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: 1.3772
• Rouge1: 47.4145
• Rouge2: 23.9579
• Rougel: 40.0508
• Rougelsum: 43.7144
• Gen Len: 17.3162

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	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.4264	1.0	1842	1.3829	46.4916	23.1227	39.444	42.9025	17.0977
1.3527	2.0	3684	1.3732	47.0694	23.4769	39.5942	43.2226	17.4554
1.2554	3.0	5526	1.3709	46.8801	23.3161	39.5423	43.1581	17.2027
1.2503	4.0	7368	1.3736	47.4138	23.7437	40.0016	43.6108	17.2198
1.1675	5.0	9210	1.3772	47.4145	23.9579	40.0508	43.7144	17.3162

Framework versions

• Transformers 4.27.3
• Pytorch 1.13.1+cu116
• Datasets 2.10.1
• Tokenizers 0.13.2