DeepSeek-coder 微调训练记录

简介

微调过程不再细说, 参考link进行即可. 主要是数据集.

1.3b模型微调训练占用资源信息

top信息

评估

根据DeepSeek-coder的Evaluation试进行对微调后的模型进行评估. 其中的评估库主要是evol-teacher和human-eval.

新建一个eval_ins.sh文件, 填入以下内容

LANG="python"
OUPUT_DIR="output"
MODEL="deepseek-coder-1.3b-instruct"CUDA_VISIBLE_DEVICES=0,1 python eval_instruct.py \--model "deepseek-ai/$MODEL" \  # 修改路径为微调保存的模型路径--output_path "$OUPUT_DIR/${LANG}.$MODEL.jsonl" \--language $LANG \--temp_dir $OUPUT_DIR

随后启动bash eval_ins.sh

model /home/stlinpeiyang/lpy22/LLM/DeepSeek-Coder/finetune/output/checkpoint-14500
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
load tokenizer <class 'transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast'> from /home/stlinpeiyang/lpy22/LLM/DeepSeek-Coder/finetune/output/checkpoint-14500 over.
Read 164 examples for evaluation over.
Generating:   1%|▌                                            | 2/164 [07:10<10:00:15, 222.32s/it]Failed to extract code block with error `list index out of range`:
>>> Task: Python/2
>>> Output:
def truncate_number(number: float) -> float:""" Given a positive floating point number, it can be decomposed intoand integer part (largest integer smaller than given number) and decimals(leftover part always smaller than 1).Return the decimal part of the number.>>> truncate_number(3.5)0.5"""integer_part = int(number)decimal_part = number - integer_partreturn decimal_partGenerating:   6%|██▋                                          | 10/164 [28:04<7:23:26, 172.77s/it]

耗时很久.