| { |
| "best_global_step": 2488, |
| "best_metric": 0.8768764994800742, |
| "best_model_checkpoint": "./results-PR/bert-base-multilingual-cased_fold_2/checkpoint-2488", |
| "epoch": 4.0, |
| "eval_steps": 500, |
| "global_step": 2488, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.8038585209003215, |
| "grad_norm": 6.323563098907471, |
| "learning_rate": 2.0056270096463023e-05, |
| "loss": 0.5669, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8567980691874497, |
| "eval_f1": 0.8594765640659389, |
| "eval_loss": 0.4563852548599243, |
| "eval_precision": 0.8693942424773098, |
| "eval_recall": 0.8567980691874497, |
| "eval_runtime": 5.1701, |
| "eval_samples_per_second": 240.419, |
| "eval_steps_per_second": 30.173, |
| "step": 622 |
| }, |
| { |
| "epoch": 1.607717041800643, |
| "grad_norm": 4.9127397537231445, |
| "learning_rate": 4.0152733118971066e-05, |
| "loss": 0.4993, |
| "step": 1000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8600160901045857, |
| "eval_f1": 0.855355253148187, |
| "eval_loss": 0.558882474899292, |
| "eval_precision": 0.8605647577386315, |
| "eval_recall": 0.8600160901045857, |
| "eval_runtime": 5.0969, |
| "eval_samples_per_second": 243.875, |
| "eval_steps_per_second": 30.607, |
| "step": 1244 |
| }, |
| { |
| "epoch": 2.4115755627009645, |
| "grad_norm": 3.4203596115112305, |
| "learning_rate": 4.993602960395657e-05, |
| "loss": 0.5025, |
| "step": 1500 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8447304907481898, |
| "eval_f1": 0.8472136258356129, |
| "eval_loss": 0.48319464921951294, |
| "eval_precision": 0.8544329791059292, |
| "eval_recall": 0.8447304907481898, |
| "eval_runtime": 5.0791, |
| "eval_samples_per_second": 244.73, |
| "eval_steps_per_second": 30.714, |
| "step": 1866 |
| }, |
| { |
| "epoch": 3.215434083601286, |
| "grad_norm": 2.613199234008789, |
| "learning_rate": 4.944107574504116e-05, |
| "loss": 0.4963, |
| "step": 2000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8761061946902655, |
| "eval_f1": 0.8768764994800742, |
| "eval_loss": 0.48076900839805603, |
| "eval_precision": 0.8782309818720038, |
| "eval_recall": 0.8761061946902655, |
| "eval_runtime": 5.0682, |
| "eval_samples_per_second": 245.256, |
| "eval_steps_per_second": 30.78, |
| "step": 2488 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 12440, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 20, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 3, |
| "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": 5230647780556800.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
