metadata
library_name: transformers
license: mit
base_model: microsoft/deberta-v3-base
tags:
- generated_from_trainer
model-index:
- name: results-deberta
results: []
results-deberta
This model is a fine-tuned version of microsoft/deberta-v3-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1976
- F1 Macro: 0.3990
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
- lr_scheduler_warmup_steps: 500
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Macro |
|---|---|---|---|---|
| 0.2118 | 1.0 | 1307 | 0.2059 | 0.2894 |
| 0.1941 | 2.0 | 2614 | 0.1989 | 0.3468 |
| 0.1857 | 3.0 | 3921 | 0.1966 | 0.3980 |
| 0.1766 | 4.0 | 5228 | 0.1976 | 0.3990 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1