| { |
| "best_metric": 0.0, |
| "best_model_checkpoint": "hf-correlations-production/checkpoint-35", |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 35, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.2857142857142857, |
| "grad_norm": 0.7777325510978699, |
| "learning_rate": 2.9411764705882355e-06, |
| "loss": 0.5875, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.5714285714285714, |
| "grad_norm": 0.754690945148468, |
| "learning_rate": 5.882352941176471e-06, |
| "loss": 0.5697, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.8571428571428571, |
| "grad_norm": 0.7596510648727417, |
| "learning_rate": 8.823529411764707e-06, |
| "loss": 0.5388, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.0, |
| "eval_f1": 0.0, |
| "eval_f1_macro": 0.0, |
| "eval_f1_micro": 0.0, |
| "eval_hamming_loss": 0.072, |
| "eval_hamming_score": 0.928, |
| "eval_loss": 0.49661701917648315, |
| "eval_precision": 0.0, |
| "eval_precision_macro": 0.0, |
| "eval_precision_micro": 0.0, |
| "eval_recall": 0.0, |
| "eval_recall_macro": 0.0, |
| "eval_recall_micro": 0.0, |
| "eval_runtime": 0.6244, |
| "eval_samples_per_second": 1.602, |
| "eval_steps_per_second": 1.602, |
| "eval_subset_accuracy": 0.0, |
| "step": 35 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 70, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 1, |
| "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": 36086022847488.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
