Comments (2)
-
Well there are many ways to do the contrastive loss. What we follow is more or less this. Pretty much what the CLIP authors used and almost all these recent embedding transformer authors such as E5.
-
Well we need to somehow combine the doc-scores with the next word prediction right ? why would you think adding the log prob won't do any difference ?
I took the equation from here.
from dalm.
Hey @shamanez
Thank you for the replies.
re:1 of course, there are many ways to contrastive losses. I'll read through the linked paper
re:2 I think the theoretical aspect of adding the logprobs make sense. My question was based around the runtime values I see, seem to be adding the same increment to all values of answer_log_prob
, to put my question explicitly
# shape: [102, 50257]
answer_log_prob = logprobs_logits[query_token_length - 1 :, :]
# addition of shapes: [102,50257] + [1,1]
marginalized_prob_sum = answer_log_prob + doc_logprobs
I think my seemingly faulty reasoning reasoned that adding the same value to all values of the distribution seems off. I'll have to work my way out of this, as I still don't understand what this means , in my head I'd expect the following
# addition of shapes: [102,50257] + [1,50257]
marginalized_prob_sum = answer_log_prob + doc_logprobs
It is very likely it's just my inexperience speaking. I'll work on this
I guess with those two question being answered. I think that's the end of my questions with the loss part and rest of the code flow for now
from dalm.
Related Issues (20)
- training fails at the end when with-tracking is false HOT 1
- E2E training checkpoint saving doesn't work HOT 1
- Minimum system requirements to train HOT 4
- Desiring Retriever Only Inference HOT 2
- Installation: Why 'indomain' and not 'dalm' ? HOT 5
- TypeError: Argument() missing 1 required positional argument: 'default'
- dalm qa-gen toy_data_train.csv doesn't work out of the box. HOT 4
- Eval e2e Rag raising device mismatch error HOT 2
- Reading comprehension synthetic data regex improvements HOT 1
- Update README to document reading comprehension
- CUDA OOM doing reading comprehension on A10 24GB VRAM GPU
- How to run model + finetuned adapter in LlamaIndex or Langchain? HOT 1
- Large values of casual loss HOT 3
- paper released?
- Rag-end2end didn't achieve any improvement in recall score compared to training only with Retriever HOT 4
- DALM installation fails in my python environment. HOT 1
- Installation problem on main branch HOT 1
- cannot import name '_sentencepiece' from partially initialized module 'sentencepiece'
- how to use title question and passage all together while training retriever only HOT 1
- Incorrect pooling BGE model HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from dalm.