huggingface/transfer-learning-conv-ai

RuntimeError: shape '[-1, 2, 34]' is invalid for input of size 61710

Open

#12 opened on Jun 4, 2019

View on GitHub
 (3 comments) (0 reactions) (0 assignees)Python (429 forks)batch import
good first issue

Repository metrics

Stars
 (1,700 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

I'm playing around with this wonderful code but I'm running into a curious issue when I try to train the model with my own data.

I replicated the personachat_self_original.json file structure and added my own data. I deleted dataset_cache_OpenAIGPTTokenizer file but when I try to train, I get this error:

INFO:train.py:Pad inputs and convert to Tensor
Traceback (most recent call last):
  File "train.py", line 252, in <module>
    train()
  File "train.py", line 164, in train
    train_loader, val_loader, train_sampler, valid_sampler = get_data_loaders(args, tokenizer)
  File "train.py", line 97, in get_data_loaders
    tensor = tensor.view((-1, datasets[dataset_name]["n_candidates"]) + tensor.shape[1:])
RuntimeError: shape '[-1, 2, 34]' is invalid for input of size 61710

I have triple checked that my dataset follows the same structure but I can't figure out why the training script doesn't like it.

Any ideas why this is happening?

Contributor guide

Research direction
The error occurs in train.py at line 97 during data loading. The tensor shape [ 1, 2, 34] indicates a mismatch between the expected number of candidates (2) and the actual data size. The user should verify that their dataset file has the correct number of candidates per example. Checking the dataset cache generation and the n candidates argument may reveal the issue. The code in get data loaders expects data to be shaped for a fixed number of candidates.
Tech stack
pythonpytorch
Domain
machine learningai
Issue type
Bug
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Stale
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Needs investigation
Prerequisites
PyTorch basicsData formattingTensor shapes
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
25