Qwen3-4B-it-pira-ep3-QA-qairm/README.md

library_name, license, base_model, tags, pipeline_tag, model-index

library_name	license	base_model	tags	pipeline_tag	model-index
peft	apache-2.0	Qwen/Qwen3-4B-Instruct-2507	base_model:adapter:Qwen/Qwen3-4B-Instruct-2507 lora transformers	text-generation	name results Qwen3-4B-it-pira-ep3-QA-qairm

Qwen3-4B-it-pira-ep3-QA-qairm

This model is a fine-tuned version of Qwen/Qwen3-4B-Instruct-2507 on the None 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: 0.0002
• train_batch_size: 4
• eval_batch_size: 8
• seed: 13
• gradient_accumulation_steps: 8
• total_train_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: 0.05
• num_epochs: 3

Training results

Framework versions

• PEFT 0.18.1
• Transformers 4.57.6
• Pytorch 2.10.0+cu128
• Datasets 4.8.3
• Tokenizers 0.22.2