---
base_model: unsloth/mistral-7b-instruct-v0.2-bnb-4bit
library_name: peft
license: apache-2.0
tags:
- adapter
- instruct-tuning
- Mistral7B
- Batch_Size-4
- Epoch-1
- trl
- sft
- unsloth
- generated_from_trainer
model-index:
- name: PerspectrumInstruct-Baseline-R_32-Alpha_64_Batch_4-Epoch_1-FT-Unsloth_Mistral7B
  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. -->

# PerspectrumInstruct-Baseline-R_32-Alpha_64_Batch_4-Epoch_1-FT-Unsloth_Mistral7B

This model is a fine-tuned version of [unsloth/mistral-7b-instruct-v0.2-bnb-4bit](https://huggingface.co/unsloth/mistral-7b-instruct-v0.2-bnb-4bit) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3841

## 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: 0.0002
- train_batch_size: 4
- eval_batch_size: 4
- seed: 3407
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 5
- num_epochs: 1

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.356         | 0.1078 | 30   | 1.0690          |
| 1.0215        | 0.2156 | 60   | 0.9446          |
| 0.9024        | 0.3235 | 90   | 0.8369          |
| 0.8971        | 0.4313 | 120  | 0.7261          |
| 0.7858        | 0.5391 | 150  | 0.6317          |
| 0.7608        | 0.6469 | 180  | 0.5461          |
| 0.6772        | 0.7547 | 210  | 0.4775          |
| 0.6375        | 0.8625 | 240  | 0.4176          |
| 0.6158        | 0.9704 | 270  | 0.3841          |


### Framework versions

- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.3.0+cu118
- Datasets 2.20.0
- Tokenizers 0.19.1