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_fold2
results: []
mdeberta-domain_fold2
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: 0.3971
- Accuracy: 0.925
- Precision: 0.9478
- Recall: 0.6667
- F1: 0.6393
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 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 5 | 1.0148 | 0.525 | 0.8417 | 0.3333 | 0.2295 |
| 1.0205 | 2.0 | 10 | 0.9308 | 0.525 | 0.8417 | 0.3333 | 0.2295 |
| 1.0205 | 3.0 | 15 | 0.8402 | 0.525 | 0.8417 | 0.3333 | 0.2295 |
| 0.8453 | 4.0 | 20 | 0.7396 | 0.525 | 0.8417 | 0.3333 | 0.2295 |
| 0.8453 | 5.0 | 25 | 0.6271 | 0.825 | 0.8883 | 0.5833 | 0.5645 |
| 0.6618 | 6.0 | 30 | 0.5737 | 0.825 | 0.8883 | 0.5833 | 0.5645 |
| 0.6618 | 7.0 | 35 | 0.4670 | 0.9 | 0.9318 | 0.6458 | 0.6212 |
| 0.4922 | 8.0 | 40 | 0.4277 | 0.925 | 0.9478 | 0.6667 | 0.6393 |
| 0.4922 | 9.0 | 45 | 0.4040 | 0.925 | 0.9478 | 0.6667 | 0.6393 |
| 0.4176 | 10.0 | 50 | 0.3971 | 0.925 | 0.9478 | 0.6667 | 0.6393 |
Framework versions
- Transformers 4.46.0
- Pytorch 2.3.1
- Datasets 2.21.0
- Tokenizers 0.20.1