metadata
license: mit
base_model: microsoft/deberta-v3-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: deberta_v3_base_finetune_hellaswag
results: []
deberta_v3_finetune_hellaswag
This model is a fine-tuned version of microsoft/deberta-v3-base on an the hellaswag dataset. It achieves the following results on the evaluation set:
- Loss: 0.3999
- Accuracy: 0.8765
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: 16
- eval_batch_size: 16
- 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: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5083 | 0.9996 | 1247 | 0.3641 | 0.8622 |
| 0.193 | 1.9992 | 2494 | 0.3999 | 0.8765 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.19.1