results

This model is a fine-tuned version of Helsinki-NLP/opus-mt-en-mul on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.5011

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: 10
• eval_batch_size: 10
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	180	0.5012
No log	2.0	360	0.4840
0.5433	3.0	540	0.4754
0.5433	4.0	720	0.4748
0.5433	5.0	900	0.4761
0.4046	6.0	1080	0.4735
0.4046	7.0	1260	0.4774
0.4046	8.0	1440	0.4816
0.3441	9.0	1620	0.4797
0.3441	10.0	1800	0.4850
0.3441	11.0	1980	0.4855
0.3032	12.0	2160	0.4881
0.3032	13.0	2340	0.4907
0.2687	14.0	2520	0.4934
0.2687	15.0	2700	0.4950
0.2687	16.0	2880	0.4973
0.2463	17.0	3060	0.4983
0.2463	18.0	3240	0.5005
0.2463	19.0	3420	0.5011
0.2352	20.0	3600	0.5011

Framework versions

• Transformers 4.45.1
• Pytorch 2.4.0+cpu
• Datasets 3.0.1
• Tokenizers 0.20.0