<!-- 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. -->
bert-based_uncased-finetuned-financial-talk
This model is a fine-tuned version of bert-base-uncased on zeroshot/twitter-financial-news-topic dataset. It achieves the following results on the evaluation set:
- Loss: 0.3595
- Accuracy: 0.9011
- F1: 0.9002
- Precision: 0.9013
- Recall: 0.9011
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: 2e-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: 6
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
---|---|---|---|---|---|---|---|
1.792 | 1.0 | 238 | 0.8558 | 0.8076 | 0.7885 | 0.7889 | 0.8076 |
0.6612 | 1.99 | 476 | 0.5125 | 0.8671 | 0.8610 | 0.8665 | 0.8671 |
0.373 | 2.99 | 714 | 0.4315 | 0.8773 | 0.8740 | 0.8765 | 0.8773 |
0.2363 | 3.98 | 952 | 0.3770 | 0.8960 | 0.8939 | 0.8936 | 0.8960 |
0.169 | 4.98 | 1190 | 0.3614 | 0.9004 | 0.8990 | 0.9015 | 0.9004 |
0.1361 | 5.97 | 1428 | 0.3595 | 0.9011 | 0.9002 | 0.9013 | 0.9011 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1