| { |
| "best_global_step": 1000, |
| "best_metric": 0.7299026676279741, |
| "best_model_checkpoint": "./hpo_Buzzeitor_longformer-base-4096-bne-es/trial_0/checkpoint-1000", |
| "epoch": 4.82771896053898, |
| "eval_steps": 100, |
| "global_step": 1000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.48123195380173245, |
| "grad_norm": 2.3587965965270996, |
| "learning_rate": 2.4559035121953966e-05, |
| "loss": 0.6174, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.48123195380173245, |
| "eval_accuracy": 0.6756756756756757, |
| "eval_f1": 0.6636363636363636, |
| "eval_loss": 0.6910868883132935, |
| "eval_precision": 0.662606978275181, |
| "eval_recall": 0.6721254355400696, |
| "eval_runtime": 2.3792, |
| "eval_samples_per_second": 93.307, |
| "eval_steps_per_second": 15.551, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.9624639076034649, |
| "grad_norm": 3.7914035320281982, |
| "learning_rate": 2.3529306186022982e-05, |
| "loss": 0.5708, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.9624639076034649, |
| "eval_accuracy": 0.6666666666666666, |
| "eval_f1": 0.6554819226574952, |
| "eval_loss": 0.7087554931640625, |
| "eval_precision": 0.6552459016393443, |
| "eval_recall": 0.6649825783972125, |
| "eval_runtime": 2.4015, |
| "eval_samples_per_second": 92.444, |
| "eval_steps_per_second": 15.407, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.4475457170356112, |
| "grad_norm": 18.273841857910156, |
| "learning_rate": 2.2499577250091998e-05, |
| "loss": 0.5561, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.4475457170356112, |
| "eval_accuracy": 0.7207207207207207, |
| "eval_f1": 0.671409472880061, |
| "eval_loss": 0.6270285248756409, |
| "eval_precision": 0.7086640211640212, |
| "eval_recall": 0.6648954703832752, |
| "eval_runtime": 2.4, |
| "eval_samples_per_second": 92.502, |
| "eval_steps_per_second": 15.417, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.9287776708373436, |
| "grad_norm": 34.575313568115234, |
| "learning_rate": 2.1480145603520324e-05, |
| "loss": 0.5025, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.9287776708373436, |
| "eval_accuracy": 0.7207207207207207, |
| "eval_f1": 0.6564839772386942, |
| "eval_loss": 0.645313560962677, |
| "eval_precision": 0.7231869254341164, |
| "eval_recall": 0.6522648083623693, |
| "eval_runtime": 2.3956, |
| "eval_samples_per_second": 92.671, |
| "eval_steps_per_second": 15.445, |
| "step": 400 |
| }, |
| { |
| "epoch": 2.41385948026949, |
| "grad_norm": 31.36258888244629, |
| "learning_rate": 2.045041666758934e-05, |
| "loss": 0.4304, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.41385948026949, |
| "eval_accuracy": 0.6801801801801802, |
| "eval_f1": 0.6252407332556646, |
| "eval_loss": 0.8638490438461304, |
| "eval_precision": 0.6532934131736527, |
| "eval_recall": 0.6226480836236934, |
| "eval_runtime": 2.403, |
| "eval_samples_per_second": 92.386, |
| "eval_steps_per_second": 15.398, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.8950914340712224, |
| "grad_norm": 28.394620895385742, |
| "learning_rate": 1.942068773165836e-05, |
| "loss": 0.3904, |
| "step": 600 |
| }, |
| { |
| "epoch": 2.8950914340712224, |
| "eval_accuracy": 0.7117117117117117, |
| "eval_f1": 0.6935817805383022, |
| "eval_loss": 0.765376091003418, |
| "eval_precision": 0.69203146374829, |
| "eval_recall": 0.6956445993031359, |
| "eval_runtime": 2.3963, |
| "eval_samples_per_second": 92.644, |
| "eval_steps_per_second": 15.441, |
| "step": 600 |
| }, |
| { |
| "epoch": 3.3801732435033687, |
| "grad_norm": 2.409611463546753, |
| "learning_rate": 1.839095879572737e-05, |
| "loss": 0.2937, |
| "step": 700 |
| }, |
| { |
| "epoch": 3.3801732435033687, |
| "eval_accuracy": 0.6441441441441441, |
| "eval_f1": 0.6437899867980095, |
| "eval_loss": 1.1262925863265991, |
| "eval_precision": 0.6769874123511024, |
| "eval_recall": 0.6824912891986062, |
| "eval_runtime": 2.4008, |
| "eval_samples_per_second": 92.469, |
| "eval_steps_per_second": 15.412, |
| "step": 700 |
| }, |
| { |
| "epoch": 3.861405197305101, |
| "grad_norm": 116.25942993164062, |
| "learning_rate": 1.736122985979639e-05, |
| "loss": 0.2703, |
| "step": 800 |
| }, |
| { |
| "epoch": 3.861405197305101, |
| "eval_accuracy": 0.7207207207207207, |
| "eval_f1": 0.7057968536251711, |
| "eval_loss": 1.0032894611358643, |
| "eval_precision": 0.7032828282828283, |
| "eval_recall": 0.7103658536585367, |
| "eval_runtime": 2.3859, |
| "eval_samples_per_second": 93.047, |
| "eval_steps_per_second": 15.508, |
| "step": 800 |
| }, |
| { |
| "epoch": 4.346487006737247, |
| "grad_norm": 136.07870483398438, |
| "learning_rate": 1.6331500923865403e-05, |
| "loss": 0.2418, |
| "step": 900 |
| }, |
| { |
| "epoch": 4.346487006737247, |
| "eval_accuracy": 0.7342342342342343, |
| "eval_f1": 0.691048472697252, |
| "eval_loss": 1.0043816566467285, |
| "eval_precision": 0.7236044657097289, |
| "eval_recall": 0.6831881533101045, |
| "eval_runtime": 2.4, |
| "eval_samples_per_second": 92.5, |
| "eval_steps_per_second": 15.417, |
| "step": 900 |
| }, |
| { |
| "epoch": 4.82771896053898, |
| "grad_norm": 120.01212310791016, |
| "learning_rate": 1.5312069277293732e-05, |
| "loss": 0.2207, |
| "step": 1000 |
| }, |
| { |
| "epoch": 4.82771896053898, |
| "eval_accuracy": 0.7567567567567568, |
| "eval_f1": 0.7299026676279741, |
| "eval_loss": 0.9589651226997375, |
| "eval_precision": 0.7414473684210526, |
| "eval_recall": 0.723780487804878, |
| "eval_runtime": 2.385, |
| "eval_samples_per_second": 93.083, |
| "eval_steps_per_second": 15.514, |
| "step": 1000 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 2484, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 12, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 4, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 0 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 9795381765152256.0, |
| "train_batch_size": 6, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
