---
license: mit
library_name: peft
tags:
- generated_from_trainer
base_model: TheBloke/zephyr-7B-alpha-GPTQ
model-index:
- name: zephyr-chatbot
  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-chatbot

This model is a fine-tuned version of [TheBloke/zephyr-7B-alpha-GPTQ](https://huggingface.co/TheBloke/zephyr-7B-alpha-GPTQ) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8794

## 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: gptq
- bits: 4
- tokenizer: None
- dataset: None
- group_size: 128
- damp_percent: 0.1
- desc_act: True
- sym: True
- true_sequential: True
- use_cuda_fp16: False
- model_seqlen: 4095
- block_name_to_quantize: model.layers
- module_name_preceding_first_block: ['model.embed_tokens']
- batch_size: 1
- pad_token_id: None
- use_exllama: False
- max_input_length: None
- exllama_config: {'version': <ExllamaVersion.ONE: 1>}
- cache_block_outputs: True

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 1000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.9364        | 1.0   | 121  | 0.9402          |
| 0.8289        | 2.0   | 242  | 0.8849          |
| 0.7249        | 3.0   | 363  | 0.8540          |
| 0.6322        | 4.0   | 484  | 0.8387          |
| 0.5337        | 5.0   | 605  | 0.8475          |
| 0.4523        | 6.0   | 726  | 0.8586          |
| 0.405         | 7.0   | 847  | 0.8698          |
| 0.3965        | 8.0   | 968  | 0.8794          |
| 0.3859        | 8.26  | 1000 | 0.8794          |


### Framework versions

- PEFT 0.7.0
- Transformers 4.36.0.dev0
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0