---
base_model: genaitraining/llama-2-7b-domain-tuned
tags:
- trl
- sft
- generated_from_trainer
datasets:
- generator
model-index:
- name: llama2-7b-tuned-qna
  results: []
library_name: peft
---

<!-- 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. -->

# llama2-7b-tuned-qna

This model is a fine-tuned version of [genaitraining/llama-2-7b-domain-tuned](https://huggingface.co/genaitraining/llama-2-7b-domain-tuned) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7823

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure


The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- _load_in_8bit: False
- _load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
- bnb_4bit_quant_storage: uint8
- load_in_4bit: True
- load_in_8bit: False
### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.821         | 1.0   | 8859 | 0.7823          |


### Framework versions

- PEFT 0.4.0
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.13.0
- Tokenizers 0.19.1