| { |
| "best_metric": 0.49799539554804517, |
| "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-3207", |
| "epoch": 4.0, |
| "eval_steps": 500, |
| "global_step": 4276, |
| "is_hyper_param_search": true, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.47, |
| "learning_rate": 7.540690617488091e-06, |
| "loss": 0.558, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.94, |
| "learning_rate": 6.542188152248672e-06, |
| "loss": 0.5143, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.49273109436035156, |
| "eval_matthews_correlation": 0.43591443951045983, |
| "eval_runtime": 0.7692, |
| "eval_samples_per_second": 1355.973, |
| "eval_steps_per_second": 85.805, |
| "step": 1069 |
| }, |
| { |
| "epoch": 1.4, |
| "learning_rate": 5.543685687009253e-06, |
| "loss": 0.408, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.87, |
| "learning_rate": 4.545183221769834e-06, |
| "loss": 0.3963, |
| "step": 2000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.4984338581562042, |
| "eval_matthews_correlation": 0.48138791213884463, |
| "eval_runtime": 0.837, |
| "eval_samples_per_second": 1246.126, |
| "eval_steps_per_second": 78.854, |
| "step": 2138 |
| }, |
| { |
| "epoch": 2.34, |
| "learning_rate": 3.5466807565304158e-06, |
| "loss": 0.3146, |
| "step": 2500 |
| }, |
| { |
| "epoch": 2.81, |
| "learning_rate": 2.5481782912909966e-06, |
| "loss": 0.3216, |
| "step": 3000 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.6548400521278381, |
| "eval_matthews_correlation": 0.49799539554804517, |
| "eval_runtime": 0.7558, |
| "eval_samples_per_second": 1380.007, |
| "eval_steps_per_second": 87.325, |
| "step": 3207 |
| }, |
| { |
| "epoch": 3.27, |
| "learning_rate": 1.5496758260515779e-06, |
| "loss": 0.2812, |
| "step": 3500 |
| }, |
| { |
| "epoch": 3.74, |
| "learning_rate": 5.511733608121592e-07, |
| "loss": 0.2629, |
| "step": 4000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.7457934617996216, |
| "eval_matthews_correlation": 0.4921844836867617, |
| "eval_runtime": 0.8107, |
| "eval_samples_per_second": 1286.468, |
| "eval_steps_per_second": 81.406, |
| "step": 4276 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 4276, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "save_steps": 500, |
| "total_flos": 150919952053548.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": { |
| "learning_rate": 8.53919308272751e-06, |
| "num_train_epochs": 4, |
| "per_device_train_batch_size": 8, |
| "seed": 13 |
| } |
| } |
|
|
