|
--- |
|
license: mit |
|
base_model: microsoft/deberta-v3-large |
|
tags: |
|
- trl |
|
- reward-trainer |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: deberta-v3-large-reward-model |
|
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-v3-large-reward-model |
|
|
|
This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0084 |
|
- Accuracy: 0.9975 |
|
|
|
## 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: 1.41e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.0336 | 2.0 | 100 | 0.0315 | 0.9975 | |
|
| 0.0043 | 4.0 | 200 | 0.0105 | 0.9925 | |
|
| 0.0006 | 6.0 | 300 | 0.0079 | 0.9975 | |
|
| 0.0001 | 8.0 | 400 | 0.0086 | 0.9975 | |
|
| 0.0002 | 10.0 | 500 | 0.0084 | 0.9975 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.0 |
|
- Pytorch 2.4.0 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|
