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: 1.6754
• Rouge1: 42.6693
• Rouge2: 18.3378
• Rougel: 35.2729
• Rougelsum: 38.9033
• Gen Len: 16.8474

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: 52
• eval_batch_size: 52
• 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
1.8824	0.35	100	1.7015	42.4703	18.3068	35.1199	38.8083	16.6532
1.8578	0.7	200	1.6878	42.0064	18.2236	34.9497	38.4611	16.7216
1.835	1.06	300	1.6823	42.7407	18.5955	35.4344	38.9663	16.9048
1.8144	1.41	400	1.6786	42.6272	18.3894	35.34	38.8868	16.6618
1.8094	1.76	500	1.6754	42.6693	18.3378	35.2729	38.9033	16.8474

Framework versions

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