595 68 276

Tom Aarsen

tomaarsen

https://linkedin.com/in/tomaarsen

tomaarsen

AI & ML interests

NLP: text embeddings, named entity recognition, few-shot text classification

Articles

Training and Finetuning Embedding Models with Sentence Transformers v3

15 days ago

• 88

Blazing Fast SetFit Inference with 🤗 Optimum Intel on Xeon

Apr 3

• 6

Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval

Mar 22

• 42

Organizations

Posts 10

Post

1975

I just published Sentence Transformers v3.0.1: the first patch release since v3 from last week. It introduces gradient checkpointing, pushing model checkpoints to Hugging Face while training, model card improvements and fixes. Details:

1️⃣ Gradient checkpointing allows for much less memory usage at a cost of ~20% training speed. Seems to allow for higher batch sizes, which is quite important for loss functions with in-batch negatives.
2️⃣ You can specify args.push_to_hub=True and args.hub_model_id to upload your model checkpoints to Hugging Face while training. It also uploads your emissions (if codecarbon is installed) and your Tensorboard logs (if tensorboard is installed)
3️⃣ Model card improvements: improved automatic widget examples, better tags, and the default of "sentence_transformers_model_id" now gets replaced when possible.
4️⃣ Several evaluator fixes, see release notes for details.
5️⃣ Fixed a bug with MatryoshkaLoss throwing an error if the supplied Matryoshka dimensions are ascending instead of descending.
6️⃣ Full Safetensors support; even the uncommon modules can now save and load "model.safetensors" files: no more pickle risks.

Check out the full release notes here: https://github.com/UKPLab/sentence-transformers/releases/tag/v3.0.1

And let me know what kind of features you'd like to see next! I have some plans already (ONNX, Sparse models, ColBERT, PEFT), but I don't yet know how I should prioritize everything.

Post

1407

‼️Sentence Transformers v3.0 is out! You can now train and finetune embedding models with multi-GPU training, bf16 support, loss logging, callbacks & much more. I also release 50+ datasets to train on.

1️⃣ Training Refactor
Embedding models can now be trained using an extensive trainer with a lot of powerful features:
- MultiGPU Training (Data Parallelism (DP) and Distributed Data Parallelism (DDP))
- bf16 training support; loss logging
- Evaluation datasets + evaluation loss
- Improved callback support + an excellent Weights & Biases integration
- Gradient checkpointing, gradient accumulation
- Improved model card generation
- Resuming from a training checkpoint without performance loss
- Hyperparameter Optimization
and much more!
Read my detailed blogpost to learn about the components that make up this new training approach: https://huggingface.co/blog/train-sentence-transformers

2️⃣ Similarity Score
Not sure how to compare embeddings? Don't worry, you can now use model.similarity(embeddings1, embeddings2) and you'll get your similarity scores immediately. Model authors can specify their desired similarity score, so you don't have to worry about it anymore!

3️⃣ Additional Kwargs
Sentence Transformers relies on various Transformers instances (AutoModel, AutoTokenizer, AutoConfig), but it was hard to provide valuable keyword arguments to these (like 'torch_dtype=torch.bfloat16' to load a model a lower precision for 2x inference speedup). This is now easy!

4️⃣ Hyperparameter Optimization
Sentence Transformers now ships with HPO, allowing you to effectively choose your hyperparameters for your data and task.

5️⃣ Dataset Release
To help you out with finetuning models, I've released 50+ ready-to-go datasets that can be used with training or finetuning embedding models: sentence-transformers/embedding-model-datasets-6644d7a3673a511914aa7552

Full release notes: https://github.com/UKPLab/sentence-transformers/releases/tag/v3.0.0

View all posts