RoBERTa_FPB_finetuned_v2
This model is a fine-tuned version of soleimanian/financial-roberta-large-sentiment on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5080
- Accuracy: 0.8660
- F1: 0.8658
- Precision: 0.8663
- Recall: 0.8660
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: 16
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 4
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
---|---|---|---|---|---|---|---|
0.3263 | 1.0 | 218 | 0.3427 | 0.8711 | 0.8725 | 0.8797 | 0.8711 |
0.377 | 2.0 | 436 | 0.4305 | 0.8454 | 0.8458 | 0.8470 | 0.8454 |
0.2243 | 3.0 | 654 | 0.5149 | 0.8763 | 0.8756 | 0.8769 | 0.8763 |
0.1564 | 4.0 | 872 | 0.5080 | 0.8660 | 0.8658 | 0.8663 | 0.8660 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Tokenizers 0.19.1
- Downloads last month
- 12