| { |
| "best_metric": 0.27679798007011414, |
| "best_model_checkpoint": "spa_en_mBERT/checkpoint-4480", |
| "epoch": 6.0, |
| "global_step": 5376, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.56, |
| "learning_rate": 1.988839285714286e-05, |
| "loss": 1.015, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8975234842015372, |
| "eval_f1": 0.7030225599300675, |
| "eval_loss": 0.40301570296287537, |
| "eval_precision": 0.7149695684879983, |
| "eval_recall": 0.691468253968254, |
| "eval_runtime": 5.8245, |
| "eval_samples_per_second": 283.973, |
| "eval_steps_per_second": 17.856, |
| "step": 896 |
| }, |
| { |
| "epoch": 1.12, |
| "learning_rate": 1.9776785714285716e-05, |
| "loss": 0.466, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.67, |
| "learning_rate": 1.9665178571428575e-05, |
| "loss": 0.3444, |
| "step": 1500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9197465890810875, |
| "eval_f1": 0.772121694173792, |
| "eval_loss": 0.30006563663482666, |
| "eval_precision": 0.7738142686329215, |
| "eval_recall": 0.770436507936508, |
| "eval_runtime": 5.9225, |
| "eval_samples_per_second": 279.276, |
| "eval_steps_per_second": 17.56, |
| "step": 1792 |
| }, |
| { |
| "epoch": 2.23, |
| "learning_rate": 1.955357142857143e-05, |
| "loss": 0.2916, |
| "step": 2000 |
| }, |
| { |
| "epoch": 2.79, |
| "learning_rate": 1.944196428571429e-05, |
| "loss": 0.2491, |
| "step": 2500 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9214545310110619, |
| "eval_f1": 0.7768938768773725, |
| "eval_loss": 0.2882336974143982, |
| "eval_precision": 0.7754859967051071, |
| "eval_recall": 0.7783068783068783, |
| "eval_runtime": 5.8599, |
| "eval_samples_per_second": 282.259, |
| "eval_steps_per_second": 17.748, |
| "step": 2688 |
| }, |
| { |
| "epoch": 3.35, |
| "learning_rate": 1.9330357142857144e-05, |
| "loss": 0.2111, |
| "step": 3000 |
| }, |
| { |
| "epoch": 3.91, |
| "learning_rate": 1.9218750000000003e-05, |
| "loss": 0.1889, |
| "step": 3500 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9311659682640557, |
| "eval_f1": 0.8087478559176673, |
| "eval_loss": 0.279913067817688, |
| "eval_precision": 0.8067254540668597, |
| "eval_recall": 0.8107804232804233, |
| "eval_runtime": 5.8665, |
| "eval_samples_per_second": 281.939, |
| "eval_steps_per_second": 17.728, |
| "step": 3584 |
| }, |
| { |
| "epoch": 4.46, |
| "learning_rate": 1.910714285714286e-05, |
| "loss": 0.1683, |
| "step": 4000 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9332115266220483, |
| "eval_f1": 0.8155864706270193, |
| "eval_loss": 0.27679798007011414, |
| "eval_precision": 0.8130669120546865, |
| "eval_recall": 0.8181216931216931, |
| "eval_runtime": 6.0326, |
| "eval_samples_per_second": 274.178, |
| "eval_steps_per_second": 17.24, |
| "step": 4480 |
| }, |
| { |
| "epoch": 5.02, |
| "learning_rate": 1.8995535714285717e-05, |
| "loss": 0.1568, |
| "step": 4500 |
| }, |
| { |
| "epoch": 5.58, |
| "learning_rate": 1.8883928571428573e-05, |
| "loss": 0.1313, |
| "step": 5000 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.9282068595714257, |
| "eval_f1": 0.7986634908032288, |
| "eval_loss": 0.30244389176368713, |
| "eval_precision": 0.7989806724913953, |
| "eval_recall": 0.7983465608465609, |
| "eval_runtime": 5.8739, |
| "eval_samples_per_second": 281.583, |
| "eval_steps_per_second": 17.705, |
| "step": 5376 |
| } |
| ], |
| "max_steps": 89600, |
| "num_train_epochs": 100, |
| "total_flos": 3919265715030336.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
