---
license: mit
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: HuggingFaceH4/zephyr-7b-beta
model-index:
- name: zephyr_instruct_generation
  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_instruct_generation

This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9931

## 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: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 0.03
- training_steps: 150

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 3.0117        | 0.77  | 10   | 2.3732          |
| 1.8306        | 1.54  | 20   | 1.3573          |
| 1.0831        | 2.31  | 30   | 1.0436          |
| 0.9737        | 3.08  | 40   | 0.9262          |
| 0.8221        | 3.85  | 50   | 0.8332          |
| 0.6876        | 4.62  | 60   | 0.7937          |
| 0.6528        | 5.38  | 70   | 0.7810          |
| 0.5818        | 6.15  | 80   | 0.7389          |
| 0.5041        | 6.92  | 90   | 0.7892          |
| 0.4484        | 7.69  | 100  | 0.7777          |
| 0.3876        | 8.46  | 110  | 0.8553          |
| 0.3731        | 9.23  | 120  | 0.8669          |
| 0.338         | 10.0  | 130  | 0.8619          |
| 0.318         | 10.77 | 140  | 0.9050          |
| 0.3198        | 11.54 | 150  | 0.9931          |


### Framework versions

- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.16.0
- Tokenizers 0.15.0