metadata
license: mit
base_model: microsoft/deberta-v3-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: content
results: []
content
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: 0.3534
- Accuracy: 0.9252
- F1: 0.9160
- Precision: 0.9677
- Recall: 0.8696
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 |
|---|---|---|---|---|---|---|---|
| 0.0926 | 0.97 | 9 | 0.2219 | 0.9320 | 0.9275 | 0.9275 | 0.9275 |
| 0.0674 | 1.95 | 18 | 0.4954 | 0.8639 | 0.8305 | 1.0 | 0.7101 |
| 0.0295 | 2.92 | 27 | 0.2664 | 0.9320 | 0.9275 | 0.9275 | 0.9275 |
| 0.0478 | 4.0 | 37 | 0.3316 | 0.9116 | 0.9078 | 0.8889 | 0.9275 |
| 0.0377 | 4.86 | 45 | 0.3534 | 0.9252 | 0.9160 | 0.9677 | 0.8696 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2