<!-- 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_gen1_summarized_cv_4
This model is a fine-tuned version of wiorz/bert_sm_gen1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.1011
- Accuracy: 0.801
- Precision: 0.4706
- Recall: 0.1641
- F1: 0.2433
- D-index: 1.4901
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: 16
- eval_batch_size: 16
- 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 |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 250 | 2.4563 | 0.79 | 0.44 | 0.2821 | 0.3438 | 1.5158 |
| 1.9188 | 2.0 | 500 | 0.7587 | 0.78 | 0.4126 | 0.3026 | 0.3491 | 1.5091 |
| 1.9188 | 3.0 | 750 | 0.4834 | 0.809 | 0.5345 | 0.1590 | 0.2451 | 1.4992 |
| 0.4332 | 4.0 | 1000 | 0.5400 | 0.811 | 0.5366 | 0.2256 | 0.3177 | 1.5251 |
| 0.4332 | 5.0 | 1250 | 0.6813 | 0.787 | 0.4286 | 0.2769 | 0.3364 | 1.5100 |
| 0.2633 | 6.0 | 1500 | 0.9358 | 0.794 | 0.4286 | 0.1692 | 0.2426 | 1.4822 |
| 0.2633 | 7.0 | 1750 | 1.5052 | 0.786 | 0.4159 | 0.2410 | 0.3052 | 1.4962 |
| 0.1124 | 8.0 | 2000 | 1.7146 | 0.791 | 0.4239 | 0.2 | 0.2718 | 1.4888 |
| 0.1124 | 9.0 | 2250 | 1.8601 | 0.794 | 0.4382 | 0.2 | 0.2746 | 1.4930 |
| 0.0465 | 10.0 | 2500 | 1.9701 | 0.774 | 0.3869 | 0.2718 | 0.3193 | 1.4903 |
| 0.0465 | 11.0 | 2750 | 2.0934 | 0.78 | 0.4101 | 0.2923 | 0.3413 | 1.5056 |
| 0.0297 | 12.0 | 3000 | 2.0712 | 0.79 | 0.4336 | 0.2513 | 0.3182 | 1.5053 |
| 0.0297 | 13.0 | 3250 | 2.1711 | 0.79 | 0.4299 | 0.2359 | 0.3046 | 1.4999 |
| 0.0328 | 14.0 | 3500 | 2.1590 | 0.795 | 0.45 | 0.2308 | 0.3051 | 1.5050 |
| 0.0328 | 15.0 | 3750 | 2.1184 | 0.803 | 0.4861 | 0.1795 | 0.2622 | 1.4982 |
| 0.0311 | 16.0 | 4000 | 2.1504 | 0.789 | 0.4355 | 0.2769 | 0.3386 | 1.5127 |
| 0.0311 | 17.0 | 4250 | 2.2112 | 0.773 | 0.3947 | 0.3077 | 0.3458 | 1.5013 |
| 0.0264 | 18.0 | 4500 | 2.2326 | 0.795 | 0.4519 | 0.2410 | 0.3144 | 1.5086 |
| 0.0264 | 19.0 | 4750 | 2.3306 | 0.774 | 0.3885 | 0.2769 | 0.3234 | 1.4921 |
| 0.0391 | 20.0 | 5000 | 2.1011 | 0.801 | 0.4706 | 0.1641 | 0.2433 | 1.4901 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
