spacemanidol/flan-t5-large-6-1-cnndm

large-6-1-t

This model is a fine-tuned version of 6-1 on the cnn_dailymail 3.0.0 dataset. It achieves the following results on the evaluation set:

• Loss: 1.6639
• Rouge1: 41.4182
• Rouge2: 19.4871
• Rougel: 30.3528
• Rougelsum: 38.7818
• Gen Len: 70.3855

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: 30
• eval_batch_size: 12
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 60
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• num_epochs: 3.0

Training results

Framework versions

• Transformers 4.27.1
• Pytorch 1.12.0+cu116
• Datasets 2.4.0
• Tokenizers 0.13.2