| { |
| "best_metric": 0.8096330275229358, |
| "best_model_checkpoint": "tiny-bert-sst2-distilled\\run-0\\checkpoint-1054", |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 1054, |
| "is_hyper_param_search": true, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "learning_rate": 0.0006568555243553003, |
| "loss": 0.9823, |
| "step": 527 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8084862385321101, |
| "eval_loss": 1.3724825382232666, |
| "eval_runtime": 1.7972, |
| "eval_samples_per_second": 485.194, |
| "eval_steps_per_second": 3.895, |
| "step": 527 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 0.0005838715772047113, |
| "loss": 0.4476, |
| "step": 1054 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8096330275229358, |
| "eval_loss": 1.3287416696548462, |
| "eval_runtime": 1.7495, |
| "eval_samples_per_second": 498.417, |
| "eval_steps_per_second": 4.001, |
| "step": 1054 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 5270, |
| "num_train_epochs": 10, |
| "save_steps": 500, |
| "total_flos": 16141525436100.0, |
| "trial_name": null, |
| "trial_params": { |
| "alpha": 0.5351224538156584, |
| "learning_rate": 0.0007298394715058892, |
| "num_train_epochs": 10, |
| "temperature": 24 |
| } |
| } |
|
|
