|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: deberta-base.as.finetuned |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# deberta-base.as.finetuned |
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 5.9191 |
|
|
|
## 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 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 6.6297 | 0.46 | 1000 | 6.5539 | |
|
| 6.4688 | 0.92 | 2000 | 6.4491 | |
|
| 6.3844 | 1.38 | 3000 | 6.3672 | |
|
| 6.3167 | 1.84 | 4000 | 6.2918 | |
|
| 6.252 | 2.3 | 5000 | 6.2378 | |
|
| 6.2027 | 2.76 | 6000 | 6.1876 | |
|
| 6.1586 | 3.22 | 7000 | 6.1400 | |
|
| 6.1194 | 3.68 | 8000 | 6.1085 | |
|
| 6.0882 | 4.14 | 9000 | 6.0751 | |
|
| 6.0543 | 4.6 | 10000 | 6.0519 | |
|
| 6.023 | 5.06 | 11000 | 6.0291 | |
|
| 6.0118 | 5.52 | 12000 | 6.0053 | |
|
| 5.9866 | 5.98 | 13000 | 5.9925 | |
|
| 5.9737 | 6.44 | 14000 | 5.9772 | |
|
| 5.9609 | 6.9 | 15000 | 5.9589 | |
|
| 5.9537 | 7.36 | 16000 | 5.9472 | |
|
| 5.9366 | 7.82 | 17000 | 5.9419 | |
|
| 5.9282 | 8.28 | 18000 | 5.9283 | |
|
| 5.926 | 8.74 | 19000 | 5.9246 | |
|
| 5.9194 | 9.2 | 20000 | 5.9283 | |
|
| 5.9172 | 9.66 | 21000 | 5.9273 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu118 |
|
- Datasets 2.17.1 |
|
- Tokenizers 0.15.2 |
|
|
