Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
pegasus-finetuned-on-samsum – AI Model by Hashiru11 | AlphaNeural AI
You can deploy this model and start earning money today!
Hashiru11
/
pegasus-finetuned-on-samsum
like
0
tensorboard
safetensors
pegasus
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
pegasus-finetuned-on-samsum
This model is a fine-tuned version of
google/pegasus-cnn_dailymail
on
knkarthick/samsum
. It achieves the following results on the evaluation set:
Loss: 1.3787
Model description
google/pegasus-cnn_dailymail model finetuned on knkarthick/samsum
Intended uses & limitations
Can be used to summarize dialogue conversations
Training hyperparameters
The following hyperparameters were used during training:
learning_rate: 5e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 2
Training results
Training Loss
Epoch
Step
Validation Loss
1.5651
1.0
921
1.4094
1.472
2.0
1842
1.3787
Framework versions
Transformers 4.56.1
Pytorch 2.8.0+cu126
Datasets 4.0.0
Tokenizers 0.22.0
