baguette

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: 42.6891
• Rouge2: 18.3323
• Rougel: 35.2966
• Rougelsum: 38.936
• 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	42.489	18.2994	35.1094	38.8338	16.6532
1.8578	0.7	200	1.6878	42.026	18.2067	34.9977	38.5157	16.7216
1.835	1.06	300	1.6823	42.7823	18.594	35.4372	38.9901	16.9048
1.8144	1.41	400	1.6786	42.6458	18.3566	35.3547	38.9123	16.6618
1.8094	1.76	500	1.6754	42.6891	18.3323	35.2966	38.936	16.8474

Framework versions

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