dugoalberto/deepseek-coder-6.7b_LoRA_python

1---2license: other3library_name: peft4tags:5- trl6- sft7- generated_from_trainer8base_model: deepseek-ai/deepseek-coder-6.7b-base9model-index:10- name: deepseek-coder-6.7b_LoRA_python11  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# deepseek-coder-6.7b_LoRA_python18 19This model is a fine-tuned version of [deepseek-ai/deepseek-coder-6.7b-base](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-base) on the None 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: 5e-0539- train_batch_size: 1640- eval_batch_size: 841- seed: 4242- gradient_accumulation_steps: 843- total_train_batch_size: 12844- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0845- lr_scheduler_type: cosine46- lr_scheduler_warmup_ratio: 0.00547- training_steps: 2048- mixed_precision_training: Native AMP49 50### Training results51 52 53 54### Framework versions55 56- PEFT 0.11.2.dev057- Transformers 4.41.158- Pytorch 2.3.0+cu12159- Datasets 2.19.160- Tokenizers 0.19.1