You can deploy this model and start earning money today!

contemmcm/
7994496d487c1fafc8418740f38044b4

generated_from_trainer

Helsinki-NLP/opus-mt-en-sv

finetune

apache-2.0

endpoints_compatible

Views

No views yet

7994496d487c1fafc8418740f38044b4

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

Loss: 1.3910
Data Size: 1.0
Epoch Runtime: 12.6131
Bleu: 3.7302

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	5.0237	0	1.6237	0.0173
No log	1	204	4.7564	0.0078	2.9921	0.0146
No log	2	408	4.2669	0.0156	1.8890	0.0247
No log	3	612	3.7771	0.0312	2.2565	0.0226
No log	4	816	3.2038	0.0625	2.6295	0.0183
No log	5	1020	2.7806	0.125	3.2125	0.0831
0.2535	6	1224	2.5711	0.25	4.5702	0.0442
2.5172	7	1428	2.3751	0.5	7.2924	0.1664
2.243	8.0	1632	2.1183	1.0	13.3088	0.5652
2.0601	9.0	1836	1.9437	1.0	12.8462	0.9861
1.9198	10.0	2040	1.8147	1.0	12.4803	1.6530
1.7854	11.0	2244	1.7111	1.0	12.9266	2.0535
1.6843	12.0	2448	1.6355	1.0	12.7206	2.1625
1.5843	13.0	2652	1.5703	1.0	12.4248	2.5825
1.5039	14.0	2856	1.5254	1.0	12.8840	2.7709
1.4426	15.0	3060	1.4802	1.0	13.1414	3.0487
1.3634	16.0	3264	1.4471	1.0	13.0250	3.1733
1.3073	17.0	3468	1.4273	1.0	12.5074	3.2403
1.2727	18.0	3672	1.4175	1.0	12.4803	3.4263
1.2095	19.0	3876	1.3885	1.0	13.9999	3.4890
1.1554	20.0	4080	1.3847	1.0	13.2925	3.5344
1.1034	21.0	4284	1.3675	1.0	13.6537	3.6320
1.0634	22.0	4488	1.3703	1.0	13.1280	3.6924
1.0421	23.0	4692	1.3698	1.0	13.8030	3.7600
0.9887	24.0	4896	1.3780	1.0	13.5793	3.7037
0.97	25.0	5100	1.3910	1.0	12.6131	3.7302

Framework versions

Transformers 4.57.0
Pytorch 2.8.0+cu128
Datasets 4.2.0
Tokenizers 0.22.1

contemmcm/7994496d487c1fafc8418740f38044b4

7994496d487c1fafc8418740f38044b4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

contemmcm/
7994496d487c1fafc8418740f38044b4