metadata
base_model: FPTAI/vibert-base-cased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vi_fin_news
results: []
vi_fin_news
This model is a fine-tuned version of FPTAI/vibert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7477
- Accuracy: 0.9176
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: 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2248 | 1.0 | 1150 | 0.2021 | 0.9172 |
| 0.182 | 2.0 | 2300 | 0.2216 | 0.9230 |
| 0.1301 | 3.0 | 3450 | 0.2681 | 0.9181 |
| 0.0985 | 4.0 | 4600 | 0.3468 | 0.9226 |
| 0.0651 | 5.0 | 5750 | 0.5141 | 0.9070 |
| 0.0332 | 6.0 | 6900 | 0.5732 | 0.9187 |
| 0.0266 | 7.0 | 8050 | 0.5991 | 0.9161 |
| 0.0129 | 8.0 | 9200 | 0.6872 | 0.9157 |
| 0.0095 | 9.0 | 10350 | 0.7212 | 0.9187 |
| 0.0023 | 10.0 | 11500 | 0.7477 | 0.9176 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.2
- Datasets 2.12.0
- Tokenizers 0.13.3