distil_bert_uncased-finetuned-relations
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: 0.4191
- Accuracy: 0.8866
- Prec: 0.8771
- Recall: 0.8866
- F1: 0.8808
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Prec | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 1.1823 | 1.0 | 232 | 0.5940 | 0.8413 | 0.8273 | 0.8413 | 0.8224 |
| 0.4591 | 2.0 | 464 | 0.4600 | 0.8607 | 0.8539 | 0.8607 | 0.8555 |
| 0.3106 | 3.0 | 696 | 0.4160 | 0.8812 | 0.8763 | 0.8812 | 0.8785 |
| 0.246 | 4.0 | 928 | 0.4113 | 0.8834 | 0.8766 | 0.8834 | 0.8796 |
| 0.2013 | 5.0 | 1160 | 0.4191 | 0.8866 | 0.8771 | 0.8866 | 0.8808 |
Framework versions
- Transformers 4.19.4
- Pytorch 1.13.0.dev20220614
- Datasets 2.2.2
- Tokenizers 0.11.6
- Downloads last month
- 48
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.