en_to_dzo_helsinki_nlp_m2

This model is a fine-tuned version of Helsinki-NLP/opus-mt-tc-bible-big-mul-mul on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3012
• Bleu: 2.8367
• Gen Len: 119.2242

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 9
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
0.8419	1.0	562	0.5239	0.0	121.8458
0.5144	2.0	1124	0.4316	1.0161	118.9429
0.4296	3.0	1686	0.3774	0.8574	118.6066
0.3759	4.0	2248	0.3462	1.4119	118.6577
0.3351	5.0	2810	0.3250	2.0178	119.8008
0.3065	6.0	3372	0.3123	2.5655	118.7538
0.2839	7.0	3934	0.3037	3.0749	118.5455
0.2665	8.0	4496	0.3023	2.9584	119.3423
0.2441	9.0	5058	0.3012	2.8367	119.2242

Framework versions

• Transformers 4.46.3
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.20.3