---
base_model: mistralai/Mistral-7B-Instruct-v0.3
library_name: peft
license: apache-2.0
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: Mistral-7B_task-3_120-samples_config-2_auto
  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. -->

# Mistral-7B_task-3_120-samples_config-2_auto

This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5208

## 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: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 50

### Training results

| Training Loss | Epoch   | Step | Validation Loss |
|:-------------:|:-------:|:----:|:---------------:|
| 3.1892        | 0.9091  | 5    | 2.4894          |
| 1.3236        | 2.0     | 11   | 0.7405          |
| 0.4001        | 2.9091  | 16   | 0.4180          |
| 0.3601        | 4.0     | 22   | 0.3182          |
| 0.217         | 4.9091  | 27   | 0.2956          |
| 0.1679        | 6.0     | 33   | 0.2813          |
| 0.1291        | 6.9091  | 38   | 0.3133          |
| 0.0786        | 8.0     | 44   | 0.3621          |
| 0.0336        | 8.9091  | 49   | 0.4239          |
| 0.0221        | 10.0    | 55   | 0.4524          |
| 0.0153        | 10.9091 | 60   | 0.4673          |
| 0.0094        | 12.0    | 66   | 0.4911          |
| 0.0063        | 12.9091 | 71   | 0.5208          |


### Framework versions

- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.1.2+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1