metadata
license: mit
base_model: microsoft/deberta-v3-base
tags:
- generated_from_trainer
datasets:
- eli5_category
model-index:
- name: finetuned-DebertaV3-eli5-askscience-TextGeneration
results: []
finetuned-DebertaV3-eli5-askscience-TextGeneration
This model is a fine-tuned version of microsoft/deberta-v3-base on the eli5_category dataset. It achieves the following results on the evaluation set:
- Loss: 3.4874
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: 2e-05
- train_batch_size: 24
- eval_batch_size: 24
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.9941 | 1.0 | 1034 | 4.4596 |
| 4.4026 | 2.0 | 2068 | 3.8975 |
| 4.3024 | 3.0 | 3102 | 3.6848 |
| 3.67 | 4.0 | 4136 | 3.5170 |
| 3.6813 | 5.0 | 5170 | 3.5066 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2