---
library_name: transformers
license: other
base_model: hez2024/LLM4Cov-Qwen3-4B-SFT-Stage0
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: LLM4Cov-Qwen3-4B-SFT-Stage1
  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. -->

# LLM4Cov-Qwen3-4B-SFT-Stage1

This model is a fine-tuned version of [hez2024/LLM4Cov-Qwen3-4B-SFT-Stage0](https://huggingface.co/hez2024/LLM4Cov-Qwen3-4B-SFT-Stage0) on the cvdp_ecov_train_stage1 dataset.

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 6
- total_train_batch_size: 24
- total_eval_batch_size: 32
- 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: 0.03
- num_epochs: 1.0

### Framework versions

- Transformers 4.57.1
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.22.1