| { |
| "best_metric": 0.7519509476031214, |
| "best_model_checkpoint": "hf-importance-production/checkpoint-48", |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 48, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.4166666666666667, |
| "grad_norm": 8.110058047350321e-07, |
| "learning_rate": 4.347826086956522e-06, |
| "loss": 0.0, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.8333333333333334, |
| "grad_norm": 7.273547453223728e-07, |
| "learning_rate": 8.695652173913044e-06, |
| "loss": 0.0, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.71875, |
| "eval_f1": 0.71875, |
| "eval_f1_macro": 0.4787878787878788, |
| "eval_loss": 1.9374552965164185, |
| "eval_precision": 0.71875, |
| "eval_precision_macro": 0.4787878787878788, |
| "eval_recall": 0.71875, |
| "eval_recall_macro": 0.4787878787878788, |
| "eval_runtime": 17.9975, |
| "eval_samples_per_second": 1.778, |
| "eval_steps_per_second": 0.445, |
| "step": 24 |
| }, |
| { |
| "epoch": 1.25, |
| "grad_norm": 4.793277639691951e-06, |
| "learning_rate": 7.2000000000000005e-06, |
| "loss": 0.0, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.6666666666666665, |
| "grad_norm": 5.300494740367867e-05, |
| "learning_rate": 3.2000000000000003e-06, |
| "loss": 0.0, |
| "step": 40 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.75, |
| "eval_f1": 0.7519509476031214, |
| "eval_f1_macro": 0.5053883314752879, |
| "eval_loss": 1.958841323852539, |
| "eval_precision": 0.7554824561403508, |
| "eval_precision_macro": 0.5029239766081871, |
| "eval_recall": 0.75, |
| "eval_recall_macro": 0.5090909090909091, |
| "eval_runtime": 17.9474, |
| "eval_samples_per_second": 1.783, |
| "eval_steps_per_second": 0.446, |
| "step": 48 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 48, |
| "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": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 48939095697408.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
