jeongyoun/t5-FairytaleQA-SUM

t5-base-finetuned-summarization-FairytaleQA

This model is a fine-tuned version of t5-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1724
• Rouge1: 23.8024
• Rouge2: 14.5314
• Rougel: 22.4922
• Rougelsum: 23.2411
• Gen Len: 19.0

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: 4
• eval_batch_size: 4
• 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	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
0.1779	1.0	2137	0.1745	23.8099	14.5515	22.4987	23.2423	19.0
0.1705	2.0	4274	0.1724	23.8024	14.5196	22.4922	23.2411	19.0
0.1717	3.0	6411	0.1724	23.8024	14.5314	22.4922	23.2411	19.0
0.1723	4.0	8548	0.1724	23.8024	14.5314	22.4922	23.2411	19.0
0.1743	5.0	10685	0.1724	23.8024	14.5314	22.4922	23.2411	19.0

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1