metadata
license: mit
base_model: microsoft/deberta-v3-base
tags:
- generated_from_trainer
model-index:
- name: deberta-v3-base-1107
results: []
deberta-v3-base-1107
This model is a fine-tuned version of microsoft/deberta-v3-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9863
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7812 | 1.0 | 1828 | 0.9348 |
| 0.4504 | 2.0 | 3656 | 0.7760 |
| 0.331 | 3.0 | 5484 | 0.6675 |
| 0.2598 | 4.0 | 7312 | 0.6908 |
| 0.1981 | 5.0 | 9140 | 0.6874 |
| 0.1503 | 6.0 | 10968 | 0.7792 |
| 0.1196 | 7.0 | 12796 | 0.8088 |
| 0.093 | 8.0 | 14624 | 0.8430 |
| 0.0709 | 9.0 | 16452 | 0.9185 |
| 0.0554 | 10.0 | 18280 | 0.9863 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1