opus_books_model_english

This model is a fine-tuned version of google-t5/t5-small on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.0262
• Bleu: 0.2611
• Gen Len: 18.4414

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: 2e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
No log	1.0	219	2.3885	0.0114	18.7877
No log	2.0	438	2.2908	0.0849	18.544
2.6058	3.0	657	2.2299	0.1009	18.4923
2.6058	4.0	876	2.1865	0.1334	18.5091
2.3958	5.0	1095	2.1510	0.1479	18.4726
2.3958	6.0	1314	2.1218	0.1947	18.4471
2.3164	7.0	1533	2.0984	0.2254	18.4531
2.3164	8.0	1752	2.0793	0.2388	18.4211
2.3164	9.0	1971	2.0641	0.2387	18.4614
2.2674	10.0	2190	2.0523	0.2476	18.4463
2.2674	11.0	2409	2.0427	0.2485	18.4343
2.2366	12.0	2628	2.0353	0.2555	18.4383
2.2366	13.0	2847	2.0302	0.2561	18.4394
2.2177	14.0	3066	2.0273	0.2597	18.4366
2.2177	15.0	3285	2.0262	0.2611	18.4414

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3