metadata
license: mit
base_model: microsoft/deberta-v3-small
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: DeBERTaV3_model_V3
results: []
DeBERTaV3_model_V3
This model is a fine-tuned version of microsoft/deberta-v3-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1653
- Accuracy: 0.9454
- F1: 0.7754
- Precision: 0.7975
- Recall: 0.7545
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: 5
- eval_batch_size: 5
- 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 | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 90 | 0.3559 | 0.875 | 0.0 | 0.0 | 0.0 |
| No log | 2.0 | 180 | 0.2851 | 0.9087 | 0.4602 | 0.8814 | 0.3114 |
| No log | 3.0 | 270 | 0.2462 | 0.9049 | 0.4940 | 0.7381 | 0.3713 |
| No log | 4.0 | 360 | 0.2183 | 0.9222 | 0.6232 | 0.7890 | 0.5150 |
| No log | 5.0 | 450 | 0.1938 | 0.9304 | 0.6869 | 0.7846 | 0.6108 |
| 0.2617 | 6.0 | 540 | 0.1804 | 0.9349 | 0.7129 | 0.7941 | 0.6467 |
| 0.2617 | 7.0 | 630 | 0.1752 | 0.9364 | 0.7231 | 0.7929 | 0.6647 |
| 0.2617 | 8.0 | 720 | 0.1719 | 0.9409 | 0.7539 | 0.7857 | 0.7246 |
| 0.2617 | 9.0 | 810 | 0.1676 | 0.9424 | 0.7601 | 0.7922 | 0.7305 |
| 0.2617 | 10.0 | 900 | 0.1653 | 0.9454 | 0.7754 | 0.7975 | 0.7545 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.1+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1