exp5_10partition_modelo_asl9000

vania2911/exp5_10partition_modelo_asl9000

exp5_10partition_modelo_asl9000 is a machine learning model from vania2911. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

3% of all-time downloads

All-time downloads

Public

Parameters

61.2M

6.9 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors245 MB · 99%

At a glance

Library: transformers
License: apache-2.0
Model type: marian
Access: Public
Created: Apr 2, 2025
Updated: Apr 2, 2025
SHA: a47736cf

Base models

Helsinki-NLP/opus-mt-es-es

Model card

From the Hugging Face model README

exp5_10partition_modelo_asl9000

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: 0.0826
Model Preparation Time: 0.0034
Bleu Msl: 0
Bleu 1 Msl: 0
Bleu 2 Msl: 0
Bleu 3 Msl: 0
Bleu 4 Msl: 0
Ter Msl: 100
Bleu Asl: 0
Bleu 1 Asl: 0.9838
Bleu 2 Asl: 0.9689
Bleu 3 Asl: 0.9510
Bleu 4 Asl: 0.9288
Ter Asl: 1.8673

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	Ter Msl	Bleu 1 Asl	Bleu 2 Asl	Bleu 3 Asl	Bleu 4 Asl	Ter Asl
No log	1.0	225	0.1402	0.0034	100	0.9571	0.9302	0.9016	0.8690	5.2217
No log	2.0	450	0.1092	0.0034	100	0.9671	0.9451	0.9202	0.8905	3.9409
0.2823	3.0	675	0.0958	0.0034	100	0.9742	0.9559	0.9339	0.9076	3.1034
0.2823	4.0	900	0.0995	0.0034	100	0.9722	0.9531	0.9312	0.9050	3.3744
0.0497	5.0	1125	0.1036	0.0034	100	0.9740	0.9555	0.9335	0.9075	3.2020
0.0497	6.0	1350	0.0950	0.0034	100	0.9748	0.9574	0.9371	0.9129	2.9064
0.025	7.0	1575	0.0952	0.0034	100	0.9752	0.9592	0.9393	0.9155	2.9064
0.025	8.0	1800	0.0997	0.0034	100	0.9783	0.9630	0.9444	0.9211	2.7094
0.0153	9.0	2025	0.0957	0.0034	100	0.9785	0.9627	0.9441	0.9214	2.4877
0.0153	10.0	2250	0.0923	0.0034	100	0.9783	0.9622	0.9429	0.9198	2.6108
0.0153	11.0	2475	0.0963	0.0034	100	0.9783	0.9619	0.9429	0.9200	2.6108
0.0118	12.0	2700	0.0957	0.0034	100	0.9800	0.9643	0.9458	0.9233	2.5369
0.0118	13.0	2925	0.0988	0.0034	100	0.9798	0.9641	0.9451	0.9222	2.4631
0.009	14.0	3150	0.1050	0.0034	100	0.9796	0.9637	0.9445	0.9212	2.5369
0.009	15.0	3375	0.0975	0.0034	100	0.9817	0.9670	0.9489	0.9269	2.2167
0.0063	16.0	3600	0.1001	0.0034	100	0.9800	0.9654	0.9474	0.9255	2.4138
0.0063	17.0	3825	0.1015	0.0034	100	0.9774	0.9623	0.9446	0.9226	2.5616
0.0058	18.0	4050	0.1012	0.0034	100	0.9798	0.9645	0.9461	0.9236	2.3892
0.0058	19.0	4275	0.0994	0.0034	100	0.9793	0.9645	0.9466	0.9249	2.5369
0.0038	20.0	4500	0.0988	0.0034	100	0.9795	0.9642	0.9460	0.9235	2.4384
0.0038	21.0	4725	0.0980	0.0034	100	0.9804	0.9654	0.9474	0.9253	2.3399
0.0038	22.0	4950	0.0983	0.0034	100	0.9806	0.9658	0.9482	0.9268	2.3645
0.003	23.0	5175	0.0985	0.0034	100	0.9804	0.9654	0.9475	0.9255	2.3645
0.003	24.0	5400	0.0998	0.0034	100	0.9806	0.9659	0.9486	0.9270	2.2906
0.0021	25.0	5625	0.0992	0.0034	100	0.9802	0.9653	0.9480	0.9265	2.4138
0.0021	26.0	5850	0.1014	0.0034	100	0.9806	0.9658	0.9481	0.9265	2.3399
0.0016	27.0	6075	0.1003	0.0034	100	0.9808	0.9663	0.9490	0.9274	2.2660
0.0016	28.0	6300	0.0990	0.0034	100	0.9806	0.9661	0.9488	0.9274	2.3399
0.0017	29.0	6525	0.1000	0.0034	100	0.9802	0.9653	0.9477	0.9260	2.3892
0.0017	30.0	6750	0.1008	0.0034	100	0.9800	0.9650	0.9472	0.9254	2.4138

Framework versions

Transformers 4.50.2
Pytorch 2.6.0+cu124
Datasets 3.5.0
Tokenizers 0.21.1

Library: transformers
Type: marian
License: apache-2.0
Created: Apr 2, 2025
Updated: Apr 2, 2025