| { |
| "best_global_step": 28, |
| "best_metric": 0.8571428571428571, |
| "best_model_checkpoint": "/kaggle/working/outputs/codebert_rd_keystrokes/checkpoint-28", |
| "epoch": 4.0, |
| "eval_steps": 400, |
| "global_step": 28, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.14285714285714285, |
| "grad_norm": 8.198164939880371, |
| "learning_rate": 0.0, |
| "loss": 0.8346311450004578, |
| "step": 1 |
| }, |
| { |
| "epoch": 3.571428571428571, |
| "grad_norm": 2.6778149604797363, |
| "learning_rate": 1.1454397434679022e-06, |
| "loss": 0.665327270825704, |
| "step": 25 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8, |
| "eval_f1": 0.8571428571428571, |
| "eval_loss": 0.5662792921066284, |
| "eval_precision": 1.0, |
| "eval_recall": 0.75, |
| "eval_runtime": 0.206, |
| "eval_samples_per_second": 48.532, |
| "eval_steps_per_second": 4.853, |
| "step": 28 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 28, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "save_steps": 400, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 2, |
| "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": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 105244422144000.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
