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: 42.6775
• Rouge2: 18.3775
• Rougel: 35.281
• Rougelsum: 38.9344
• 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	42.4867	18.3364	35.0855	38.8376	16.6532
1.8578	0.7	200	1.6878	42.0066	18.2434	34.9702	38.5065	16.7216
1.835	1.06	300	1.6823	42.7374	18.6187	35.4371	38.993	16.9048
1.8144	1.41	400	1.6786	42.6189	18.3792	35.3473	38.9192	16.6618
1.8094	1.76	500	1.6754	42.6775	18.3775	35.281	38.9344	16.8474

Framework versions

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