t5_base_fine_tuned_opus_books_en_de

This model is a fine-tuned version of t5-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2693
• Sacrebleu: 30.5457

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Sacrebleu
0.9813	1.0	945	0.2616	32.3189
0.6188	2.0	1890	0.2653	31.6118
0.5944	3.0	2835	0.2680	30.8915
0.5798	4.0	3780	0.2690	30.7392
0.5741	5.0	4725	0.2693	30.5457

Framework versions

• Transformers 4.35.0
• Pytorch 2.0.0
• Datasets 2.1.0
• Tokenizers 0.14.1