You can deploy this model and start earning money today!

contemmcm/
2e685b883accf2af1b45ae991f69ba51

generated_from_trainer

Helsinki-NLP/opus-mt-en-sv

finetune

apache-2.0

endpoints_compatible

Views

No views yet

2e685b883accf2af1b45ae991f69ba51

This model is a fine-tuned version of Helsinki-NLP/opus-mt-en-sv on the Helsinki-NLP/opus_books [fr-no] dataset. It achieves the following results on the evaluation set:

Loss: 2.6592
Data Size: 1.0
Epoch Runtime: 6.8658
Bleu: 2.7114

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	7.4129	0	1.0635	0.0398
No log	1	86	6.7802	0.0078	1.3136	0.0477
No log	2	172	6.2119	0.0156	1.4183	0.0480
No log	3	258	5.7763	0.0312	1.5812	0.0887
No log	4	344	5.2438	0.0625	1.7704	0.1844
0.2987	5	430	4.7060	0.125	2.2318	0.6107
1.1504	6	516	4.1571	0.25	2.9734	0.6482
1.4433	7	602	3.6125	0.5	4.2513	0.7483
2.0202	8.0	688	3.1815	1.0	6.4813	1.2353
3.0377	9.0	774	2.9603	1.0	6.1508	1.6256
2.777	10.0	860	2.8436	1.0	6.2357	1.8889
2.5983	11.0	946	2.7595	1.0	6.3116	1.9771
2.3474	12.0	1032	2.6948	1.0	6.2786	2.3073
2.2067	13.0	1118	2.6619	1.0	6.3204	2.2608
2.0558	14.0	1204	2.6432	1.0	6.3582	2.4937
1.9083	15.0	1290	2.6452	1.0	6.3082	2.6868
1.7878	16.0	1376	2.6473	1.0	6.3996	2.7239
1.6748	17.0	1462	2.6526	1.0	6.3619	2.7673
1.5629	18.0	1548	2.6592	1.0	6.8658	2.7114

Framework versions

Transformers 4.57.0
Pytorch 2.8.0+cu128
Datasets 4.2.0
Tokenizers 0.22.1

contemmcm/2e685b883accf2af1b45ae991f69ba51

2e685b883accf2af1b45ae991f69ba51

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

contemmcm/
2e685b883accf2af1b45ae991f69ba51