<!-- 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. -->
phrasebank-sentiment-analysis
This model is a fine-tuned version of bert-base-uncased on the financial_phrasebank dataset. It achieves the following results on the evaluation set:
- Loss: 0.9618
- F1: 0.8428
- Accuracy: 0.8549
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- 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 | Accuracy |
---|---|---|---|---|---|
0.0872 | 0.94 | 100 | 0.6726 | 0.8262 | 0.8549 |
0.0621 | 1.89 | 200 | 0.7939 | 0.8362 | 0.8556 |
0.0567 | 2.83 | 300 | 0.7211 | 0.8462 | 0.8645 |
0.0395 | 3.77 | 400 | 0.7824 | 0.8350 | 0.8556 |
0.0326 | 4.72 | 500 | 0.8522 | 0.8448 | 0.8618 |
0.0228 | 5.66 | 600 | 0.9315 | 0.8342 | 0.8466 |
0.0192 | 6.6 | 700 | 0.9355 | 0.8302 | 0.8487 |
0.0107 | 7.55 | 800 | 0.9090 | 0.8475 | 0.8611 |
0.0058 | 8.49 | 900 | 0.9500 | 0.8455 | 0.8583 |
0.0031 | 9.43 | 1000 | 0.9618 | 0.8428 | 0.8549 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1