metadata
license: mit
base_model: microsoft/deberta-v3-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: fine_tuned_deberta
results: []
fine_tuned_deberta
This model is a fine-tuned version of microsoft/deberta-v3-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2193
- Accuracy: 0.9437
- F1: 0.9398
- Precision: 0.9921
- Recall: 0.8929
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.7008 | 0.96 | 17 | 0.6755 | 0.5704 | 0.2375 | 0.95 | 0.1357 |
| 0.578 | 1.97 | 35 | 0.5885 | 0.6866 | 0.5822 | 0.8493 | 0.4429 |
| 0.4858 | 2.99 | 53 | 0.4109 | 0.8239 | 0.8344 | 0.7778 | 0.9 |
| 0.2615 | 4.0 | 71 | 0.2202 | 0.9401 | 0.9373 | 0.9695 | 0.9071 |
| 0.1685 | 4.79 | 85 | 0.2193 | 0.9437 | 0.9398 | 0.9921 | 0.8929 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2