---
library_name: transformers
language:
- multilingual
- bn
- cs
- de
- en
- et
- fi
- fr
- gu
- ha
- hi
- is
- ja
- kk
- km
- lt
- lv
- pl
- ps
- ru
- ta
- tr
- uk
- xh
- zh
- zu
license: apache-2.0
base_model: answerdotai/ModernBERT-base
tags:
- quality-estimation
- regression
- generated_from_trainer
datasets:
- ymoslem/wmt-da-human-evaluation
model-index:
- name: Quality Estimation for Machine Translation
  results:
  - task:
      type: regression
    dataset:
      name: ymoslem/wmt-da-human-evaluation-long-context
      type: QE
    metrics:
    - name: Pearson
      type: Pearson Correlation
      value: 0.2055
    - name: MAE
      type: Mean Absolute Error
      value: 0.2004
    - name: RMSE
      type: Root Mean Squared Error
      value: 0.2767
    - name: R-R2
      type: R-Squared
      value: -1.6745
  - task:
      type: regression
    dataset:
      name: ymoslem/wmt-da-human-evaluation
      type: QE
    metrics:
    - name: Pearson
      type: Pearson Correlation
      value: null
    - name: MAE
      type: Mean Absolute Error
      value: null
    - name: RMSE
      type: Root Mean Squared Error
      value: null
    - name: R-R2
      type: R-Squared
      value: null
metrics:
- pearsonr
- mae
- r_squared
new_version: ymoslem/ModernBERT-base-qe-v1
---


# Quality Estimation for Machine Translation

This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on the [ymoslem/wmt-da-human-evaluation](https://huggingface.co/datasets/ymoslem/wmt-da-human-evaluation-long-context) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0561

## Model description

This model is for reference-free, sentence level quality estimation (QE) of machine translation (MT) systems.
The long-context / document-level model can be found at: [ModernBERT-base-long-context-qe-v1](https://huggingface.co/ymoslem/ModernBERT-base-long-context-qe-v1),
which is trained on a long-context / document-level QE dataset [ymoslem/wmt-da-human-evaluation-long-context](https://huggingface.co/datasets/ymoslem/wmt-da-human-evaluation-long-context)

## Training and evaluation data

This model is trained on the sentence-level quality estimation dataset: [ymoslem/wmt-da-human-evaluation](https://huggingface.co/datasets/ymoslem/wmt-da-human-evaluation)

## Training procedure

### Training hyperparameters

This version of the model uses tokenizer.model_max_length=512.
The model with full length of 8192 can be found here [ymoslem/ModernBERT-base-qe-v1](https://huggingface.co/ymoslem/ModernBERT-base-qe-v1),
which is still trained on a sentence-level QE dataset [ymoslem/wmt-da-human-evaluation](https://huggingface.co/datasets/ymoslem/wmt-da-human-evaluation)

The long-context / document-level model can be found at: [ModernBERT-base-long-context-qe-v1](https://huggingface.co/ymoslem/ModernBERT-base-long-context-qe-v1),
which is trained on a long-context / document-level QE dataset [ymoslem/wmt-da-human-evaluation-long-context](https://huggingface.co/datasets/ymoslem/wmt-da-human-evaluation-long-context)

The following hyperparameters were used during training:
- learning_rate: 0.0003
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- training_steps: 10000

### Training results

| Training Loss | Epoch  | Step  | Validation Loss |
|:-------------:|:------:|:-----:|:---------------:|
| 0.0656        | 0.1004 | 1000  | 0.0636          |
| 0.0643        | 0.2007 | 2000  | 0.0623          |
| 0.0592        | 0.3011 | 3000  | 0.0598          |
| 0.0596        | 0.4015 | 4000  | 0.0586          |
| 0.0575        | 0.5019 | 5000  | 0.0577          |
| 0.0574        | 0.6022 | 6000  | 0.0570          |
| 0.0584        | 0.7026 | 7000  | 0.0566          |
| 0.0574        | 0.8030 | 8000  | 0.0563          |
| 0.0565        | 0.9033 | 9000  | 0.0561          |
| 0.0557        | 1.0037 | 10000 | 0.0561          |


### Framework versions

- Transformers 4.48.0
- Pytorch 2.4.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0