metadata
license: mit
base_model: microsoft/deberta-v3-large
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: deberta-v3-large-test-231
results: []
deberta-v3-large-test-231
This model is a fine-tuned version of microsoft/deberta-v3-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0695
- Precision: 0.9900
- Recall: 0.9900
- F1: 0.9900
- Accuracy: 0.9900
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: 12
- eval_batch_size: 12
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0663 | 1.0 | 1994 | 0.0489 | 0.9878 | 0.9878 | 0.9878 | 0.9878 |
| 0.0383 | 2.0 | 3988 | 0.0584 | 0.9850 | 0.9850 | 0.9850 | 0.9850 |
| 0.0138 | 3.0 | 5982 | 0.0783 | 0.9870 | 0.9870 | 0.9870 | 0.9870 |
| 0.0026 | 4.0 | 7976 | 0.0691 | 0.9878 | 0.9878 | 0.9878 | 0.9878 |
| 0.0016 | 5.0 | 9970 | 0.0695 | 0.9900 | 0.9900 | 0.9900 | 0.9900 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1