---
library_name: transformers
base_model: llama_small_config.json
tags:
- generated_from_trainer
model-index:
- name: llama-3.2-350M-fourier_multiplication_dataset
  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. -->

# llama-3.2-350M-fourier_multiplication_dataset

This model is a fine-tuned version of [llama_small_config.json](https://huggingface.co/llama_small_config.json) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.7836

## 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: 0.0005
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 1

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 2.6476        | 0.1415 | 1000 | 2.5967          |
| 2.0109        | 0.2831 | 2000 | 2.0067          |
| 2.1092        | 0.4246 | 3000 | 2.1034          |
| 1.9086        | 0.5661 | 4000 | 1.9051          |
| 1.8537        | 0.7076 | 5000 | 1.8473          |
| 1.7953        | 0.8492 | 6000 | 1.7943          |
| 1.7858        | 0.9907 | 7000 | 1.7836          |


### Framework versions

- Transformers 4.48.2
- Pytorch 2.3.1+cu118
- Datasets 3.2.0
- Tokenizers 0.21.0