Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
Model_roberta_results – AI Model by darshan7 | AlphaNeural AI
You can deploy this model and start earning money today!
darshan7
/
Model_roberta_results
like
0
transformers
tf
roberta
question-answering
generated_from_keras_callback
cc-by-4.0
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
darshan7/Model_roberta_results
This model is a fine-tuned version of
ydshieh/roberta-base-squad2
on an unknown dataset. It achieves the following results on the evaluation set:
Train Loss: 0.0124
Validation Loss: 0.0711
Epoch: 9
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': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 181655, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
training_precision: float32
Training results
Train Loss
Validation Loss
Epoch
0.1299
0.0725
0
0.0621
0.0610
1
0.0394
0.0553
2
0.0256
0.0631
3
0.0161
0.0711
4
0.0123
0.0711
5
0.0123
0.0711
6
0.0123
0.0711
7
0.0125
0.0711
8
0.0124
0.0711
9
Framework versions
Transformers 4.30.1
TensorFlow 2.12.0
Datasets 2.12.0
Tokenizers 0.13.3
