Nemo30/SPEC_CODE_AGENT

1---2library_name: peft3license: other4base_model: deepseek-ai/deepseek-coder-1.3b-base5tags:6- base_model:adapter:deepseek-ai/deepseek-coder-1.3b-base7- lora8- transformers9pipeline_tag: text-generation10model-index:11- name: SPEC_CODE_AGENT12  results: []13---14 15<!-- This model card has been generated automatically according to the information the Trainer had access to. You16should probably proofread and complete it, then remove this comment. -->17 18# SPEC_CODE_AGENT19 20This model is a fine-tuned version of [deepseek-ai/deepseek-coder-1.3b-base](https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-base) on the None dataset.21 22## Model description23 24More information needed25 26## Intended uses & limitations27 28More information needed29 30## Training and evaluation data31 32More information needed33 34## Training procedure35 36### Training hyperparameters37 38The following hyperparameters were used during training:39- learning_rate: 0.000240- train_batch_size: 241- eval_batch_size: 842- seed: 4243- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments44- lr_scheduler_type: linear45- num_epochs: 346- mixed_precision_training: Native AMP47 48### Training results49 50 51 52### Framework versions53 54- PEFT 0.18.155- Transformers 5.0.056- Pytorch 2.10.0+cu12857- Datasets 4.0.058- Tokenizers 0.22.2