metadata
license: other
base_model: microsoft/Orca-2-13b
tags:
- generated_from_trainer
model-index:
- name: qlora
results: []
qlora
This model is a fine-tuned version of microsoft/Orca-2-13b on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.6529
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: 0.0002
- train_batch_size: 6
- eval_batch_size: 6
- seed: 42
- gradient_accumulation_steps: 6
- total_train_batch_size: 36
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 15
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0484 | 1.23 | 20 | 2.6529 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.1+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0