---
license: other
base_model: deepseek-ai/deepseek-math-7b-base
tags:
- alignment-handbook
- generated_from_trainer
datasets:
- AI-MO/numina-problems-sft-v1.7-preproc
model-index:
- name: sft_deepseek-math-7b_aimo_v31.24
  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. -->

# sft_deepseek-math-7b_aimo_v31.24

This model is a fine-tuned version of [deepseek-ai/deepseek-math-7b-base](https://huggingface.co/deepseek-ai/deepseek-math-7b-base) on the AI-MO/numina-problems-sft-v1.7-preproc dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4538

## 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: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 32
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 3.0

### Training results

| Training Loss | Epoch | Step  | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 0.4649        | 1.0   | 6954  | 0.4518          |
| 0.4026        | 2.0   | 13908 | 0.4403          |
| 0.3461        | 3.0   | 20862 | 0.4538          |


### Framework versions

- Transformers 4.41.2
- Pytorch 2.1.2+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1