ModernBERT-base-reference_AllLang2-Cefr2

This model is a fine-tuned version of answerdotai/ModernBERT-base on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.1614
F1: 0.7991

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 3.6e-05
train_batch_size: 3
eval_batch_size: 3
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 48
optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	F1
13.434	1.0	1187	0.9551	0.6060
12.7427	2.0	2374	0.8242	0.6122
10.5392	3.0	3561	0.6622	0.6993
8.4093	4.0	4748	0.7189	0.7923
6.2165	5.0	5935	0.7702	0.8011
3.4972	6.0	7122	0.8621	0.7922
2.1566	7.0	8309	0.9976	0.7763
1.5776	8.0	9496	0.9838	0.7991
1.1022	9.0	10683	1.1791	0.7563
0.9423	10.0	11870	1.1614	0.7991

Framework versions

Transformers 4.53.1
Pytorch 2.6.0+cu124
Datasets 3.6.0
Tokenizers 0.21.2

Citation

@inproceedings{alva-manchego-etal-2025-findings,
    title = "Findings of the {TSAR} 2025 Shared Task on Readability-Controlled Text Simplification",
    author = "Alva-Manchego, Fernando  and Stodden, Regina  and Imperial, Joseph Marvin  and Barayan, Abdullah  and North, Kai  and Tayyar Madabushi, Harish",
    editor = "Shardlow, Matthew  and Alva-Manchego, Fernando  and North, Kai  and Stodden, Regina  and Saggion, Horacio  and Khallaf, Nouran  and Hayakawa, Akio",
    booktitle = "Proceedings of the Fourth Workshop on Text Simplification, Accessibility and Readability (TSAR 2025)",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.tsar-1.8/",
    doi = "10.18653/v1/2025.tsar-1.8",
    pages = "116--130",
    ISBN = "979-8-89176-176-6"
}