Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
bart-cnn-samsum-peft-trained-x – AI Model by AlfredBink | AlphaNeural AI
You can deploy this model and start earning money today!
AlfredBink
/
bart-cnn-samsum-peft-trained-x
like
0
transformers
tensorboard
safetensors
bart
text2text-generation
generated_from_trainer
facebook/bart-large-cnn
finetune
mit
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
bart-cnn-samsum-peft-trained-x
This model is a fine-tuned version of
facebook/bart-large-cnn
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 0.0489
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: 1e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 8
Training results
Training Loss
Epoch
Step
Validation Loss
2.7177
1.0
200
2.2686
0.1079
2.0
400
0.0782
0.0679
3.0
600
0.0565
0.0639
4.0
800
0.0528
0.052
5.0
1000
0.0509
0.0542
6.0
1200
0.0498
0.0545
7.0
1400
0.0491
0.0542
8.0
1600
0.0489
Framework versions
Transformers 4.35.2
Pytorch 2.1.0+cu121
Datasets 2.16.1
Tokenizers 0.15.0
