ModernBERT-base-ft-financial-news-sentiment-analysis-2
This model is a fine-tuned version of answerdotai/ModernBERT-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1293
- F1 Score: 0.9765
- Precision Score: 0.9765
- Recall Score: 0.9765
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: 8e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.98) and epsilon=1e-06 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Score | Precision Score | Recall Score |
|---|---|---|---|---|---|---|
| 0.6927 | 1.0 | 16 | 0.3884 | 0.8449 | 0.8816 | 0.8265 |
| 0.2203 | 2.0 | 32 | 0.2017 | 0.9556 | 0.9558 | 0.9559 |
| 0.0847 | 3.0 | 48 | 0.1663 | 0.9472 | 0.9507 | 0.9471 |
| 0.0273 | 4.0 | 64 | 0.1765 | 0.9705 | 0.9710 | 0.9706 |
| 0.0198 | 5.0 | 80 | 0.1980 | 0.9646 | 0.9653 | 0.9647 |
| 0.0141 | 6.0 | 96 | 0.1396 | 0.9795 | 0.9797 | 0.9794 |
| 0.0087 | 7.0 | 112 | 0.1204 | 0.9674 | 0.9677 | 0.9676 |
| 0.0013 | 8.0 | 128 | 0.1285 | 0.9705 | 0.9704 | 0.9706 |
| 0.0002 | 9.0 | 144 | 0.1274 | 0.9765 | 0.9765 | 0.9765 |
| 0.0002 | 10.0 | 160 | 0.1293 | 0.9765 | 0.9765 | 0.9765 |
Framework versions
- Transformers 4.48.0.dev0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0