flan-t5-small-finetuned-question-generation

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

• Loss: 1.5998
• Rouge1: 50.1718
• Rouge2: 27.5603
• Rougel: 46.3981
• Rougelsum: 46.3975
• Gen Len: 13.7948

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: 0.0001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.819	1.0	10913	1.6159	48.8496	26.1270	45.1331	45.1442	13.8064
1.6487	2.0	21826	1.5947	48.8142	26.2209	45.1475	45.1482	13.8229
1.5546	3.0	32739	1.5910	49.6261	27.1655	45.9472	45.9535	13.9086
1.4862	4.0	43652	1.5887	49.9953	27.4630	46.2824	46.2841	13.7223
1.4327	5.0	54565	1.5950	50.1663	27.6038	46.4602	46.4721	13.7106
1.3907	6.0	65478	1.5910	49.9510	27.4795	46.2230	46.2218	13.8172
1.3598	7.0	76391	1.5973	50.1049	27.4804	46.3268	46.3300	13.7966
1.3388	8.0	87304	1.5998	50.1718	27.5603	46.3981	46.3975	13.7948

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1
• Datasets 2.20.0
• Tokenizers 0.19.1