4aa37f73985adab60395b755ad07ee2f

This model is a fine-tuned version of Helsinki-NLP/opus-mt-tc-bible-big-deu_eng_fra_por_spa-mul on the Helsinki-NLP/opus_books [it-sv] dataset. It achieves the following results on the evaluation set:

• Loss: 2.4203
• Data Size: 1.0
• Epoch Runtime: 6.2083
• Bleu: 2.2799

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: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• total_train_batch_size: 32
• total_eval_batch_size: 32
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: constant
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Data Size	Epoch Runtime	Bleu
No log	0	0	8.0780	0	0.9571	0.0250
No log	1	74	6.7426	0.0078	1.3746	0.0599
No log	2	148	5.5208	0.0156	1.3154	0.0784
0.2155	3	222	4.6607	0.0312	1.6722	0.1678
0.2155	4	296	4.0828	0.0625	1.9645	0.2064
0.2922	5	370	3.5531	0.125	2.5064	0.3552
0.2922	6	444	3.1093	0.25	3.3836	0.7301
0.6954	7	518	2.7332	0.5	4.7963	1.0645
1.7023	8.0	592	2.3873	1.0	7.4086	1.6240
2.0177	9.0	666	2.2894	1.0	6.1432	1.8825
1.8028	10.0	740	2.2560	1.0	5.9864	2.1244
1.4979	11.0	814	2.2650	1.0	6.2215	1.9804
1.338	12.0	888	2.3028	1.0	6.8173	2.1859
1.1015	13.0	962	2.3743	1.0	7.0574	2.2915
0.9857	14.0	1036	2.4203	1.0	6.2083	2.2799

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu128
• Datasets 4.2.0
• Tokenizers 0.22.1