train_utils media token fix #283
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
anas-awadalla
requested changes
Dec 2, 2023
open_flamingo/train/train_utils.py
Outdated
| @@ -77,8 +79,11 @@ def train_one_epoch( | |||
| batch_metadata_to_log[ | |||
| f"{datasets[dataset_ix].name}_num_tokens" | |||
| ] = attention_mask.sum().item() | |||
| model = unwrap_model(model) | |||
| model.media_token_id = 400 | |||
There was a problem hiding this comment.
Hmm I don't think these should be here? Lines 82-84 are unnecessary I think
open_flamingo/train/train_utils.py
Outdated
| batch_metadata_to_log[f"{datasets[dataset_ix].name}_num_images"] = ( | ||
| (input_ids == model.media_token_id).sum().item() | ||
| (input_ids == model.module.media_token_id).sum().item() |
There was a problem hiding this comment.
You should use the unwrap method here on the model rather than directly calling .module
open_flamingo/train/train_utils.py
Outdated
| @@ -10,6 +10,8 @@ | |||
| from data_utils import DataInfo | |||
| import random | |||
| import numpy as np | |||
| from torch.nn.parallel import DistributedDataParallel as DDP | |||
There was a problem hiding this comment.
Once lines 82-84 are removed this import will be unused and should also be removed
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
added lines to train_util for helper function to unwrap model and also added media token id