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: 0.2283
- Accuracy: 0.9331
- F1: 0.9272
- Precision: 1.0
- Recall: 0.8643
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: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.7017 | 0.96 | 17 | 0.6835 | 0.5352 | 0.1081 | 1.0 | 0.0571 |
| 0.6085 | 1.97 | 35 | 0.5872 | 0.6866 | 0.5822 | 0.8493 | 0.4429 |
| 0.518 | 2.99 | 53 | 0.4436 | 0.7958 | 0.8141 | 0.7384 | 0.9071 |
| 0.2366 | 4.0 | 71 | 0.2283 | 0.9331 | 0.9272 | 1.0 | 0.8643 |
| 0.1579 | 4.96 | 88 | 0.2696 | 0.9331 | 0.9294 | 0.9690 | 0.8929 |
| 0.1626 | 5.97 | 106 | 0.2726 | 0.9225 | 0.9179 | 0.9609 | 0.8786 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2