metadata
library_name: transformers
license: mit
base_model: microsoft/deberta-v3-small
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: deberta-v3-small-Label_B-768-epochs-5
results: []
deberta-v3-small-Label_B-768-epochs-5
This model is a fine-tuned version of microsoft/deberta-v3-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0703
- Accuracy: 0.9868
- F1: 0.9868
- Precision: 0.9869
- Recall: 0.9868
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: 5e-05
- train_batch_size: 12
- eval_batch_size: 12
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 48
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.0851 | 0.9995 | 1066 | 0.0843 | 0.9747 | 0.9746 | 0.9752 | 0.9747 |
| 0.0433 | 2.0 | 2133 | 0.0894 | 0.9755 | 0.9755 | 0.9764 | 0.9755 |
| 0.0251 | 2.9995 | 3199 | 0.0651 | 0.9829 | 0.9829 | 0.9831 | 0.9829 |
| 0.0025 | 4.0 | 4266 | 0.0703 | 0.9868 | 0.9868 | 0.9869 | 0.9868 |
| 0.0035 | 4.9977 | 5330 | 0.0996 | 0.9819 | 0.9820 | 0.9824 | 0.9819 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0