| { |
| "best_metric": 0.0, |
| "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-268", |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 536, |
| "is_hyper_param_search": true, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.6040828824043274, |
| "eval_matthews_correlation": 0.0, |
| "eval_runtime": 0.7357, |
| "eval_samples_per_second": 1417.686, |
| "eval_steps_per_second": 89.71, |
| "step": 268 |
| }, |
| { |
| "epoch": 1.8656716417910446, |
| "grad_norm": 1.227530598640442, |
| "learning_rate": 1.0888916717266636e-07, |
| "loss": 0.6038, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.594471275806427, |
| "eval_matthews_correlation": 0.0, |
| "eval_runtime": 0.815, |
| "eval_samples_per_second": 1279.76, |
| "eval_steps_per_second": 80.982, |
| "step": 536 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 536, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "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": 96169002895764.0, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": { |
| "learning_rate": 1.6212387112374769e-06, |
| "num_train_epochs": 2, |
| "per_device_train_batch_size": 32, |
| "seed": 18 |
| } |
| } |
|
|
