This model is a fine-tuned version of google-t5/t5-small on an the Amazon Fine Food Reviews dataset.
It achieves the following results on the evaluation set:
Loss: 2.879612684249878
Rouge1: 0.6625
Rouge2: 0.4053
Rougel: 0.1755
Rougelsum: 0.1755
Gen Len: 5.3418
Bleu: 0.0178
Bert Precision: 0.8657
Bert Recall: 0.8505
Bert F1: 0.8575
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: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
