c857d54f7f192037ab22c244ef039ba2

This model is a fine-tuned version of google-t5/t5-3b on the Helsinki-NLP/opus_books [es-pt] dataset. It achieves the following results on the evaluation set:

• Loss: 1.4181
• Data Size: 1.0
• Epoch Runtime: 32.9357
• Bleu: 8.1709

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	3.2944	0	1.7353	1.3713
No log	1	33	2.8008	0.0078	2.4593	2.5608
No log	2	66	2.4435	0.0156	7.8904	4.5463
No log	3	99	2.1325	0.0312	13.3088	7.1310
0.1462	4	132	1.8029	0.0625	18.8619	8.1301
0.1462	5	165	1.6826	0.125	22.8153	5.6566
0.1462	6	198	1.5931	0.25	30.5116	5.1151
0.3288	7	231	1.4659	0.5	28.6133	6.0279
1.0157	8.0	264	1.3724	1.0	33.9262	7.7299
1.0157	9.0	297	1.3406	1.0	35.6349	8.1775
1.2764	10.0	330	1.3345	1.0	37.1619	8.7143
1.0483	11.0	363	1.3426	1.0	40.1266	7.7332
1.0483	12.0	396	1.3476	1.0	29.2315	8.2712
0.8835	13.0	429	1.3956	1.0	30.8995	7.5540
0.7596	14.0	462	1.4181	1.0	32.9357	8.1709

Framework versions

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