tensorflow / tensorflow/recommenders

loss becomes nan

Open
#655 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
2k
Forks
300
PR merge metrics
No merged PRs in 30d

Description

58/108 [===============>..............] - ETA: 1:05:49 - root_mean_squared_error: nan - factorized_top_k/top_1_categorical_accuracy: 0.0045 - factorized_top_k/top_5_categorical_accuracy: 0.0089 - factorized_top_k/top_10_categorical_accuracy: 0.0130 - factorized_top_k/top_50_categorical_accuracy: 0.0295 - factorized_top_k/top_100_categorical_accuracy: 0.0380 - loss: nan - regularization_loss: nan - total_loss: nan

why do we have the loss becoming nan? Any tips appreciated.

Thanks,
Robert

Contributor guide

Open the contributing guide

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

No source files, tests, or entry points are identified; the report only includes training output showing NaN values. Start by obtaining the model, data, and training configuration that produced this run, then reproduce it and trace when the loss first becomes NaN. Done means identifying a reproducible cause and documenting or testing the corresponding fix.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, tensorflow
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.