deepspeedai / deepspeedai/DeepSpeedExamples

BingBertSQuAD Fine-tuning result mismatch tutorial document

Open
#190 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
6.8k
Forks
1.1k
Avg merge
2d 16h
Merged PRs (30d)
1

Description

I rerun the shell file run_squad_baseline.sh under BingBertSquad without any modification on 8 gpus V100, the pretrain mode is https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-whole-word-masking-pytorch_model.bin, but I didn't get right results.

The document says for default config, the result should be EM: 87.27, F1: 93.33, but I got {"exact_match": 8.136234626300851, "f1": 16.67697307405455}.
and for PER_GPU_BATCH_SIZE=3, traing speed is 8.31it/s, means samples/second is about 24.93, which is aroud 36.34 in document.

Did I miss something?

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reviewing run_squad_baseline.sh and the linked BERT fine-tuning tutorial, then reproduce the reported run on 8 V100 GPUs with the stated pretrained model. Compare the default metrics and the PER_GPU_BATCH_SIZE=3 throughput with the documented values; done means identifying and documenting the cause of the mismatch or confirming the tutorial needs correction.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, shell
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.