---
license: mit
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: TheBloke/zephyr-7B-beta-GPTQ
model-index:
- name: zephyr_7k
  results: []
---

<!-- 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. -->

# zephyr_7k

This model is a fine-tuned version of [TheBloke/zephyr-7B-beta-GPTQ](https://huggingface.co/TheBloke/zephyr-7B-beta-GPTQ) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2630

## 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: 0.0001
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.3761        | 0.23  | 100  | 1.1737          |
| 0.8147        | 0.46  | 200  | 0.4469          |
| 0.3427        | 0.68  | 300  | 0.2869          |
| 0.2726        | 0.91  | 400  | 0.2630          |


### Framework versions

- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.0.0
- Datasets 2.16.0
- Tokenizers 0.15.0