04ddd442baee02bfeed8b44aeaf23dec

This model is a fine-tuned version of google-t5/t5-3b on the Helsinki-NLP/opus_books [es-no] dataset. It achieves the following results on the evaluation set:

• Loss: 1.7251
• Data Size: 1.0
• Epoch Runtime: 49.3483
• Bleu: 3.2054

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	3.0722	0	3.5170	0.2547
No log	1	89	2.8122	0.0078	4.3624	0.4280
No log	2	178	2.5493	0.0156	9.3522	1.1651
No log	3	267	2.3908	0.0312	13.5029	1.6462
No log	4	356	2.2908	0.0625	19.6069	2.0112
No log	5	445	2.1927	0.125	22.0305	1.9480
0.1639	6	534	2.0561	0.25	30.1683	1.7313
0.7471	7	623	1.9170	0.5	36.3555	1.9704
1.9101	8.0	712	1.7830	1.0	59.8510	2.2318
1.6847	9.0	801	1.7022	1.0	49.0735	2.4397
1.5486	10.0	890	1.6679	1.0	50.7396	2.7558
1.3925	11.0	979	1.6464	1.0	50.3828	2.7986
1.2455	12.0	1068	1.6370	1.0	52.6548	2.9703
1.1438	13.0	1157	1.6529	1.0	54.8597	3.0192
1.0515	14.0	1246	1.6598	1.0	50.0066	3.0726
0.9721	15.0	1335	1.6997	1.0	54.6917	3.0852
0.8643	16.0	1424	1.7251	1.0	49.3483	3.2054

Framework versions

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