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: 0.4601
- Accuracy: 0.8630
- Precision: 0.8456
- Recall: 0.8212
- F1: 0.8320
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 |
|---|---|---|---|---|---|---|---|
| 1.0441 | 1.0 | 19 | 0.8982 | 0.5890 | 0.8630 | 0.3333 | 0.2471 |
| 0.8108 | 2.0 | 38 | 0.7417 | 0.5890 | 0.8630 | 0.3333 | 0.2471 |
| 0.7043 | 3.0 | 57 | 0.7361 | 0.6438 | 0.7410 | 0.4222 | 0.3842 |
| 0.5828 | 4.0 | 76 | 0.6559 | 0.7192 | 0.6862 | 0.5517 | 0.5662 |
| 0.5089 | 5.0 | 95 | 0.5497 | 0.8562 | 0.8516 | 0.7811 | 0.7923 |
| 0.3767 | 6.0 | 114 | 0.5299 | 0.8425 | 0.8558 | 0.7517 | 0.7753 |
| 0.3405 | 7.0 | 133 | 0.4696 | 0.8699 | 0.8707 | 0.8034 | 0.8248 |
| 0.2441 | 8.0 | 152 | 0.4845 | 0.8425 | 0.8207 | 0.8168 | 0.8186 |
| 0.2385 | 9.0 | 171 | 0.4611 | 0.8767 | 0.8706 | 0.8217 | 0.8400 |
| 0.1887 | 10.0 | 190 | 0.4601 | 0.8630 | 0.8456 | 0.8212 | 0.8320 |
Framework versions
- Transformers 4.46.0
- Pytorch 2.3.1
- Datasets 2.21.0
- Tokenizers 0.20.1