---
library_name: transformers
license: apache-2.0
base_model: mistralai/Mistral-7B-Instruct-v0.1
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
- trl
- sft
- alignment-handbook
- generated_from_trainer
datasets:
- generator
model-index:
- name: mistral_sky_o1_4_full
  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_sky_o1_4_full

This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6130

## 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: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- total_eval_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: 1

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 0.719         | 0.1678 | 100  | 0.7392          |
| 0.6588        | 0.3356 | 200  | 0.7134          |
| 0.6216        | 0.5034 | 300  | 0.6813          |
| 0.5948        | 0.6711 | 400  | 0.6399          |
| 0.5367        | 0.8389 | 500  | 0.6199          |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1