---
license: mit
datasets:
- unicamp-dl/mmarco
language:
- de
tags:
- colbert
- ColBERT
---



## Training

#### Details

The model is initialized from the [dbmdz/bert-base-german-uncased](https://huggingface.co/dbmdz/bert-base-german-uncased) checkpoint and fine-tuned on 10M triples via pairwise softmax cross-entropy loss over the computed scores of the positive and negative passages associated to a query. It was trained on a single Tesla A100 GPU with 40GBs of memory during 200k steps with 10% of warmup steps using a batch size of 96 and the AdamW optimizer with a constant learning rate of 3e-06. Total training time was around 12 hours.

#### Data

The model is fine-tuned on the German version of the [mMARCO](https://huggingface.co/datasets/unicamp-dl/mmarco) dataset, a multi-lingual machine-translated version of the MS MARCO dataset.
The triples are sampled from the ~39.8M triples of [triples.train.small.tsv](https://microsoft.github.io/msmarco/Datasets.html#passage-ranking-dataset)

## Evaluation

The model is evaluated on the smaller development set of mMARCO-de, which consists of 6,980 queries for a corpus of 8.8M candidate passages. We report the mean reciprocal rank (MRR) and recall at various cut-offs (R@k).

| model                                                                                                                   |  Vocab. | #Param. |  Size |   MRR@10 |   R@50 |  R@1000 |
|:------------------------------------------------------------------------------------------------------------------------|:--------|--------:|------:|---------:|-------:|--------:|
| **ColBERTv1.0-german-mmarcoDE**                                                                                         |  german |    110M | 440MB |    26.62 |  63.66 |   68.32 |