss": 7.5605, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9358064516129032, | |
| "eval_loss": 1.4388868808746338, | |
| "eval_runtime": 8.7689, | |
| "eval_samples_per_second": 353.524, | |
| "eval_steps_per_second": 11.062, | |
| "step": 626 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1252, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 222488892388608.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": { | |
| "alpha": 0.3834548032441225, | |
| "num_train_epochs": 4, | |
| "temperature": 3.2573096526016223 | |
| } | |
| } | |