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: 1.3737
• Rouge1: 47.6387
• Rouge2: 24.1608
• Rougel: 40.1108
• Rougelsum: 43.9213
• Gen Len: 17.2076

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
1.453	1.0	1842	1.3864	47.0319	22.9684	39.1486	42.9635	17.3797
1.3399	2.0	3684	1.3758	47.1982	23.4772	39.756	43.4967	17.1954
1.268	3.0	5526	1.3782	47.5188	23.9509	39.9305	43.7792	17.3822
1.2313	4.0	7368	1.3737	47.6387	24.1608	40.1108	43.9213	17.2076
1.206	5.0	9210	1.3764	47.7288	23.9829	40.1887	43.9615	17.2857

Framework versions

• Transformers 4.36.0
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0