You can deploy this model and start earning money today!

contemmcm/
4e3462d16952345153ca5635a5a21fd4

Name: 4e3462d16952345153ca5635a5a21fd4
Rating: 2.5 (12 reviews)

generated_from_trainer

Views

No views yet

4e3462d16952345153ca5635a5a21fd4

This model is a fine-tuned version of google/umt5-xl on the Helsinki-NLP/opus_books [es-pt] dataset. It achieves the following results on the evaluation set:

Loss: 1.9943
Data Size: 1.0
Epoch Runtime: 29.9419
Bleu: 11.2094

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	5.3492	0	2.0212	3.4438
No log	1	33	4.9663	0.0078	2.5893	4.1170
No log	2	66	4.6588	0.0156	7.0822	5.3905
No log	3	99	4.0458	0.0312	12.2250	8.7263
0.3111	4	132	3.7439	0.0625	17.6068	10.9321
0.3111	5	165	3.3414	0.125	23.1434	13.4585
0.3111	6	198	2.8961	0.25	22.0209	17.9711
0.7431	7	231	2.4527	0.5	26.5888	21.5912
1.9708	8.0	264	2.1089	1.0	44.6921	9.5379
1.9708	9.0	297	1.9657	1.0	40.6676	9.7992
2.253	10.0	330	1.8753	1.0	30.3930	10.7678
1.8319	11.0	363	1.8728	1.0	33.3907	11.1842
1.8319	12.0	396	1.8597	1.0	36.8172	11.0736
1.506	13.0	429	1.8850	1.0	31.8290	10.9175
1.2539	14.0	462	1.9000	1.0	37.0740	11.1616
1.2539	15.0	495	1.9790	1.0	40.2249	11.1400
1.0544	16.0	528	1.9943	1.0	29.9419	11.2094

Framework versions

Transformers 4.57.0
Pytorch 2.8.0+cu128
Datasets 4.2.0
Tokenizers 0.22.1

contemmcm/4e3462d16952345153ca5635a5a21fd4

4e3462d16952345153ca5635a5a21fd4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

contemmcm/
4e3462d16952345153ca5635a5a21fd4