---
library_name: transformers
license: other
base_model: /gpfs/public/align/huxueyu/MultilingualSL/LLaMA-Factory/saves/qwen2_5_7B/full/en_train_1+20241201-075443
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: es_train_256+20250205-111134
  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. -->

# es_train_256+20250205-111134

This model is a fine-tuned version of [/gpfs/public/align/huxueyu/MultilingualSL/LLaMA-Factory/saves/qwen2_5_7B/full/en_train_1+20241201-075443](https://huggingface.co//gpfs/public/align/huxueyu/MultilingualSL/LLaMA-Factory/saves/qwen2_5_7B/full/en_train_1+20241201-075443) on the es_train_256 dataset.

## 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: 2
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 64
- total_train_batch_size: 1024
- total_eval_batch_size: 64
- optimizer: Use OptimizerNames.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_ratio: 0.04
- num_epochs: 3.0

### Training results



### Framework versions

- Transformers 4.46.1
- Pytorch 2.4.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3