flan-t5-large-extraction-cnndm_2000-summary

This model is a fine-tuned version of google/flan-t5-large on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.7295
• Rouge1: 27.984
• Rouge2: 11.9662
• Rougel: 25.9999
• Rougelsum: 26.0222
• Gen Len: 18.962

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: 2e-05
• train_batch_size: 8
• eval_batch_size: 24
• seed: 1799
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
2.1425	0.8	200	1.7841	27.3288	11.2913	25.3127	25.3298	18.958
1.8911	1.6	400	1.7508	28.4085	12.3877	26.3391	26.374	18.98
1.7625	2.4	600	1.7295	27.984	11.9662	25.9999	26.0222	18.962
1.7011	3.2	800	1.7338	28.5793	12.578	26.6817	26.7064	18.974
1.6198	4.0	1000	1.7298	28.7805	12.8467	26.6043	26.6578	18.992
1.5813	4.8	1200	1.7331	28.305	12.1954	26.1588	26.1865	18.984

Framework versions

• Transformers 4.18.0
• Pytorch 1.10.0+cu111
• Datasets 2.5.1
• Tokenizers 0.12.1