Model
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: 1.5484
- F1: 0.7866
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.8731 | 1.0 | 1469 | 0.9043 | 0.6580 |
| 0.5627 | 2.0 | 2938 | 0.7961 | 0.7249 |
| 0.3709 | 3.0 | 4407 | 0.7498 | 0.7616 |
| 0.2306 | 4.0 | 5876 | 1.0133 | 0.7449 |
| 0.1605 | 5.0 | 7345 | 0.9206 | 0.7930 |
| 0.0903 | 6.0 | 8814 | 1.1841 | 0.7797 |
| 0.0506 | 7.0 | 10283 | 1.4182 | 0.7864 |
| 0.027 | 8.0 | 11752 | 1.5484 | 0.7866 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1
- Downloads last month
- 111
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for MohammadKarami/mdebertatask2
Base model
microsoft/mdeberta-v3-base