ft-t5-small-with-opusbook

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

• Loss: 1.7656
• Bleu: 4.7012
• Gen Len: 17.56

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: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
No log	1.0	13	1.8005	4.5307	17.53
No log	2.0	26	1.7837	4.7189	17.58
No log	3.0	39	1.7733	4.6952	17.56
No log	4.0	52	1.7675	4.7149	17.56
No log	5.0	65	1.7656	4.7012	17.56

Framework versions

• Transformers 4.35.2
• Pytorch 2.0.0
• Datasets 2.15.0
• Tokenizers 0.15.0