<!-- 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-15-2.6e-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: 0.0675
- F1: 0.9128
- Roc Auc: 0.9545
- Accuracy: 0.8711
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: 2.6e-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: 15
Training results
Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
---|---|---|---|---|---|---|
No log | 1.0 | 55 | 0.2865 | 0.0 | 0.5 | 0.0956 |
No log | 2.0 | 110 | 0.1733 | 0.8114 | 0.9007 | 0.6850 |
No log | 3.0 | 165 | 0.1040 | 0.9004 | 0.9393 | 0.8555 |
No log | 4.0 | 220 | 0.0902 | 0.8980 | 0.9413 | 0.8514 |
No log | 5.0 | 275 | 0.0779 | 0.9058 | 0.9484 | 0.8565 |
No log | 6.0 | 330 | 0.0766 | 0.9013 | 0.9431 | 0.8576 |
No log | 7.0 | 385 | 0.0739 | 0.9043 | 0.9482 | 0.8607 |
No log | 8.0 | 440 | 0.0698 | 0.9161 | 0.9540 | 0.8784 |
No log | 9.0 | 495 | 0.0721 | 0.9073 | 0.9509 | 0.8680 |
0.1291 | 10.0 | 550 | 0.0683 | 0.9106 | 0.9504 | 0.8690 |
0.1291 | 11.0 | 605 | 0.0707 | 0.9060 | 0.9470 | 0.8617 |
0.1291 | 12.0 | 660 | 0.0659 | 0.9175 | 0.9560 | 0.8805 |
0.1291 | 13.0 | 715 | 0.0673 | 0.9089 | 0.9516 | 0.8680 |
0.1291 | 14.0 | 770 | 0.0673 | 0.9127 | 0.9540 | 0.8701 |
0.1291 | 15.0 | 825 | 0.0675 | 0.9128 | 0.9545 | 0.8711 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3