---
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: 1.2879

## 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: 3e-05
- 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: 400

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 3.3773        | 0.77  | 10   | 2.9712          |
| 2.8948        | 1.54  | 20   | 2.5856          |
| 2.4289        | 2.31  | 30   | 2.2310          |
| 2.0707        | 3.08  | 40   | 1.8374          |
| 1.6398        | 3.85  | 50   | 1.4469          |
| 1.2391        | 4.62  | 60   | 1.2461          |
| 1.1218        | 5.38  | 70   | 1.0960          |
| 0.969         | 6.15  | 80   | 0.9912          |
| 0.8524        | 6.92  | 90   | 0.9169          |
| 0.795         | 7.69  | 100  | 0.8785          |
| 0.7214        | 8.46  | 110  | 0.8506          |
| 0.6816        | 9.23  | 120  | 0.7987          |
| 0.6392        | 10.0  | 130  | 0.8146          |
| 0.5615        | 10.77 | 140  | 0.8004          |
| 0.5619        | 11.54 | 150  | 0.7833          |
| 0.4588        | 12.31 | 160  | 0.7906          |
| 0.4674        | 13.08 | 170  | 0.8011          |
| 0.4311        | 13.85 | 180  | 0.8330          |
| 0.3866        | 14.62 | 190  | 0.8773          |
| 0.3581        | 15.38 | 200  | 0.9049          |
| 0.3656        | 16.15 | 210  | 0.8357          |
| 0.3231        | 16.92 | 220  | 0.9665          |
| 0.3144        | 17.69 | 230  | 0.9519          |
| 0.3019        | 18.46 | 240  | 0.9800          |
| 0.2953        | 19.23 | 250  | 1.0051          |
| 0.2822        | 20.0  | 260  | 1.0017          |
| 0.2573        | 20.77 | 270  | 1.0349          |
| 0.2641        | 21.54 | 280  | 1.1069          |
| 0.2494        | 22.31 | 290  | 1.1577          |
| 0.2456        | 23.08 | 300  | 1.1906          |
| 0.2393        | 23.85 | 310  | 1.0416          |
| 0.2293        | 24.62 | 320  | 1.2253          |
| 0.2286        | 25.38 | 330  | 1.1886          |
| 0.2341        | 26.15 | 340  | 1.1371          |
| 0.2222        | 26.92 | 350  | 1.3020          |
| 0.2159        | 27.69 | 360  | 1.2110          |
| 0.2185        | 28.46 | 370  | 1.2803          |
| 0.2192        | 29.23 | 380  | 1.1759          |
| 0.2203        | 30.0  | 390  | 1.2866          |
| 0.2187        | 30.77 | 400  | 1.2879          |


### Framework versions

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