Comments (4)
Thank you for your open source, I am replicating your fine-tuning process according to the code on github. Do the results of train loss=0.16 and eval_loss=0.21 I trained on the 75k dataset match yours? I will continue training on the 110k dataset.
I trained for 4 epochs and indeed started overfitting after the second epoch.
from magicoder.
Magicoder-S-CL.json
Magicoder-CL.json
Magicoder-S-DS.json
Magicoder-DS.json
Hi, here are the trainer states. Hope they can help!
from magicoder.
Magicoder-S-CL.json Magicoder-CL.json Magicoder-S-DS.json Magicoder-DS.json
Hi, here are the trainer states. Hope they can help!
Thank you very much, my training process is basically the same as your loss metric and the test results on humaneval dataset are basically consistent
But I have a question. Why is the model fully fine-tuned by instruction, but why is the capacity infilinig increased?
I look forward to hearing from you.
from magicoder.
Good to hear you can reproduce it. Yeah we did observe that the infilling capability was at least not decreasing. We believe this is because the model learned some general alignment during the instruction tuning, and infilling is a kind of alignment based on the surrounding context. Further study of this phenomenon would be interesting.
from magicoder.
Related Issues (20)
- The model outputs nothing but "\n" HELP! 😭 HOT 4
- Training data format for Magicoder-OSS-Instruct-75K HOT 4
- So many impressive experiments ! Are there any experiments with neftune ? HOT 1
- The correctness of solution HOT 1
- used Dilated attenton instead of Vanilla Attention in Llama model and fine-tuen the model ,
- How do you set the 'stop_words' parameter
- Data collection and generation HOT 1
- Got same problem that model only return lots of '\n' HOT 5
- Achieved close performance of MagicoderS by finetuning only with `evol-codealpaca-v1`. HOT 8
- A scaling law of instruction-code-data would be very interesting... HOT 3
- catastrophic forgetting problem HOT 1
- The templates used in reproducing the eval results: why adding the instruction again after "### Response: "? HOT 1
- 8台A40机器上复现magicoder-S-DS-6.7B的结果
- Is it normal to take more than one hour to get the humanevalplus results?
- HuggingFace Playground has failed
- Quantised Finetuning on 22GB*4 GPUs
- A question of the generated data from the starcoderdata HOT 2
- Overlap between Magicoder-Evol-Instruct-110K and HumanEval HOT 2
- Code for the evaluations on APPS.
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 magicoder.