pegasus-finetune-news – AI Model by ibk007 | AlphaNeural AI

You can deploy this model and start earning money today!

ibk007/
pegasus-finetune-news

like

0

text2text-generation

generated_from_trainer

google/pegasus-cnn_dailymail

endpoints_compatible

Views

No views yet

pegasus-finetune-news

This model is a fine-tuned version of google/pegasus-cnn_dailymail on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 4.0045
Rouge1: 38.75
Rouge2: 12.77
Rougel: 26.19
Rougelsum: 26.19

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: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 2
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
6.5926	1.0	198	6.3431	34.77	11.0	23.63	23.63
6.1828	2.0	396	5.8732	36.33	12.16	24.51	24.51
5.6097	3.0	594	5.2180	38.44	13.11	25.83	25.78
4.8181	4.0	792	4.3879	38.56	12.79	26.36	26.31
4.5547	5.0	990	4.0045	38.75	12.77	26.19	26.19

Framework versions

Transformers 4.51.3
Pytorch 2.6.0+cu124
Datasets 3.6.0
Tokenizers 0.21.1