my_awesome_opus_books_model

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

• Loss: 1.6410
• Bleu: 5.5014
• Gen Len: 17.6083

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: 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: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
1.8953	1.0	3178	1.6645	5.3209	17.6224
1.8509	2.0	6356	1.6410	5.5014	17.6083

Framework versions

• Transformers 4.32.1
• Pytorch 2.0.1+cu117
• Datasets 2.14.4
• Tokenizers 0.13.3