LLM4Cov-Qwen3-4B-SFT-Stage2

This model is a fine-tuned version of hez2024/LLM4Cov-Qwen3-4B-SFT-Stage1 on the cvdp_ecov_train_stage2 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