finalform/parse_case_info_Qwen3-Coder-30B-A3B-Instruct

1---2library_name: peft3license: other4base_model: Qwen/Qwen3-Coder-30B-A3B-Instruct5tags:6- base_model:adapter:Qwen/Qwen3-Coder-30B-A3B-Instruct7- llama-factory8- lora9- transformers10metrics:11- accuracy12pipeline_tag: text-generation13model-index:14- name: parse_case_info_results15  results: []16---17 18<!-- This model card has been generated automatically according to the information the Trainer had access to. You19should probably proofread and complete it, then remove this comment. -->20 21# parse_case_info_results22 23This model is a fine-tuned version of [Qwen/Qwen3-Coder-30B-A3B-Instruct](https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct) on the train dataset.24It achieves the following results on the evaluation set:25- Loss: 0.021626- Accuracy: 0.998427 28## Model description29 30More information needed31 32## Intended uses & limitations33 34More information needed35 36## Training and evaluation data37 38More information needed39 40## Training procedure41 42### Training hyperparameters43 44The following hyperparameters were used during training:45- learning_rate: 0.000446- train_batch_size: 447- eval_batch_size: 248- seed: 4249- distributed_type: multi-GPU50- num_devices: 451- total_train_batch_size: 1652- total_eval_batch_size: 853- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments54- lr_scheduler_type: cosine55- lr_scheduler_warmup_ratio: 0.08556- num_epochs: 3.057 58### Training results59 60| Training Loss | Epoch | Step | Validation Loss | Accuracy |61|:-------------:|:-----:|:----:|:---------------:|:--------:|62| 0.0332        | 2.0   | 10   | 0.0216          | 0.9984   |63 64 65### Framework versions66 67- PEFT 0.17.168- Transformers 4.57.169- Pytorch 2.10.0+cu12870- Datasets 4.0.071- Tokenizers 0.22.2