t5-base-cnndaily

This model is a fine-tuned version of north/t5_base_NCC_lm on the jkorsvik/cnn_daily_mail_nor_final dataset. It achieves the following results on the evaluation set:

• eval_loss: 2.5736
• eval_rouge1: 11.7206
• eval_rouge2: 1.695
• eval_rougeL: 8.9311
• eval_rougeLsum: 10.6052
• eval_gen_len: 54.8944
• eval_runtime: 175.8203
• eval_samples_per_second: 20.197
• eval_steps_per_second: 0.631
• step: 0

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: 16
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 4
• total_train_batch_size: 256
• total_eval_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20.0

Framework versions

• Transformers 4.27.0.dev0
• Pytorch 1.13.1
• Datasets 2.10.1
• Tokenizers 0.13.2