9892c69b8ce660332f64cf05e2154f17

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

• Loss: 1.0776
• Data Size: 1.0
• Epoch Runtime: 1021.1650
• Bleu: 15.6416

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	2.2426	0	70.9220	4.7059
No log	1	2336	1.6327	0.0078	80.3382	12.1482
0.0262	2	4672	1.5494	0.0156	89.5344	13.7689
0.0377	3	7008	1.4785	0.0312	106.3581	13.5768
1.5506	4	9344	1.4069	0.0625	135.9375	14.5184
1.4786	5	11680	1.3373	0.125	200.6290	14.4053
1.358	6	14016	1.2428	0.25	316.6712	14.7558
1.2637	7	16352	1.1627	0.5	564.0895	15.3167
1.1517	8.0	18688	1.0868	1.0	1026.8957	15.4860
1.0093	9.0	21024	1.0508	1.0	1030.7444	15.4056
0.917	10.0	23360	1.0370	1.0	1020.0794	15.9829
0.848	11.0	25696	1.0415	1.0	1046.6410	15.7640
0.7567	12.0	28032	1.0429	1.0	1053.9459	15.8170
0.6874	13.0	30368	1.0575	1.0	1072.1412	15.5004
0.643	14.0	32704	1.0776	1.0	1021.1650	15.6416

Framework versions

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