Comments (5)
If following the exact same evaluation setting with bigcode-evaluation-harness, I can obtain the following pass@1 results for the 33B model as below:
Evaluating generations...
{
"humaneval": {
"pass@1": 0.5365853658536586
},
"config": {
"prefix": "",
"do_sample": false,
"temperature": 0.2,
"top_k": 0,
"top_p": 0.95,
"n_samples": 1,
"eos": "<|endoftext|>",
"seed": 0,
"model": "deepseek-ai/deepseek-coder-33b-base",
"modeltype": "causal",
"peft_model": null,
"revision": null,
"use_auth_token": false,
"trust_remote_code": true,
"tasks": "humaneval",
"instruction_tokens": null,
"batch_size": 1,
"max_length_generation": 650,
"precision": "fp32",
"load_in_8bit": false,
"load_in_4bit": false,
"limit": null,
"limit_start": 0,
"postprocess": true,
"allow_code_execution": true,
"generation_only": false,
"load_generations_path": null,
"load_data_path": null,
"metric_output_path": "evaluation_results.json",
"save_generations": false,
"save_generations_path": "generations.json",
"save_references": false,
"prompt": "prompt",
"max_memory_per_gpu": "auto",
"check_references": false
}
}
Considering that the slightly different operations during post-processing, I think the claimed pass@1 should be reproducible.
from deepseek-coder.
@SivilTaram Thanks for the reference! I think these results are all possible by a better/optimal generation/inference parameters (e.g., we use bf16
and your config is calling fp32
; our max generation length is 512 while yours is larger; etc.) since I believe our post-processing is robust as only two output solutions from deepseek-coder are not compilable (and we manually checked it is due to infinite enumeration of outputs) while the rest all look good.
Anyways,I also get a copy of the author-provided solutions (thanks to the authors!) which can produce the claimed results:
I will close the issue as I don't have further questions. Thanks for the attention and the great work! :)
from deepseek-coder.
An interesting finding tho: https://evalplus.github.io/leaderboard.html
From our independent evaluation, codellama-34b is a bit stronger than deepseekcoder-33b on the original HumanEval but instead on HumanEval+ deepseekcoder-33b is found to be better, indicating deepseekcoder is producing more robust code (i.e., HumanEval+ adds more test-cases for HumanEval whose tests might be insufficient for showing the correctness).
from deepseek-coder.
BTW, could you indicate the instruction that is used for the deepseek-ai/deepseek-coder-33b-instruct
on HumanEval? Thanks!
from deepseek-coder.
Update: I am able to get the following result using the prompt here and some post cleaning to make all produced compilable:
from deepseek-coder.
Related Issues (20)
- 微调完的模型,如何跟基础模型合并? HOT 1
- 本地部署怎么实现vscode自动代码补全? HOT 1
- How to use fine-tuned model? HOT 3
- 使用vllm加速inference后输出容易不符合格式要求
- 使用vllm加载33b-base或33b-instruct后,使用DS-1000、Program-Aided Math Reasoning (PAL)评估集进行评估,得分很低,与论文上的数据不符
- 并发数目
- 用vllm加速推理框架 推理速度还是很慢 HOT 1
- Are EOS tokens masked during pre-training? If so, how does FIM mode know how to connect to the `text_after`?
- 训练数据切分问题 HOT 1
- 疑惑:为什么 base 模型的 tokenizer 词表中也有类似 <|Assistant|> 这样多用于 chat 模型的 special tokens?
- Deepseekcoder 6 spitting out corrupt output for code generation question
- 为什么在进行一次训练加载后,会出现找不到显卡no slot的报错呢?
- RuntimeError: CUDA error: no kernel image is available for execution on the device
- Where is DeepSeek-Coder-V2?
- Long Code Arena
- deepseek-coder-6.7b-base vuejs代码补全上存在一些问题
- 加载模型时出错
- What is the correct padding side for train/eval of base model for FIM?
- dependency parsing code and deduplication script
- Problem in Math Evaluation HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from deepseek-coder.