Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
bart_informative_canon_tpuv4-16 – AI Model by arthd24 | AlphaNeural AI
You can deploy this model and start earning money today!
arthd24
/
bart_informative_canon_tpuv4-16
like
0
transformers
tf
bart
text2text-generation
generated_from_keras_callback
cahya/bart-base
finetune
cc-by-sa-3.0
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
arthd24/bart_informative_canon_tpuv4-16
This model is a fine-tuned version of
cahya/bart-base
on an unknown dataset. It achieves the following results on the evaluation set:
Train Loss: 0.9645
Validation Loss: 1.3407
Epoch: 4
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:
optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 0.00016, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
training_precision: float32
Training results
Train Loss
Validation Loss
Epoch
1.4942
1.3048
0
1.2638
1.2892
1
1.1444
1.3026
2
1.0489
1.3232
3
0.9645
1.3407
4
Framework versions
Transformers 4.51.3
TensorFlow 2.16.1
Datasets 3.5.0
Tokenizers 0.21.1
