en_to_dzo_nllb_mul_mt_nlp_m4

This model is a fine-tuned version of facebook/nllb-200-distilled-600M on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.7293
• Bleu: 19.2074
• Gen Len: 15.6777

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: 5e-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
2.2141	1.0	562	1.8532	9.1051	16.0711
1.7479	2.0	1124	1.7386	10.4502	15.3854
1.501	3.0	1686	1.6975	18.3404	16.2342
1.3186	4.0	2248	1.6957	17.8507	15.6396
1.1776	5.0	2810	1.6957	17.353	15.4945
1.0629	6.0	3372	1.7076	17.9624	15.6937
0.9827	7.0	3934	1.7202	17.6422	15.8619
0.9099	8.0	4496	1.7254	19.1543	15.5365
0.8253	9.0	5058	1.7293	19.2074	15.6777

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0