| { |
| "best_global_step": 93, |
| "best_metric": 0.9518677022450607, |
| "best_model_checkpoint": "lora_pii_detector_mmbert-32k_r8_token_model/checkpoint-93", |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 93, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.3225806451612903, |
| "grad_norm": 28.529237747192383, |
| "learning_rate": 2.7000000000000002e-05, |
| "loss": 5.3341, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.6451612903225806, |
| "grad_norm": 28.822555541992188, |
| "learning_rate": 2.9715728395293587e-05, |
| "loss": 4.263, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.967741935483871, |
| "grad_norm": 23.09440803527832, |
| "learning_rate": 2.874688621590339e-05, |
| "loss": 3.1418, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.5290275761973875, |
| "eval_f1": 0.6812475482822514, |
| "eval_loss": 1.713678240776062, |
| "eval_precision": 0.9564547130584865, |
| "eval_recall": 0.5290275761973876, |
| "eval_runtime": 0.6046, |
| "eval_samples_per_second": 203.455, |
| "eval_steps_per_second": 13.233, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.2903225806451613, |
| "grad_norm": 14.115083694458008, |
| "learning_rate": 2.7135254915624213e-05, |
| "loss": 2.1739, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.6129032258064515, |
| "grad_norm": 9.12806224822998, |
| "learning_rate": 2.495619258285757e-05, |
| "loss": 1.5243, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.935483870967742, |
| "grad_norm": 8.78358268737793, |
| "learning_rate": 2.231158975042979e-05, |
| "loss": 1.3747, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.944121915820029, |
| "eval_f1": 0.9465152764691677, |
| "eval_loss": 0.27175939083099365, |
| "eval_precision": 0.9492522125342383, |
| "eval_recall": 0.944121915820029, |
| "eval_runtime": 0.3095, |
| "eval_samples_per_second": 397.43, |
| "eval_steps_per_second": 25.849, |
| "step": 62 |
| }, |
| { |
| "epoch": 2.258064516129032, |
| "grad_norm": 4.098817348480225, |
| "learning_rate": 1.9325105107520264e-05, |
| "loss": 1.1873, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.5806451612903225, |
| "grad_norm": 7.473396301269531, |
| "learning_rate": 1.613638335679216e-05, |
| "loss": 1.0562, |
| "step": 80 |
| }, |
| { |
| "epoch": 2.903225806451613, |
| "grad_norm": 8.857183456420898, |
| "learning_rate": 1.2894525583299835e-05, |
| "loss": 1.1235, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9477503628447025, |
| "eval_f1": 0.9518677022450607, |
| "eval_loss": 0.24011534452438354, |
| "eval_precision": 0.9565055622257022, |
| "eval_recall": 0.9477503628447025, |
| "eval_runtime": 0.2977, |
| "eval_samples_per_second": 413.23, |
| "eval_steps_per_second": 26.877, |
| "step": 93 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 155, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "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": 101358543358800.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
