| { | |
| "best_metric": 0.46569143021903203, | |
| "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-9/checkpoint-804", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 804, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.5013087391853333, | |
| "eval_matthews_correlation": 0.4182979471843555, | |
| "eval_runtime": 0.7144, | |
| "eval_samples_per_second": 1460.02, | |
| "eval_steps_per_second": 92.389, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 1.8656716417910446, | |
| "grad_norm": 5.0521626472473145, | |
| "learning_rate": 4.459085219377165e-06, | |
| "loss": 0.4803, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.5291440486907959, | |
| "eval_matthews_correlation": 0.44699732518353524, | |
| "eval_runtime": 0.8146, | |
| "eval_samples_per_second": 1280.378, | |
| "eval_steps_per_second": 81.021, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.5174696445465088, | |
| "eval_matthews_correlation": 0.46569143021903203, | |
| "eval_runtime": 0.9044, | |
| "eval_samples_per_second": 1153.241, | |
| "eval_steps_per_second": 72.976, | |
| "step": 804 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 804, | |
| "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": 98314095087672.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 1.1793106961773818e-05, | |
| "num_train_epochs": 3, | |
| "per_device_train_batch_size": 32, | |
| "seed": 28 | |
| } | |
| } | |