<!-- 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. -->
email_q_ner_short_2
This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0829
- Precision: 0.45
- Recall: 0.6923
- F1: 0.5455
- Accuracy: 0.9863
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0466 | 1.0 | 72 | 0.0725 | 0.2462 | 0.4103 | 0.3077 | 0.9871 |
| 0.0178 | 2.0 | 144 | 0.0631 | 0.4032 | 0.6410 | 0.4950 | 0.9860 |
| 0.0127 | 3.0 | 216 | 0.0435 | 0.4091 | 0.6923 | 0.5143 | 0.9885 |
| 0.0061 | 4.0 | 288 | 0.0941 | 0.3492 | 0.5641 | 0.4314 | 0.9851 |
| 0.0051 | 5.0 | 360 | 0.0824 | 0.4107 | 0.5897 | 0.4842 | 0.9868 |
| 0.0028 | 6.0 | 432 | 0.0829 | 0.45 | 0.6923 | 0.5455 | 0.9863 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cpu
- Datasets 2.14.5
- Tokenizers 0.13.3
