| { |
| "best_global_step": 34, |
| "best_metric": 0.6197988390922546, |
| "best_model_checkpoint": "distilbert_km_10_v1_cola/checkpoint-34", |
| "epoch": 6.0, |
| "eval_steps": 500, |
| "global_step": 204, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 1.0952237844467163, |
| "learning_rate": 4.9e-05, |
| "loss": 0.6167, |
| "step": 34 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.693192720413208, |
| "eval_loss": 0.6197988390922546, |
| "eval_matthews_correlation": 0.06558874629318973, |
| "eval_runtime": 0.4412, |
| "eval_samples_per_second": 2364.169, |
| "eval_steps_per_second": 11.334, |
| "step": 34 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 1.346522331237793, |
| "learning_rate": 4.8e-05, |
| "loss": 0.5902, |
| "step": 68 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.6874400973320007, |
| "eval_loss": 0.6214444041252136, |
| "eval_matthews_correlation": 0.0583575833998332, |
| "eval_runtime": 0.465, |
| "eval_samples_per_second": 2242.958, |
| "eval_steps_per_second": 10.752, |
| "step": 68 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 2.121037483215332, |
| "learning_rate": 4.7e-05, |
| "loss": 0.5443, |
| "step": 102 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.665388286113739, |
| "eval_loss": 0.6365245580673218, |
| "eval_matthews_correlation": 0.02092435484015298, |
| "eval_runtime": 0.4394, |
| "eval_samples_per_second": 2373.84, |
| "eval_steps_per_second": 11.38, |
| "step": 102 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 3.4788787364959717, |
| "learning_rate": 4.600000000000001e-05, |
| "loss": 0.4812, |
| "step": 136 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.6711409687995911, |
| "eval_loss": 0.6850274205207825, |
| "eval_matthews_correlation": 0.0702101916376067, |
| "eval_runtime": 0.4784, |
| "eval_samples_per_second": 2180.272, |
| "eval_steps_per_second": 10.452, |
| "step": 136 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 3.016806125640869, |
| "learning_rate": 4.5e-05, |
| "loss": 0.4113, |
| "step": 170 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.6318312287330627, |
| "eval_loss": 0.7599416375160217, |
| "eval_matthews_correlation": 0.06160069280905865, |
| "eval_runtime": 0.4386, |
| "eval_samples_per_second": 2378.084, |
| "eval_steps_per_second": 11.4, |
| "step": 170 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 4.438681602478027, |
| "learning_rate": 4.4000000000000006e-05, |
| "loss": 0.3473, |
| "step": 204 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.6510066986083984, |
| "eval_loss": 0.8574540615081787, |
| "eval_matthews_correlation": 0.08420916597044516, |
| "eval_runtime": 0.4499, |
| "eval_samples_per_second": 2318.307, |
| "eval_steps_per_second": 11.114, |
| "step": 204 |
| }, |
| { |
| "epoch": 6.0, |
| "step": 204, |
| "total_flos": 3398186177722368.0, |
| "train_loss": 0.4984959293814266, |
| "train_runtime": 58.2403, |
| "train_samples_per_second": 7341.13, |
| "train_steps_per_second": 29.189 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 1700, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 50, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 5, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 5 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3398186177722368.0, |
| "train_batch_size": 256, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
