8661

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

• Loss: 0.4556
• Model Preparation Time: 0.0033
• Bleu Msl: 0.0
• Bleu 1 Msl: 0.7186
• Bleu 2 Msl: 0.0156
• Bleu 3 Msl: 0.0046
• Bleu 4 Msl: 0.0023
• Ter Msl: 100
• Bleu Asl: 0
• Bleu 1 Asl: 0
• Bleu 2 Asl: 0
• Bleu 3 Asl: 0
• Bleu 4 Asl: 0
• Ter Asl: 100

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: 0.0001
• train_batch_size: 32
• eval_batch_size: 64
• seed: 42
• optimizer: Use OptimizerNames.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: 30
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time	Bleu Msl	Bleu 1 Msl	Bleu 2 Msl	Bleu 3 Msl	Bleu 4 Msl	Ter Msl	Bleu Asl	Bleu 1 Asl	Bleu 2 Asl	Bleu 3 Asl	Bleu 4 Asl	Ter Asl
No log	1.0	217	0.2103	0.0033	100.0000	0.5468	0.0100	0.0028	0.0014	100	100.0000	0.5379	0.0067	0.0017	0.0008	100
No log	2.0	434	0.2122	0.0033	0.0	0.5927	0.0104	0.0029	0.0014	100	100.0000	0.5025	0.0065	0.0016	0.0007	100
0.0494	3.0	651	0.2011	0.0033	0.0	0.5780	0.0103	0.0029	0.0014	100	100.0000	0.4857	0.0064	0.0016	0.0007	100
0.0494	4.0	868	0.1981	0.0033	0.0	0.4092	0.0087	0.0026	0.0013	100	100.0000	0.4318	0.0060	0.0016	0.0007	100
0.0352	5.0	1085	0.2058	0.0033	0.0	0.5193	0.0098	0.0028	0.0013	100	100.0000	0.4983	0.0065	0.0016	0.0007	100
0.0352	6.0	1302	0.1956	0.0033	100.0000	0.4734	0.0093	0.0027	0.0013	100	100.0000	0.4966	0.0065	0.0016	0.0007	100
0.0256	7.0	1519	0.2039	0.0033	100.0000	0.6073	0.0106	0.0029	0.0014	100	100.0000	0.4916	0.0064	0.0016	0.0007	100
0.0256	8.0	1736	0.2070	0.0033	100.0000	0.5486	0.0100	0.0028	0.0014	100	100.0000	0.4983	0.0065	0.0016	0.0007	100
0.0256	9.0	1953	0.2127	0.0033	100.0000	0.5596	0.0101	0.0028	0.0014	100	100.0000	0.4293	0.0060	0.0015	0.0007	100
0.0166	10.0	2170	0.2174	0.0033	0.0	0.4899	0.0095	0.0027	0.0013	100	100.0000	0.4428	0.0061	0.0016	0.0007	100
0.0166	11.0	2387	0.2100	0.0033	100.0000	0.5706	0.0102	0.0028	0.0014	100	100.0000	0.4773	0.0063	0.0016	0.0007	100
0.0136	12.0	2604	0.2033	0.0033	100.0000	0.5303	0.0099	0.0028	0.0013	100	100.0000	0.4689	0.0063	0.0016	0.0007	100
0.0136	13.0	2821	0.2080	0.0033	100.0000	0.5578	0.0101	0.0028	0.0014	100	100.0000	0.5034	0.0065	0.0016	0.0007	100
0.0112	14.0	3038	0.2025	0.0033	100.0000	0.6202	0.0107	0.0029	0.0014	100	100.0000	0.5	0.0065	0.0016	0.0007	100
0.0112	15.0	3255	0.2101	0.0033	100.0000	0.6202	0.0107	0.0029	0.0014	100	100.0000	0.4579	0.0062	0.0016	0.0007	100
0.0112	16.0	3472	0.2052	0.0033	100.0000	0.5156	0.0097	0.0028	0.0013	100	100.0000	0.4588	0.0062	0.0016	0.0007	100
0.0079	17.0	3689	0.2090	0.0033	100.0000	0.5670	0.0102	0.0028	0.0014	100	100.0000	0.4571	0.0062	0.0016	0.0007	100
0.0079	18.0	3906	0.2092	0.0033	100.0000	0.6	0.0105	0.0029	0.0014	100	100.0000	0.4924	0.0064	0.0016	0.0007	100
0.006	19.0	4123	0.2111	0.0033	100.0000	0.5706	0.0102	0.0028	0.0014	100	100.0000	0.4848	0.0064	0.0016	0.0007	100
0.006	20.0	4340	0.2144	0.0033	100.0000	0.5229	0.0098	0.0028	0.0013	100	100.0000	0.4705	0.0063	0.0016	0.0007	100
0.0052	21.0	4557	0.2109	0.0033	100.0000	0.5596	0.0101	0.0028	0.0014	100	100.0000	0.4790	0.0064	0.0016	0.0007	100
0.0052	22.0	4774	0.2130	0.0033	100.0000	0.5211	0.0098	0.0028	0.0013	100	100.0000	0.4790	0.0064	0.0016	0.0007	100
0.0052	23.0	4991	0.2109	0.0033	100.0000	0.5688	0.0102	0.0028	0.0014	100	100.0000	0.5093	0.0066	0.0016	0.0007	100
0.0046	24.0	5208	0.2107	0.0033	100.0000	0.5706	0.0102	0.0028	0.0014	100	100.0000	0.4924	0.0064	0.0016	0.0007	100
0.0046	25.0	5425	0.2151	0.0033	100.0000	0.5615	0.0102	0.0028	0.0014	100	100.0000	0.5042	0.0065	0.0016	0.0007	100
0.0031	26.0	5642	0.2156	0.0033	100.0000	0.5651	0.0102	0.0028	0.0014	100	100.0000	0.5084	0.0065	0.0016	0.0007	100
0.0031	27.0	5859	0.2153	0.0033	100.0000	0.5596	0.0101	0.0028	0.0014	100	100.0000	0.4941	0.0065	0.0016	0.0007	100
0.0029	28.0	6076	0.2152	0.0033	100.0000	0.5743	0.0103	0.0029	0.0014	100	100.0000	0.4840	0.0064	0.0016	0.0007	100
0.0029	29.0	6293	0.2157	0.0033	100.0000	0.5780	0.0103	0.0029	0.0014	100	100.0000	0.4891	0.0064	0.0016	0.0007	100
0.0023	30.0	6510	0.2158	0.0033	100.0000	0.5798	0.0103	0.0029	0.0014	100	100.0000	0.4933	0.0064	0.0016	0.0007	100

Framework versions

• Transformers 4.49.0
• Pytorch 2.5.1+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0