Comments (2)
Hi @ejld, yes BERT has a large variance on many fine-tuning tasks (see also the discussion in #64).
You should try a bunch of different seeds (like 10 seeds for example) and compare the mean and standard deviation of the results.
from transformers.
Hi!
Could it be different seeds?
See e.g. #53 (comment)
from transformers.
Related Issues (20)
- LLaVA image_token_index is not 64000 but 64002 HOT 1
- Question about recent PR updates in BLIP-2 code HOT 4
- Generate method does not return hidden states when "output_hidden_states=True" is passed HOT 2
- [BLIP-2] Batch generation error in inference HOT 3
- GaLore implementation assigns same optimizer to galore_params and non_galore_params
- HuggingFace `from_pretrained()` called multiple times when launching with `torchrun` HOT 2
- Question about downloading the model from the Hub using `from_pretrained()` call HOT 1
- Import error of the newest version of transformers HOT 6
- inputs device error with fuyu model HOT 2
- Issue loading some peft adapter model when revision is specified HOT 2
- cosine_with_restarts schedule not restart HOT 7
- vocab_size for modeling_llama.py HOT 5
- Exporting Mixtral using ONNX Exporter Fails Due to Python List Conversion HOT 2
- `assisted_decoding` called directly inside `generate` triggering warning to use when it shouldn't HOT 1
- Pipeline can't find torch or tensorflow, errors out in notebook. HOT 3
- Incorrect model_type for ViTHybridModel HOT 2
- [HELP] Secure Delivery of Trained LLM for Client Demo HOT 1
- Int4 transformers training HOT 1
- Inconsistent tokenization between fast and slow tokenizers for sentencepiece user-defined tokens. HOT 1
- Speculative Decoding Snippet Not Working
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 transformers.