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: 1.6670
• Rouge1: 43.1157
• Rouge2: 18.7389
• Rougel: 35.4615
• Rougelsum: 39.2648
• Gen Len: 16.9109

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	42.1055	18.0331	34.7517	38.3767	16.5788
1.8463	0.43	200	1.6947	42.4427	18.2735	34.9451	38.8469	17.3614
1.8548	0.65	300	1.6792	42.6324	18.5506	35.1724	38.8717	17.1514
1.8358	0.87	400	1.6772	42.2127	18.2031	34.8749	38.3969	16.5873
1.8129	1.08	500	1.6729	42.6431	18.6961	35.4006	38.8667	16.9170
1.8068	1.3	600	1.6709	42.5591	18.3093	35.1272	38.6379	16.9451
1.7973	1.52	700	1.6687	42.8925	18.6265	35.292	38.9546	16.7546
1.7979	1.74	800	1.6668	42.9455	18.7294	35.4018	39.099	16.8791
1.7899	1.95	900	1.6670	43.1157	18.7389	35.4615	39.2648	16.9109

Framework versions

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