DCAgent/a1-stack_cpp

1---2library_name: transformers3license: other4base_model: Qwen/Qwen3-8B5tags:6- llama-factory7- full8- generated_from_trainer9model-index:10- name: sft_a1_stack_cpp__Qwen3-8B11  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# sft_a1_stack_cpp__Qwen3-8B18 19This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the /e/scratch/jureap59/raoof1/sft_data/hf_hub/datasets--DCAgent--exp_rpt_stack-cpp_10k_glm_4.7_traces_jupiter/snapshots/b229bdadf094370e7be8cf19e799cb01a5fc7b80_thinking_preprocessed 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: 4e-0539- train_batch_size: 140- eval_batch_size: 841- seed: 4242- distributed_type: multi-GPU43- num_devices: 1644- total_train_batch_size: 1645- total_eval_batch_size: 12846- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments47- lr_scheduler_type: cosine48- lr_scheduler_warmup_ratio: 0.149- num_epochs: 7.050 51### Training results52 53 54 55### Framework versions56 57- Transformers 4.57.658- Pytorch 2.9.1+cu13059- Datasets 4.7.060- Tokenizers 0.22.261