| { |
| "best_metric": 0.6631765774552385, |
| "best_model_checkpoint": "training_dir/checkpoint-1250", |
| "epoch": 5.0, |
| "eval_steps": 500, |
| "global_step": 1250, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 7.054202556610107, |
| "learning_rate": 3e-05, |
| "loss": 0.947, |
| "step": 250 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.35882867132867136, |
| "eval_f1": 0.18951324487670584, |
| "eval_loss": 1.1078598499298096, |
| "eval_precision": 0.12875801536749965, |
| "eval_recall": 0.35882867132867136, |
| "eval_runtime": 48.7697, |
| "eval_samples_per_second": 46.914, |
| "eval_steps_per_second": 5.864, |
| "step": 250 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 8.063375473022461, |
| "learning_rate": 6e-05, |
| "loss": 0.6685, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.6062062937062938, |
| "eval_f1": 0.57190397933845, |
| "eval_loss": 0.8881105780601501, |
| "eval_precision": 0.5980584671844231, |
| "eval_recall": 0.6062062937062938, |
| "eval_runtime": 48.5739, |
| "eval_samples_per_second": 47.104, |
| "eval_steps_per_second": 5.888, |
| "step": 500 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 17.603412628173828, |
| "learning_rate": 5.25e-05, |
| "loss": 0.5728, |
| "step": 750 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.5878496503496503, |
| "eval_f1": 0.5621748822370558, |
| "eval_loss": 1.6389495134353638, |
| "eval_precision": 0.6276473886381739, |
| "eval_recall": 0.5878496503496503, |
| "eval_runtime": 48.841, |
| "eval_samples_per_second": 46.846, |
| "eval_steps_per_second": 5.856, |
| "step": 750 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 61.78361129760742, |
| "learning_rate": 4.5e-05, |
| "loss": 0.4837, |
| "step": 1000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.6359265734265734, |
| "eval_f1": 0.6211330799726014, |
| "eval_loss": 1.4274829626083374, |
| "eval_precision": 0.6772601484892057, |
| "eval_recall": 0.6359265734265734, |
| "eval_runtime": 48.713, |
| "eval_samples_per_second": 46.969, |
| "eval_steps_per_second": 5.871, |
| "step": 1000 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 3.5804481506347656, |
| "learning_rate": 3.7500000000000003e-05, |
| "loss": 0.3592, |
| "step": 1250 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.6765734265734266, |
| "eval_f1": 0.6631765774552385, |
| "eval_loss": 1.30519437789917, |
| "eval_precision": 0.6758934188659348, |
| "eval_recall": 0.6765734265734266, |
| "eval_runtime": 48.2801, |
| "eval_samples_per_second": 47.39, |
| "eval_steps_per_second": 5.924, |
| "step": 1250 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2500, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "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": 2086004287219104.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
