You can deploy this model and start earning money today!

contemmcm/
e0d9a80cc6405a3f406d64137a3f3a4c

Name: e0d9a80cc6405a3f406d64137a3f3a4c
Rating: 2.5 (5 reviews)

generated_from_trainer

Helsinki-NLP/opus-mt-en-sv

finetune

apache-2.0

endpoints_compatible

Views

No views yet

e0d9a80cc6405a3f406d64137a3f3a4c

This model is a fine-tuned version of Helsinki-NLP/opus-mt-en-sv on the Helsinki-NLP/opus_books [es-ru] dataset. It achieves the following results on the evaluation set:

Loss: 1.1589
Data Size: 1.0
Epoch Runtime: 26.2758
Bleu: 4.4193

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	5.0798	0	2.5103	0.0177
No log	1	419	4.4166	0.0078	3.3418	0.0840
No log	2	838	3.9687	0.0156	3.0122	0.0115
0.1134	3	1257	3.2525	0.0312	3.3522	0.0592
0.1134	4	1676	2.7815	0.0625	4.1998	0.0891
0.1817	5	2095	2.5510	0.125	5.6397	0.0480
0.3333	6	2514	2.3131	0.25	8.6902	0.2810
2.1504	7	2933	2.0082	0.5	14.7014	0.5598
1.7766	8.0	3352	1.6886	1.0	26.6909	1.4732
1.6011	9.0	3771	1.5178	1.0	26.9188	1.7795
1.4912	10.0	4190	1.4100	1.0	26.5421	2.2404
1.3696	11.0	4609	1.3420	1.0	27.3952	2.6403
1.3088	12.0	5028	1.2822	1.0	27.1165	2.9192
1.2246	13.0	5447	1.2354	1.0	26.3122	3.2785
1.2016	14.0	5866	1.2078	1.0	25.5330	3.3692
1.1243	15.0	6285	1.1899	1.0	26.0247	3.6236
1.0949	16.0	6704	1.1700	1.0	26.3475	3.5643
1.0541	17.0	7123	1.1507	1.0	26.0165	3.8937
1.0104	18.0	7542	1.1457	1.0	27.3559	3.9735
0.971	19.0	7961	1.1367	1.0	26.1694	3.9319
0.929	20.0	8380	1.1297	1.0	27.1917	4.2008
0.9101	21.0	8799	1.1318	1.0	27.0305	4.1735
0.8739	22.0	9218	1.1261	1.0	25.9767	4.1045
0.8561	23.0	9637	1.1320	1.0	25.0329	4.1344
0.8087	24.0	10056	1.1360	1.0	26.8554	4.3092
0.8031	25.0	10475	1.1353	1.0	26.3226	4.2992
0.7596	26.0	10894	1.1589	1.0	26.2758	4.4193

Framework versions

Transformers 4.57.0
Pytorch 2.8.0+cu128
Datasets 4.2.0
Tokenizers 0.22.1

contemmcm/e0d9a80cc6405a3f406d64137a3f3a4c

e0d9a80cc6405a3f406d64137a3f3a4c

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

contemmcm/
e0d9a80cc6405a3f406d64137a3f3a4c