my_awesome_opus_books_model

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: 0.0199
• Bleu: 0.0
• Gen Len: 15.3322
• Meteor: 0.334

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len	Meteor
0.0225	1.0	2350	0.0212	0.0	13.3211	0.3919
0.0214	2.0	4700	0.0206	0.0	15.8069	0.3832
0.021	3.0	7050	0.0204	0.0	15.9015	0.3599
0.0207	4.0	9400	0.0204	0.0	13.5323	0.3856
0.0206	5.0	11750	0.0202	0.0	16.8016	0.249
0.0203	6.0	14100	0.0201	0.0	13.7396	0.3848
0.0204	7.0	16450	0.0200	0.0	15.1254	0.3674
0.0203	8.0	18800	0.0200	0.0	14.3336	0.3826
0.0203	9.0	21150	0.0199	0.0	14.9733	0.3565
0.0203	10.0	23500	0.0199	0.0	15.3322	0.334

Framework versions

• Transformers 4.45.1
• Pytorch 2.4.1
• Datasets 3.0.1
• Tokenizers 0.20.0