<!-- 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. -->
distilt_bert_29_med_intents
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1727
- Accuracy: 0.9655
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: 16
- eval_batch_size: 16
- 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 | Accuracy |
---|---|---|---|---|
No log | 1.0 | 378 | 0.6173 | 0.9091 |
1.4195 | 2.0 | 756 | 0.2166 | 0.9498 |
0.27 | 3.0 | 1134 | 0.1537 | 0.9655 |
0.115 | 4.0 | 1512 | 0.1599 | 0.9624 |
0.115 | 5.0 | 1890 | 0.1444 | 0.9530 |
0.0613 | 6.0 | 2268 | 0.1567 | 0.9655 |
0.0479 | 7.0 | 2646 | 0.1799 | 0.9624 |
0.0291 | 8.0 | 3024 | 0.1752 | 0.9624 |
0.0291 | 9.0 | 3402 | 0.1681 | 0.9687 |
0.0228 | 10.0 | 3780 | 0.1727 | 0.9655 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1