<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

gec-ua-uk

This model is a fine-tuned version of facebook/mbart-large-50 on the UA-GEC dataset.

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: 2e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2

Training results

The model was evaluated on the validation dataset provided in the UNLP 2023 Shared Task in Grammatical Error Correction for Ukrainian

=========== Span-Based Correction ============
TP	FP	FN	Prec	Rec	F0.5
570	158	698	0.783	0.4495	0.6818
==============================================


============ Span-Based Detection ============
TP	FP	FN	Prec	Rec	F0.5
604	124	662	0.8297	0.4771	0.7228
==============================================

Framework versions

• Transformers 4.32.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.4
• Tokenizers 0.13.3