Chuanwise

哈哈哈哈哈哈哈哈

我也遇到了这个问题。

> The issue still open?! @nmvijay I just import the jena-sparql-api-core-2.10.0-22.jar into my project directly, not update the pom, then set the order lower than maven lib, get both chicken...

> This repository should probably be archived as it hasn't been maintained for a long time but I don't currently have the rights to do that. @Chuanwise: Can you tell...

Complete Log: ```log #0 building with "default" instance using docker driver #1 [internal] load .dockerignore #1 transferring context: 2B done #1 DONE 0.0s #2 [internal] load build definition from Dockerfile...

This change makes ImageOnMap works on 1.19.2.

ping?

I changed codes near `engine.py:25` to: ```py vqa_loss, vaq_loss, qav_loss = model(data) print(f"vqa_loss: {vqa_loss}, vaq_loss: {vaq_loss}, qav_loss: {qav_loss}") ``` And here is the log: ``` [19:52:42.854386] vqa_loss: 1.484375, vaq_loss: 1.8125,...

I saw your comment last night and changed `blr` to `1e-4`, but the problem still exist. Now I'm trying to use `--accum_iter 32`. 🤔

The problem still exist: ``` Not using distributed mode [09:30:04.319382] job dir: /home/23031212503/projects/Flipped-VQA [09:30:04.319483] Namespace(batch_size=1, epochs=10, accum_iter=32, llama_model_path='./pretrained/llama/', model='7B', adapter_layer=32, adapter_len=10, max_seq_len=650, max_feats=10, weight_decay=0.02, lr=None, blr=0.0001, min_lr=0.0, warmup_epochs=2, dataset='tvqa', output_dir='./checkpoint/tvqa',...