| --- |
| library_name: transformers |
| license: apache-2.0 |
| base_model: Qwen/Qwen2-1.5B |
| tags: |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| model-index: |
| - name: fine_tuned_roct_callback10 |
| results: [] |
| --- |
| |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| should probably proofread and complete it, then remove this comment. --> |
|
|
| # fine_tuned_roct_callback10 |
| |
| This model is a fine-tuned version of [Qwen/Qwen2-1.5B](https://huggingface.co/Qwen/Qwen2-1.5B) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.1842 |
| - Accuracy: 0.9587 |
| |
| ## Model description |
| |
| More information needed |
| |
| ## Intended uses & limitations |
| |
| More information needed |
| |
| ## Training and evaluation data |
| |
| More information needed |
| |
| ## Training procedure |
| |
| ### Training hyperparameters |
| |
| The following hyperparameters were used during training: |
| - learning_rate: 2e-05 |
| - train_batch_size: 8 |
| - eval_batch_size: 8 |
| - seed: 42 |
| - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
| - lr_scheduler_type: linear |
| - num_epochs: 3 |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | |
| |:-------------:|:------:|:----:|:---------------:|:--------:| |
| | 0.6746 | 0.0309 | 100 | 1.1656 | 0.8788 | |
| | 0.5117 | 0.0617 | 200 | 0.3858 | 0.8788 | |
| | 0.3739 | 0.0926 | 300 | 1.0712 | 0.8788 | |
| | 0.4961 | 0.1235 | 400 | 0.3711 | 0.8274 | |
| | 0.2688 | 0.1543 | 500 | 0.1956 | 0.8965 | |
| | 0.2633 | 0.1852 | 600 | 0.2161 | 0.9 | |
| | 0.3015 | 0.2160 | 700 | 0.2866 | 0.9073 | |
| | 0.2304 | 0.2469 | 800 | 0.2740 | 0.9017 | |
| | 0.2114 | 0.2778 | 900 | 0.2462 | 0.9191 | |
| | 0.2807 | 0.3086 | 1000 | 0.2409 | 0.9125 | |
| | 0.2323 | 0.3395 | 1100 | 0.3777 | 0.8837 | |
| | 0.2514 | 0.3704 | 1200 | 0.2062 | 0.9281 | |
| | 0.2278 | 0.4012 | 1300 | 0.1762 | 0.9351 | |
| | 0.2099 | 0.4321 | 1400 | 0.1856 | 0.9247 | |
| | 0.2004 | 0.4630 | 1500 | 0.2237 | 0.9313 | |
| | 0.2177 | 0.4938 | 1600 | 0.1715 | 0.9313 | |
| | 0.3046 | 0.5247 | 1700 | 0.1545 | 0.9434 | |
| | 0.2179 | 0.5556 | 1800 | 0.1713 | 0.9472 | |
| | 0.1665 | 0.5864 | 1900 | 0.1142 | 0.9549 | |
| | 0.2066 | 0.6173 | 2000 | 0.1424 | 0.9563 | |
| | 0.1908 | 0.6481 | 2100 | 0.1284 | 0.9635 | |
| | 0.145 | 0.6790 | 2200 | 0.1550 | 0.9618 | |
| | 0.147 | 0.7099 | 2300 | 0.7114 | 0.8826 | |
| | 0.1634 | 0.7407 | 2400 | 0.1536 | 0.9625 | |
| | 0.1184 | 0.7716 | 2500 | 0.2507 | 0.9458 | |
| | 0.1771 | 0.8025 | 2600 | 0.1449 | 0.9583 | |
| | 0.1399 | 0.8333 | 2700 | 0.2384 | 0.9347 | |
| | 0.1709 | 0.8642 | 2800 | 0.1296 | 0.9542 | |
| | 0.1545 | 0.8951 | 2900 | 0.1842 | 0.9587 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 4.49.0 |
| - Pytorch 2.6.0+cu126 |
| - Datasets 3.3.2 |
| - Tokenizers 0.21.0 |
| |
