Comments (4)
Yes, typically when you use comet-train
you are just loading XLM-R weights (or any other encoder) and finetuning on top.
The only exception is if you use the model flag load_weights_from_checkpoint
. This flag can be used to load an existing COMET checkpoint.
from comet.
For our models from WMT21 shared task we actually did that.. we train a checkpoint on DA's and then we fine-tune them in MQM z-scores using that same flag: Are References Really Needed?
Unbabel-IST 2021 Submission for the Metrics Shared Task
from comet.
Btw the advantage of load_weights_from_checkpoint
over resume_from_checkpoint
is that the architecture doesn't need to be exactly the same! we only load the matching (key, values) between the new model and the checkpoint. While in resume_from_checkpoint
the model architecture needs to be exactly the same. Does this make sense?
Let's imagine you want to reuse the weights learned with a Ranking Model... with load_weights_from_checkpoint
you will be able to do that and then fine-tune a Regression Model.
from comet.
Thank you so much for your detailed explanations!
from comet.
Related Issues (20)
- Avoid downloading XLM-R checkpoint from huggingface HOT 1
- Use BetterTransformer for fast inference HOT 1
- [QUESTION] default model is not update? HOT 2
- Version 2.0 HOT 2
- Specifying GPU ID for inference HOT 4
- Models not accessible HOT 2
- Inefficient _layer_norm implementation in layerwise_attention.py HOT 1
- [QUESTION]__init__.py generates a wrong path for hparams.yaml in Windows HOT 6
- tensor_lru_cache is limited to tensors with at least 2-Dimensions HOT 5
- `Unbabel/wmt22-comet-da` model not working as part of Huggingface evaluate HOT 2
- Can't reproduce Cometinho model scores HOT 3
- Do system scores above 100 really "differ"? HOT 4
- wmt20-comet-qe-da do not work under huggingface guides (possible version conflicts) HOT 3
- Support pandas 2
- [QUESTION] How to finetune `wmt22-comet-da` and have results scaled to 0-1 range HOT 1
- UnifiedMetric test failing: test_multitask_with_references HOT 1
- Segmentation error when tring to reproduce wmt22 results HOT 1
- How to reproduce Unbabel/wmt22-comet-da model HOT 2
- Evaluate lines with newline characters
- [QUESTION] Does COMET support Scoring multiple refs like scarebleu? HOT 2
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 comet.