<!-- 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-2e-5-0.01-32-20_augmented_60_percent_empty_2
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: 0.0304
- F1: 0.9166
- Roc Auc: 0.9580
- Accuracy: 0.9460
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: 2.5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- 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 | F1 | Roc Auc | Accuracy |
---|---|---|---|---|---|---|
No log | 1.0 | 63 | 0.1679 | 0.0 | 0.5 | 0.5991 |
No log | 1.99 | 126 | 0.0858 | 0.6802 | 0.7690 | 0.8048 |
No log | 2.99 | 189 | 0.0525 | 0.8974 | 0.9423 | 0.9361 |
No log | 4.0 | 253 | 0.0415 | 0.9041 | 0.9470 | 0.9395 |
No log | 5.0 | 316 | 0.0381 | 0.9023 | 0.9479 | 0.9381 |
No log | 5.99 | 379 | 0.0345 | 0.9082 | 0.9466 | 0.9420 |
No log | 6.99 | 442 | 0.0321 | 0.9155 | 0.9546 | 0.9465 |
0.0888 | 8.0 | 506 | 0.0319 | 0.9106 | 0.9560 | 0.9415 |
0.0888 | 9.0 | 569 | 0.0313 | 0.9123 | 0.9572 | 0.9420 |
0.0888 | 9.96 | 630 | 0.0304 | 0.9166 | 0.9580 | 0.9460 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3