metadata
tags:
- generated_from_trainer
metrics:
- f1
base_model: ProsusAI/finbert
model-index:
- name: twiiter_try15_fold1
results: []
twiiter_try15_fold1
This model is a fine-tuned version of ProsusAI/finbert on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1718
- F1: 0.9816
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: 3e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.2154 | 1.0 | 500 | 0.0921 | 0.9763 |
| 0.0689 | 2.0 | 1000 | 0.1517 | 0.9646 |
| 0.0329 | 3.0 | 1500 | 0.0965 | 0.9821 |
| 0.0102 | 4.0 | 2000 | 0.1161 | 0.9819 |
| 0.0097 | 5.0 | 2500 | 0.1399 | 0.9784 |
| 0.0028 | 6.0 | 3000 | 0.2075 | 0.9725 |
| 0.006 | 7.0 | 3500 | 0.1767 | 0.9768 |
| 0.0059 | 8.0 | 4000 | 0.1750 | 0.9775 |
| 0.0001 | 9.0 | 4500 | 0.2467 | 0.9724 |
| 0.0073 | 10.0 | 5000 | 0.1923 | 0.9754 |
| 0.0026 | 11.0 | 5500 | 0.1645 | 0.9790 |
| 0.002 | 12.0 | 6000 | 0.1862 | 0.9801 |
| 0.0008 | 13.0 | 6500 | 0.1643 | 0.98 |
| 0.0 | 14.0 | 7000 | 0.1708 | 0.9816 |
| 0.0 | 15.0 | 7500 | 0.1718 | 0.9816 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3