---
base_model: mistralai/Mistral-7B-v0.1
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
- trl
- sft
- generated_from_trainer
datasets:
- GAIR/lima
model-index:
- name: mistral-lima
  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-lima

This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the GAIR/lima dataset.
It achieves the following results on the evaluation set:
- Loss: 3.9177

## 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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 16
- total_train_batch_size: 128
- total_eval_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10.0

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.8197        | 1.0   | 6    | 2.1417          |
| 1.3836        | 2.0   | 12   | 1.7507          |
| 0.9111        | 3.0   | 18   | 2.1441          |
| 0.4865        | 4.0   | 24   | 2.5979          |
| 0.0827        | 5.0   | 30   | 2.8178          |
| 0.0365        | 6.0   | 36   | 3.2582          |
| 0.019         | 7.0   | 42   | 3.6269          |
| 0.0127        | 8.0   | 48   | 3.8257          |
| 0.0092        | 9.0   | 54   | 3.9027          |
| 0.0071        | 10.0  | 60   | 3.9177          |


### Framework versions

- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 2.14.6
- Tokenizers 0.15.2