<!-- 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. -->
fg-bert-sustainability-20-1e-05-0.02-64
This model is a fine-tuned version of Raccourci/fairguest-bert on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0768
- F1: 0.9111
- Roc Auc: 0.9481
- Accuracy: 0.8721
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: 1e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| No log | 1.0 | 55 | 0.3490 | 0.0 | 0.4999 | 0.0946 |
| No log | 2.0 | 110 | 0.3051 | 0.0 | 0.5 | 0.0956 |
| No log | 3.0 | 165 | 0.2361 | 0.2265 | 0.5641 | 0.1611 |
| No log | 4.0 | 220 | 0.1869 | 0.6345 | 0.7492 | 0.4657 |
| No log | 5.0 | 275 | 0.1469 | 0.8934 | 0.9318 | 0.8358 |
| No log | 6.0 | 330 | 0.1197 | 0.9057 | 0.9409 | 0.8555 |
| No log | 7.0 | 385 | 0.1060 | 0.9126 | 0.9507 | 0.8680 |
| No log | 8.0 | 440 | 0.0958 | 0.9151 | 0.9487 | 0.8763 |
| No log | 9.0 | 495 | 0.0912 | 0.9153 | 0.9496 | 0.8721 |
| 0.2274 | 10.0 | 550 | 0.0863 | 0.9163 | 0.9521 | 0.8742 |
| 0.2274 | 11.0 | 605 | 0.0842 | 0.9131 | 0.9507 | 0.8711 |
| 0.2274 | 12.0 | 660 | 0.0816 | 0.9160 | 0.9507 | 0.8773 |
| 0.2274 | 13.0 | 715 | 0.0810 | 0.9156 | 0.9511 | 0.8763 |
| 0.2274 | 14.0 | 770 | 0.0803 | 0.9097 | 0.9484 | 0.8680 |
| 0.2274 | 15.0 | 825 | 0.0790 | 0.9103 | 0.9466 | 0.8690 |
| 0.2274 | 16.0 | 880 | 0.0774 | 0.9100 | 0.9475 | 0.8701 |
| 0.2274 | 17.0 | 935 | 0.0779 | 0.9134 | 0.9499 | 0.8732 |
| 0.2274 | 18.0 | 990 | 0.0767 | 0.9136 | 0.9508 | 0.8763 |
| 0.0682 | 19.0 | 1045 | 0.0767 | 0.9112 | 0.9486 | 0.8732 |
| 0.0682 | 20.0 | 1100 | 0.0768 | 0.9111 | 0.9481 | 0.8721 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
