| { |
| "best_global_step": 80, |
| "best_metric": 0.9958399986721193, |
| "best_model_checkpoint": "/home/ubuntu/context_aware_modeling/fine_tuning/checkpoints/qwen3-8b_r32/checkpoint-80", |
| "epoch": 1.8181818181818183, |
| "eval_steps": 20, |
| "global_step": 100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.36363636363636365, |
| "eval_accuracy": 0.9044056525353283, |
| "eval_balanced_accuracy": 0.901877133105802, |
| "eval_loss": 0.08732637017965317, |
| "eval_macro_f1": 0.90297659081011, |
| "eval_runtime": 39.9812, |
| "eval_samples_per_second": 30.089, |
| "eval_steps_per_second": 0.475, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.7272727272727273, |
| "eval_accuracy": 0.742310889443059, |
| "eval_balanced_accuracy": 0.735494880546075, |
| "eval_loss": 0.08577165752649307, |
| "eval_macro_f1": 0.7197970138129186, |
| "eval_runtime": 39.9877, |
| "eval_samples_per_second": 30.084, |
| "eval_steps_per_second": 0.475, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.9090909090909091, |
| "grad_norm": 0.41501519083976746, |
| "learning_rate": 8.517573744099741e-05, |
| "loss": 0.26, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.0909090909090908, |
| "eval_accuracy": 0.9858686616791354, |
| "eval_balanced_accuracy": 0.985494880546075, |
| "eval_loss": 0.08195541054010391, |
| "eval_macro_f1": 0.9858461282921714, |
| "eval_runtime": 39.8666, |
| "eval_samples_per_second": 30.176, |
| "eval_steps_per_second": 0.477, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.4545454545454546, |
| "eval_accuracy": 0.9958437240232751, |
| "eval_balanced_accuracy": 0.9957337883959044, |
| "eval_loss": 0.07636160403490067, |
| "eval_macro_f1": 0.9958399986721193, |
| "eval_runtime": 39.884, |
| "eval_samples_per_second": 30.162, |
| "eval_steps_per_second": 0.476, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.8181818181818183, |
| "grad_norm": 0.09980760514736176, |
| "learning_rate": 3.845094616073783e-05, |
| "loss": 0.0789, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.8181818181818183, |
| "eval_accuracy": 0.9958437240232751, |
| "eval_balanced_accuracy": 0.9957337883959044, |
| "eval_loss": 0.07304411381483078, |
| "eval_macro_f1": 0.9958399986721193, |
| "eval_runtime": 39.9125, |
| "eval_samples_per_second": 30.141, |
| "eval_steps_per_second": 0.476, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 165, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 20, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 5, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 1 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.010343436759859e+17, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
