flan-t5-small-samsum

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

• Loss: 1.6313
• Rouge1: 44.0269
• Rouge2: 20.0328
• Rougel: 36.6724
• Rougelsum: 40.1413
• Gen Len: 16.8120

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
1.5776	1.0	1842	1.6419	43.5645	19.3402	36.24	39.8321	16.8242
1.5492	2.0	3684	1.6314	43.7723	19.3665	36.3105	39.8579	16.9744
1.5435	3.0	5526	1.6355	43.7953	19.6781	36.3307	39.9281	16.7937
1.5375	4.0	7368	1.6338	43.7685	19.7748	36.3904	39.9452	16.8852
1.5386	5.0	9210	1.6313	44.0269	20.0328	36.6724	40.1413	16.8120

Framework versions

• Transformers 4.33.2
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3