t5_base_fine_tuned_synthetic_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: 0.3255
• Sacrebleu: 34.6747

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
0.454	1.0	945	0.2922	34.8635
0.0474	2.0	1890	0.3058	34.8379
0.0421	3.0	2835	0.3144	34.8678
0.039	4.0	3780	0.3234	34.7021
0.0369	5.0	4725	0.3255	34.6747

Framework versions

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