metadata
tags:
- generated_from_trainer
metrics:
- accuracy
base_model: ProsusAI/finbert
model-index:
- name: stock_sentiment_hp
results: []
stock_sentiment_hp
This model is a fine-tuned version of ProsusAI/finbert on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3513
- Accuracy: 0.7899
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: 1.1207606211860571e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 2
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
No log | 1.0 | 325 | 0.3687 | 0.7652 |
0.3705 | 2.0 | 650 | 0.3336 | 0.7809 |
0.3705 | 3.0 | 975 | 0.3449 | 0.7926 |
0.2435 | 4.0 | 1300 | 0.3513 | 0.7899 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.7.0
- Tokenizers 0.13.2