| { |
| "best_global_step": 93, |
| "best_metric": 0.38837920489296635, |
| "best_model_checkpoint": "models/roberta-large-touche-base-binary/trainer/checkpoint-93", |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 93, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.10810810810810811, |
| "grad_norm": 12.057156562805176, |
| "learning_rate": 6.4285714285714295e-06, |
| "loss": 1.51865234375, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.21621621621621623, |
| "grad_norm": 10.9874906539917, |
| "learning_rate": 1.3571428571428574e-05, |
| "loss": 1.37591552734375, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.32432432432432434, |
| "grad_norm": 10.673126220703125, |
| "learning_rate": 1.9920318725099602e-05, |
| "loss": 1.4565673828125, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.43243243243243246, |
| "grad_norm": 17.499927520751953, |
| "learning_rate": 1.912350597609562e-05, |
| "loss": 1.4800537109375, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.5405405405405406, |
| "grad_norm": 15.72847843170166, |
| "learning_rate": 1.8326693227091633e-05, |
| "loss": 1.447882080078125, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.6486486486486487, |
| "grad_norm": 11.744357109069824, |
| "learning_rate": 1.752988047808765e-05, |
| "loss": 1.3298416137695312, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.7567567567567568, |
| "grad_norm": 8.649158477783203, |
| "learning_rate": 1.6733067729083667e-05, |
| "loss": 1.40760498046875, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.8648648648648649, |
| "grad_norm": 15.254891395568848, |
| "learning_rate": 1.593625498007968e-05, |
| "loss": 1.349920654296875, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.972972972972973, |
| "grad_norm": 21.086435317993164, |
| "learning_rate": 1.5139442231075698e-05, |
| "loss": 1.3678375244140626, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.515, |
| "eval_fallacy_f1": 0.6666666666666666, |
| "eval_loss": 0.6907617449760437, |
| "eval_macro_f1": 0.38837920489296635, |
| "eval_runtime": 1.539, |
| "eval_samples_per_second": 129.957, |
| "eval_steps_per_second": 8.447, |
| "step": 93 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 279, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "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": 167434574706672.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
