Closed pha-nguyen closed 3 months ago
Hi, thank you! They will be released in several hours.
Now released. Please check scripts/coin/live1+.sh and data/coin/. Feel free to ask any questions!
Now I close this issue. Please reopen it once you have any problems.
@chenjoya This line should be:
return self.get_input_embeddings()(input_ids.clamp(max=self.vocab_size-1))
Is this an expected behavior?
Hi, please dont do that. 128256 is just a placeholder, it will be replaced with image embedding during forwarding.
Could you give me the full scripts that you run? Thank you so much.
@chenjoya I followed your training script on COIN dataset (changed to evaluate.py as well). Then I got the error below:
After debugging inside, I see the input_ids
is out of range of config.vocab_size
.
Thank you. I will check that. After 3pm today.
Hello, I cannot reimplement your problem by training COIN.
input_ids is out of range of config.vocab_size.
This is okay, since we just use 128256 as a placeholder, it will not call get_inputs_embeddings. Its weird the program will call this line:
This should only be called when we do not have visual frames (only language tokens). In this situation, the input_ids should not have 128256, since there is no frames need to use placeholder.
Could you provide me the full scripts? So I can debug with that. Thank you!
I am so sorry that the COIN evaluation indeed exists some bugs. So sorry for that. Now they have been fixed. The main changes are
Hope the above helps!
Hi, thank you for the great work! Could you please disclose the scripts for COIN will be released anytime soon?