metadata
library_name: transformers
license: mit
base_model: microsoft/deberta-v3-base
tags:
- trl
- reward-trainer
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: deberta-v3-base-reward-model
results: []
deberta-v3-base-reward-model
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: 0.0165
- Accuracy: 0.995
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 |
|---|---|---|---|---|
| 0.039 | 2.0 | 100 | 0.0255 | 0.9925 |
| 0.0092 | 4.0 | 200 | 0.0185 | 0.995 |
| 0.0008 | 6.0 | 300 | 0.0148 | 0.995 |
| 0.0022 | 8.0 | 400 | 0.0187 | 0.995 |
| 0.0006 | 10.0 | 500 | 0.0165 | 0.995 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.1
- Datasets 3.0.1
- Tokenizers 0.20.0