metadata
library_name: transformers
license: mit
base_model: microsoft/mdeberta-v3-base
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: mdeberta-domain_fold4
results: []
mdeberta-domain_fold4
This model is a fine-tuned version of microsoft/mdeberta-v3-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3705
- Accuracy: 0.8552
- Precision: 0.8128
- Recall: 0.8276
- F1: 0.8194
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 |
|---|---|---|---|---|---|---|---|
| 1.0349 | 1.0 | 19 | 0.9208 | 0.5931 | 0.8644 | 0.3333 | 0.2482 |
| 0.88 | 2.0 | 38 | 0.7011 | 0.5931 | 0.8644 | 0.3333 | 0.2482 |
| 0.68 | 3.0 | 57 | 0.6370 | 0.5931 | 0.8644 | 0.3333 | 0.2482 |
| 0.6179 | 4.0 | 76 | 0.5360 | 0.8 | 0.6860 | 0.6971 | 0.6459 |
| 0.4709 | 5.0 | 95 | 0.3949 | 0.8483 | 0.7967 | 0.7860 | 0.7852 |
| 0.3643 | 6.0 | 114 | 0.3526 | 0.8690 | 0.8279 | 0.8209 | 0.8236 |
| 0.2901 | 7.0 | 133 | 0.3713 | 0.8690 | 0.8269 | 0.8277 | 0.8242 |
| 0.2414 | 8.0 | 152 | 0.3506 | 0.8759 | 0.8394 | 0.8392 | 0.8374 |
| 0.1941 | 9.0 | 171 | 0.3766 | 0.8621 | 0.8206 | 0.8391 | 0.8290 |
| 0.1977 | 10.0 | 190 | 0.3705 | 0.8552 | 0.8128 | 0.8276 | 0.8194 |
Framework versions
- Transformers 4.46.0
- Pytorch 2.3.1
- Datasets 2.21.0
- Tokenizers 0.20.1