b3a18eeed4b3cce07f9275cde7feadd9

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

• Loss: 11.8839
• Data Size: 0.125
• Epoch Runtime: 6.0240
• Bleu: 0.3251

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	11.2139	0	1.3833	0.2746
No log	1	33	11.3891	0.0078	1.6378	0.3161
No log	2	66	11.3910	0.0156	2.2869	0.3808
No log	3	99	11.5816	0.0312	3.3492	0.3018
0.9624	4	132	12.2121	0.0625	4.8865	0.3113
0.9624	5	165	11.8839	0.125	6.0240	0.3251

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu128
• Datasets 4.2.0
• Tokenizers 0.22.1