bbhattar/flan_t5_xl_cnn_dailymail

flan-t5-xl

This model is a fine-tuned version of google/flan-t5-xl on the cnn_dailymail dataset. It achieves the following results on the evaluation set:

• Loss: 1.2648
• Rouge1: 45.1318
• Rouge2: 22.2773
• Rougel: 31.9084
• Rougelsum: 42.0558
• Gen Len: 94.2332

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: 0.0001
• train_batch_size: 24
• eval_batch_size: 24
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• total_train_batch_size: 96
• total_eval_batch_size: 96
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.4352	1.0	2991	1.2645	43.8582	21.2227	30.7038	40.761	101.9968
1.3198	2.0	5982	1.2525	44.4594	21.8174	31.4304	41.4563	94.0733
1.2151	3.0	8973	1.2648	45.1318	22.2773	31.9084	42.0558	94.2332

Framework versions

• Transformers 4.27.1
• Pytorch 2.0.0
• Datasets 2.10.1
• Tokenizers 0.13.2