pegasus-200tok-summaries-bert-base-cased-news-16batch_3epoch_2e5lr_01wd

This model is a fine-tuned version of bert-base-cased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2990
• F1: 0.9197

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: 16
• eval_batch_size: 16
• seed: 47
• 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	F1
0.0751	1.0	3124	0.2061	0.9120
0.0336	2.0	6248	0.2623	0.9134
0.0168	3.0	9372	0.2990	0.9197

Framework versions

• Transformers 4.35.1
• Pytorch 2.1.0+cu121
• Datasets 2.14.6
• Tokenizers 0.14.1