flan-t5-base-samsum

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

• Loss: 1.3707
• Rouge1: 47.5194
• Rouge2: 23.7737
• Rougel: 39.9592
• Rougelsum: 43.6505
• Gen Len: 17.2027

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: 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: 5

Training results

Training Loss	Epoch	Step	Gen Len	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
1.4543	1.0	1842	17.5531	1.3866	46.7793	22.9078	39.1288	42.9793
1.3399	2.0	3684	17.3297	1.3731	47.3308	24.0129	39.9801	43.7026
1.2682	3.0	5526	17.3309	1.3744	47.3898	23.7923	39.7349	43.5254
1.2302	4.0	7368	17.2027	1.3707	47.5194	23.7737	39.9592	43.6505
1.2082	5.0	9210	1.3751	47.6088	23.8305	40.0216	43.6941	17.2295

Framework versions

• Transformers 4.36.1
• Pytorch 2.0.1+cu117
• Datasets 2.15.0
• Tokenizers 0.15.0