metadata
library_name: transformers
license: mit
base_model: microsoft/deberta-v3-base
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: mdeberta-domain_EN_fold3
results: []
mdeberta-domain_EN_fold3
This model is a fine-tuned version of microsoft/deberta-v3-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4288
- Accuracy: 0.8414
- Precision: 0.7835
- Recall: 0.7813
- F1: 0.7618
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 1.0342 | 1.0 | 19 | 0.8300 | 0.5931 | 0.8644 | 0.3333 | 0.2482 |
| 0.7812 | 2.0 | 38 | 0.6683 | 0.6414 | 0.8744 | 0.4111 | 0.3821 |
| 0.6431 | 3.0 | 57 | 0.6047 | 0.7793 | 0.8260 | 0.6406 | 0.5553 |
| 0.6002 | 4.0 | 76 | 0.5521 | 0.7931 | 0.8316 | 0.6636 | 0.6016 |
| 0.4757 | 5.0 | 95 | 0.4576 | 0.7862 | 0.6713 | 0.6974 | 0.6574 |
| 0.4112 | 6.0 | 114 | 0.5542 | 0.7517 | 0.6641 | 0.7157 | 0.6721 |
| 0.34 | 7.0 | 133 | 0.4608 | 0.8069 | 0.7236 | 0.7246 | 0.7004 |
| 0.2907 | 8.0 | 152 | 0.4542 | 0.7931 | 0.7067 | 0.7470 | 0.7149 |
| 0.2521 | 9.0 | 171 | 0.4539 | 0.8138 | 0.7410 | 0.7811 | 0.7514 |
| 0.2023 | 10.0 | 190 | 0.4288 | 0.8414 | 0.7835 | 0.7813 | 0.7618 |
Framework versions
- Transformers 4.46.0
- Pytorch 2.3.1
- Datasets 2.21.0
- Tokenizers 0.20.1