metadata
license: mit
base_model: microsoft/deberta-base-mnli
tags:
- generated_from_trainer
model-index:
- name: deberta_base_all
results: []
deberta_base_all
This model is a fine-tuned version of microsoft/deberta-base-mnli on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4071
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5695 | 1.0 | 1949 | 0.4123 |
| 0.1587 | 2.0 | 3898 | 0.3700 |
| 0.0671 | 3.0 | 5847 | 0.3963 |
| 0.1556 | 4.0 | 7796 | 0.3373 |
| 0.103 | 5.0 | 9745 | 0.3485 |
| 0.1483 | 6.0 | 11694 | 0.4014 |
| 0.166 | 7.0 | 13643 | 0.3890 |
| 0.0515 | 8.0 | 15592 | 0.3875 |
| 0.0664 | 9.0 | 17541 | 0.4162 |
| 0.0321 | 10.0 | 19490 | 0.4071 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1