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: 1.6729
• Rouge1: 42.6222
• Rouge2: 18.682
• Rougel: 35.3954
• Rougelsum: 38.9104
• Gen Len: 16.9170

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.8863	0.22	100	1.7049	42.1145	18.0254	34.733	38.4052	16.5788
1.8463	0.43	200	1.6947	42.4119	18.2925	34.9702	38.8535	17.3614
1.8548	0.65	300	1.6792	42.5967	18.5244	35.1965	38.9087	17.1514
1.8358	0.87	400	1.6772	42.167	18.2032	34.8647	38.4144	16.5873
1.8129	1.08	500	1.6729	42.6222	18.682	35.3954	38.9104	16.9170
1.8068	1.3	600	1.6709	42.5238	18.311	35.1257	38.6584	16.9451
1.7973	1.52	700	1.6687	42.8715	18.6133	35.3054	38.971	16.7546
1.7979	1.74	800	1.6668	42.9038	18.7483	35.4156	39.1118	16.8791
1.7899	1.95	900	1.6670	43.1142	18.7369	35.4796	39.2724	16.9109

Framework versions

• Transformers 4.36.0
• Pytorch 2.0.0
• Datasets 2.15.0
• Tokenizers 0.15.0