metadata
license: mit
base_model: microsoft/deberta-v3-small
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: ts_tg
results: []
ts_tg
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: 0.0516
- Accuracy: 0.8517
- F1: 0.8759
- Precision: 0.8996
- Recall: 0.8533
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: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 202 | 0.1370 | 0.5242 | 0.6378 | 0.8129 | 0.5248 |
| No log | 2.0 | 404 | 0.0857 | 0.6877 | 0.7700 | 0.8749 | 0.6875 |
| 0.1567 | 3.0 | 606 | 0.0667 | 0.7810 | 0.8331 | 0.8929 | 0.7809 |
| 0.1567 | 4.0 | 808 | 0.0593 | 0.8145 | 0.8525 | 0.8947 | 0.8142 |
| 0.0566 | 5.0 | 1010 | 0.0554 | 0.8406 | 0.8668 | 0.8926 | 0.8425 |
| 0.0566 | 6.0 | 1212 | 0.0529 | 0.8437 | 0.8718 | 0.8994 | 0.8459 |
| 0.0566 | 7.0 | 1414 | 0.0522 | 0.8474 | 0.8737 | 0.8992 | 0.8496 |
| 0.0383 | 8.0 | 1616 | 0.0516 | 0.8517 | 0.8759 | 0.8996 | 0.8533 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1