golaxy/ReDI_Decomposition

1---2library_name: peft3license: other4base_model: Qwen3-8B5tags:6- llama-factory7- lora8- generated_from_trainer9model-index:10- name: decom_v211  results: []12---13 14<!-- This model card has been generated automatically according to the information the Trainer had access to. You15should probably proofread and complete it, then remove this comment. -->16 17# decom_v218 19This model is a fine-tuned version of [Qwen3-8B] on the Coin dataset.20 21## Model description22 23More information needed24 25## Intended uses & limitations26 27More information needed28 29## Training and evaluation data30 31More information needed32 33## Training procedure34 35### Training hyperparameters36 37The following hyperparameters were used during training:38- learning_rate: 0.000139- train_batch_size: 140- eval_batch_size: 841- seed: 4242- gradient_accumulation_steps: 843- total_train_batch_size: 844- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments45- lr_scheduler_type: cosine46- lr_scheduler_warmup_ratio: 0.147- num_epochs: 3.048 49### Training results50 51 52 53### Framework versions54 55- PEFT 0.15.256- Transformers 4.52.457- Pytorch 2.6.0+cu12458- Datasets 3.6.059- Tokenizers 0.21.1