<!-- 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. -->
fin4
This model is a fine-tuned version of nlpaueb/sec-bert-num on the fin dataset. It achieves the following results on the evaluation set:
- Loss: 0.0549
- Precision: 0.9209
- Recall: 0.9283
- F1: 0.9246
- Accuracy: 0.9913
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 129 | 0.1041 | 0.8242 | 0.8406 | 0.8323 | 0.9788 |
No log | 2.0 | 258 | 0.0511 | 0.9173 | 0.9283 | 0.9228 | 0.9902 |
No log | 3.0 | 387 | 0.0430 | 0.9102 | 0.9283 | 0.9191 | 0.9907 |
0.0598 | 4.0 | 516 | 0.0501 | 0.9368 | 0.9442 | 0.9405 | 0.9922 |
0.0598 | 5.0 | 645 | 0.0436 | 0.9325 | 0.9363 | 0.9344 | 0.9924 |
0.0598 | 6.0 | 774 | 0.0489 | 0.9433 | 0.9283 | 0.9357 | 0.9917 |
0.0598 | 7.0 | 903 | 0.0499 | 0.932 | 0.9283 | 0.9301 | 0.9919 |
0.0028 | 8.0 | 1032 | 0.0537 | 0.9209 | 0.9283 | 0.9246 | 0.9913 |
0.0028 | 9.0 | 1161 | 0.0540 | 0.9170 | 0.9243 | 0.9206 | 0.9911 |
0.0028 | 10.0 | 1290 | 0.0549 | 0.9209 | 0.9283 | 0.9246 | 0.9913 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.7.1
- Tokenizers 0.13.2