kyegomez / kyegomez/LongNet

train error

Open
#22 8 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
727
Forks
59
PR merge metrics
No merged PRs in 30d

Description

I ran train.py and got error below

Traceback (most recent call last): File "/public/home/wangycgroup/public/02_Data/Internal/phage/train.py", line 86, in <module> loss = model(next(train_loader)) File "/public/home/wangycgroup/wangjn/software/miniconda3/envs/venv/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "/public/home/wangycgroup/wangjn/software/miniconda3/envs/venv/lib/python3.9/site-packages/long_net/model.py", line 326, in forward logits = self.net(x_inp, **kwargs) File "/public/home/wangycgroup/wangjn/software/miniconda3/envs/venv/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "/public/home/wangycgroup/wangjn/software/miniconda3/envs/venv/lib/python3.9/site-packages/long_net/model.py", line 272, in forward x = self.transformer(x) File "/public/home/wangycgroup/wangjn/software/miniconda3/envs/venv/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "/public/home/wangycgroup/wangjn/software/miniconda3/envs/venv/lib/python3.9/site-packages/long_net/model.py", line 245, in forward x = block(x) + x File "/public/home/wangycgroup/wangjn/software/miniconda3/envs/venv/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "/public/home/wangycgroup/wangjn/software/miniconda3/envs/venv/lib/python3.9/site-packages/long_net/model.py", line 206, in forward attn = self.attn(q, k, v) File "/public/home/wangycgroup/wangjn/software/miniconda3/envs/venv/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) TypeError: forward() takes 2 positional arguments but 4 were given

the output is

`No CUDA runtime is found, using CUDA_HOME='/usr/local/cuda'
Using StableAdamWUnfused-v1

training: 0%| | 0/100000 [00:00<?, ?it/s]
training: 0%| | 0/100000 [00:00<?, ?it/s]
`

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 reproducing the failure from train.py at line 86, then trace the calls through long_net/model.py, especially the forward methods around lines 206 and 245. Compare the arguments passed at the attention call with the relevant forward signature and rerun training to confirm the error is resolved.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
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.