<!-- 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. -->
bert_sm_cv_4
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.3264
- Accuracy: 0.822
- Precision: 0.5714
- Recall: 0.3487
- F1: 0.4331
- D-index: 1.5816
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 8000
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | D-index |
|---|---|---|---|---|---|---|---|---|
| 0.5342 | 1.0 | 1000 | 0.4182 | 0.828 | 0.6117 | 0.3231 | 0.4228 | 1.5811 |
| 0.5562 | 2.0 | 2000 | 0.5091 | 0.825 | 0.5943 | 0.3231 | 0.4186 | 1.5770 |
| 0.5531 | 3.0 | 3000 | 0.6970 | 0.821 | 0.5678 | 0.3436 | 0.4281 | 1.5785 |
| 0.4464 | 4.0 | 4000 | 0.9186 | 0.816 | 0.5495 | 0.3128 | 0.3987 | 1.5615 |
| 0.3459 | 5.0 | 5000 | 1.0847 | 0.815 | 0.5510 | 0.2769 | 0.3686 | 1.5480 |
| 0.2035 | 6.0 | 6000 | 1.2288 | 0.818 | 0.5504 | 0.3641 | 0.4383 | 1.5813 |
| 0.2029 | 7.0 | 7000 | 1.3880 | 0.811 | 0.5395 | 0.2103 | 0.3026 | 1.5198 |
| 0.0907 | 8.0 | 8000 | 1.6336 | 0.824 | 0.6 | 0.2923 | 0.3931 | 1.5654 |
| 0.1161 | 9.0 | 9000 | 1.6379 | 0.799 | 0.4821 | 0.4154 | 0.4463 | 1.5729 |
| 0.0516 | 10.0 | 10000 | 1.6650 | 0.812 | 0.5304 | 0.3128 | 0.3935 | 1.5561 |
| 0.0249 | 11.0 | 11000 | 1.8710 | 0.815 | 0.5410 | 0.3385 | 0.4164 | 1.5688 |
| 0.0097 | 12.0 | 12000 | 1.9980 | 0.821 | 0.5741 | 0.3179 | 0.4092 | 1.5700 |
| 0.0047 | 13.0 | 13000 | 2.1137 | 0.821 | 0.5930 | 0.2615 | 0.3630 | 1.5509 |
| 0.0001 | 14.0 | 14000 | 2.1541 | 0.825 | 0.5893 | 0.3385 | 0.4300 | 1.5822 |
| 0.0038 | 15.0 | 15000 | 2.2491 | 0.814 | 0.5338 | 0.3641 | 0.4329 | 1.5760 |
| 0.0063 | 16.0 | 16000 | 2.2822 | 0.818 | 0.5546 | 0.3385 | 0.4204 | 1.5728 |
| 0.0 | 17.0 | 17000 | 2.3280 | 0.815 | 0.5373 | 0.3692 | 0.4377 | 1.5790 |
| 0.011 | 18.0 | 18000 | 2.3034 | 0.822 | 0.5714 | 0.3487 | 0.4331 | 1.5816 |
| 0.0 | 19.0 | 19000 | 2.3205 | 0.822 | 0.5714 | 0.3487 | 0.4331 | 1.5816 |
| 0.0054 | 20.0 | 20000 | 2.3264 | 0.822 | 0.5714 | 0.3487 | 0.4331 | 1.5816 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
