47f4cde71cbbf6fedf6cc532413e0350

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 [en-es] dataset. It achieves the following results on the evaluation set:

• Loss: 2.1413
• Data Size: 1.0
• Epoch Runtime: 145.4017
• Bleu: 6.2992

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	6.7534	0	11.4883	0.3033
No log	1	2336	4.3562	0.0078	13.7510	2.1663
0.0659	2	4672	3.7353	0.0156	13.5693	2.3889
0.0843	3	7008	3.3584	0.0312	16.6784	2.8535
3.155	4	9344	3.0466	0.0625	20.0139	3.4931
2.9083	5	11680	2.7824	0.125	30.0332	4.1836
2.5799	6	14016	2.5393	0.25	44.5311	4.7526
2.373	7	16352	2.3265	0.5	77.3855	5.2621
2.161	8.0	18688	2.1648	1.0	147.3496	5.7457
1.9095	9.0	21024	2.1040	1.0	147.0347	6.0150
1.7575	10.0	23360	2.0740	1.0	146.4269	6.1318
1.6091	11.0	25696	2.0798	1.0	145.6022	6.2485
1.4849	12.0	28032	2.0885	1.0	144.7744	6.2711
1.3648	13.0	30368	2.1071	1.0	146.5439	6.2781
1.2774	14.0	32704	2.1413	1.0	145.4017	6.2992

Framework versions

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