<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
t5-small-finetuned-qgsquad-qgen
This model is a fine-tuned version of t5-small on the qg_squad dataset. It achieves the following results on the evaluation set:
- Loss: 0.4039
- Rouge4 Precision: 0.0931
- Rouge4 Recall: 0.0834
- Rouge4 Fmeasure: 0.0843
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge4 Precision | Rouge4 Recall | Rouge4 Fmeasure |
---|---|---|---|---|---|---|
0.4325 | 1.0 | 4733 | 0.3960 | 0.0984 | 0.0867 | 0.0889 |
0.4137 | 2.0 | 9466 | 0.3863 | 0.1061 | 0.0946 | 0.0963 |
0.3914 | 3.0 | 14199 | 0.3806 | 0.1051 | 0.0938 | 0.0955 |
0.3946 | 4.0 | 18932 | 0.3786 | 0.1084 | 0.097 | 0.0986 |
0.3857 | 5.0 | 23665 | 0.3784 | 0.1101 | 0.0991 | 0.1007 |
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1