<!-- 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_qa_ner_short
This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1417
- Precision: 0.264
- Recall: 0.5323
- F1: 0.3529
- Accuracy: 0.9703
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: 6
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.2022 | 1.0 | 51 | 0.1392 | 0.0285 | 0.1290 | 0.0466 | 0.9533 |
0.0795 | 2.0 | 102 | 0.1106 | 0.1241 | 0.2903 | 0.1739 | 0.9709 |
0.0424 | 3.0 | 153 | 0.1628 | 0.1576 | 0.4194 | 0.2291 | 0.9613 |
0.0224 | 4.0 | 204 | 0.1243 | 0.1805 | 0.3871 | 0.2462 | 0.9704 |
0.0314 | 5.0 | 255 | 0.1381 | 0.248 | 0.5 | 0.3316 | 0.9694 |
0.0066 | 6.0 | 306 | 0.1417 | 0.264 | 0.5323 | 0.3529 | 0.9703 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cpu
- Datasets 2.14.5
- Tokenizers 0.13.3