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_fold1
results: []
mdeberta-domain_fold1
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: 0.5289
- Accuracy: 0.8562
- Precision: 0.8293
- Recall: 0.7956
- F1: 0.8011
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 |
|---|---|---|---|---|---|---|---|
| 1.0269 | 1.0 | 19 | 0.8985 | 0.5890 | 0.8630 | 0.3333 | 0.2471 |
| 0.8123 | 2.0 | 38 | 0.7571 | 0.5890 | 0.8630 | 0.3333 | 0.2471 |
| 0.7079 | 3.0 | 57 | 0.7243 | 0.5890 | 0.8630 | 0.3333 | 0.2471 |
| 0.6259 | 4.0 | 76 | 0.7249 | 0.7808 | 0.8511 | 0.6444 | 0.5909 |
| 0.5818 | 5.0 | 95 | 0.7192 | 0.7671 | 0.6242 | 0.6222 | 0.5773 |
| 0.5081 | 6.0 | 114 | 0.6343 | 0.7877 | 0.7129 | 0.6628 | 0.6687 |
| 0.4902 | 7.0 | 133 | 0.5858 | 0.8219 | 0.7819 | 0.7256 | 0.7107 |
| 0.3946 | 8.0 | 152 | 0.5584 | 0.8288 | 0.7766 | 0.7656 | 0.7603 |
| 0.3876 | 9.0 | 171 | 0.5457 | 0.8562 | 0.8396 | 0.7811 | 0.7859 |
| 0.3239 | 10.0 | 190 | 0.5289 | 0.8562 | 0.8293 | 0.7956 | 0.8011 |
Framework versions
- Transformers 4.46.0
- Pytorch 2.3.1
- Datasets 2.21.0
- Tokenizers 0.20.1