| { | |
| "best_metric": 0.7986666666666666, | |
| "best_model_checkpoint": "Bert_tinybert-distilled/run-31/checkpoint-516", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 516, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.9708962440490723, | |
| "learning_rate": 0.00018007353154788933, | |
| "loss": 0.5186, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_AUC": 0.8338702222222223, | |
| "eval_BAC": 0.758, | |
| "eval_MCC": 0.5164413442563544, | |
| "eval_PR_AUC": 0.7903470719520844, | |
| "eval_accuracy": 0.758, | |
| "eval_loss": 0.45808151364326477, | |
| "eval_runtime": 6.2856, | |
| "eval_samples_per_second": 238.642, | |
| "eval_steps_per_second": 7.477, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.5569114685058594, | |
| "learning_rate": 0.0001543487413267623, | |
| "loss": 0.4771, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_AUC": 0.8571271111111111, | |
| "eval_BAC": 0.7793333333333333, | |
| "eval_MCC": 0.591094330111451, | |
| "eval_PR_AUC": 0.8037547287750328, | |
| "eval_accuracy": 0.7793333333333333, | |
| "eval_loss": 0.4492648243904114, | |
| "eval_runtime": 6.2364, | |
| "eval_samples_per_second": 240.525, | |
| "eval_steps_per_second": 7.536, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 2.398871898651123, | |
| "learning_rate": 0.00012862395110563524, | |
| "loss": 0.4628, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_AUC": 0.8642417777777778, | |
| "eval_BAC": 0.7986666666666666, | |
| "eval_MCC": 0.5973864367101849, | |
| "eval_PR_AUC": 0.8284732954100074, | |
| "eval_accuracy": 0.7986666666666666, | |
| "eval_loss": 0.425106942653656, | |
| "eval_runtime": 6.229, | |
| "eval_samples_per_second": 240.809, | |
| "eval_steps_per_second": 7.545, | |
| "step": 516 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1376, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 8, | |
| "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": 1351133190000.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": { | |
| "alpha": 0.8022374115576867, | |
| "learning_rate": 0.0002057983217690164, | |
| "num_train_epochs": 8, | |
| "temperature": 4 | |
| } | |
| } | |