flan-T5-base-sum

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: 1.3721
• Rouge1: 47.6617
• Rouge2: 23.7647
• Rougel: 40.1155
• Rougelsum: 43.6943
• Gen Len: 17.2759

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
1.4403	1.0	1842	1.3822	47.2814	23.7835	39.7427	43.4897	17.0256
1.3572	2.0	3684	1.3747	47.553	23.5714	39.8212	43.6246	17.4420
1.2822	3.0	5526	1.3721	47.6617	23.7647	40.1155	43.6943	17.2759
1.2375	4.0	7368	1.3764	47.7453	24.1099	40.1684	43.8659	17.2943
1.1935	5.0	9210	1.3780	47.614	23.6643	39.8434	43.6558	17.3077

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1+cu118
• Datasets 2.13.1
• Tokenizers 0.13.3