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: 42.6557
• Rouge2: 18.3585
• Rougel: 35.2496
• Rougelsum: 38.866
• 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	42.4532	18.3147	35.0815	38.7699	16.6532
1.8578	0.7	200	1.6878	41.9748	18.2334	34.934	38.4167	16.7216
1.835	1.06	300	1.6823	42.7247	18.6058	35.402	38.9437	16.9048
1.8144	1.41	400	1.6786	42.5857	18.3954	35.3072	38.8397	16.6618
1.8094	1.76	500	1.6754	42.6557	18.3585	35.2496	38.866	16.8474

Framework versions

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