---
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: ahmedabdelwahed/Mojiz-sft
model-index:
- name: test
  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. -->

# test

This model is a fine-tuned version of [ahmedabdelwahed/Mojiz-sft](https://huggingface.co/ahmedabdelwahed/Mojiz-sft) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0000
- Rewards/chosen: 16.5213
- Rewards/rejected: -7.9440
- Rewards/accuracies: 1.0
- Rewards/margins: 24.4653
- Logps/rejected: -86.9274
- Logps/chosen: -293.2704
- Logits/rejected: -11.2915
- Logits/chosen: -12.2516

## 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: linear
- lr_scheduler_warmup_steps: 150
- training_steps: 1000

### Training results

| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
| 0.0017        | 0.41  | 100  | 0.0000          | 9.9359         | -3.7597          | 1.0                | 13.6956         | -78.5589       | -306.4413    | -11.4127        | -12.4541      |
| 0.0002        | 0.82  | 200  | 0.0000          | 14.1969        | -5.8004          | 1.0                | 19.9973         | -82.6403       | -297.9192    | -11.3000        | -12.2682      |
| 0.0037        | 1.22  | 300  | 0.0000          | 14.8615        | -6.7633          | 1.0                | 21.6248         | -84.5661       | -296.5901    | -11.2673        | -12.2269      |
| 0.0           | 1.63  | 400  | 0.0000          | 15.4935        | -7.6471          | 1.0                | 23.1406         | -86.3337       | -295.3261    | -11.2271        | -12.1591      |
| 0.0           | 2.04  | 500  | 0.0000          | 15.8634        | -7.8871          | 1.0                | 23.7505         | -86.8136       | -294.5863    | -11.2316        | -12.1672      |
| 0.0           | 2.45  | 600  | 0.0000          | 16.1624        | -7.8756          | 1.0                | 24.0380         | -86.7906       | -293.9882    | -11.2578        | -12.2052      |
| 0.0           | 2.86  | 700  | 0.0000          | 16.1247        | -8.2229          | 1.0                | 24.3476         | -87.4853       | -294.0637    | -11.2414        | -12.1705      |
| 0.0           | 3.27  | 800  | 0.0000          | 16.4219        | -7.9771          | 1.0                | 24.3989         | -86.9936       | -293.4693    | -11.2814        | -12.2344      |
| 0.0           | 3.67  | 900  | 0.0000          | 16.4248        | -7.9873          | 1.0                | 24.4122         | -87.0141       | -293.4634    | -11.2812        | -12.2342      |
| 0.0           | 4.08  | 1000 | 0.0000          | 16.5213        | -7.9440          | 1.0                | 24.4653         | -86.9274       | -293.2704    | -11.2915        | -12.2516      |


### Framework versions

- PEFT 0.7.1
- Transformers 4.36.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.15.0