Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
BERT_Tweet_Sentiment_50k_5eps – AI Model by joe5campbell | AlphaNeural AI
You can deploy this model and start earning money today!
joe5campbell
/
BERT_Tweet_Sentiment_50k_5eps
like
0
transformers
tf
bert
text-classification
generated_from_keras_callback
apache-2.0
autotrain_compatible
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
BERT_Tweet_Sentiment_50k_5eps
This model is a fine-tuned version of
bert-base-uncased
on an unknown dataset. It achieves the following results on the evaluation set:
Train Loss: 0.0256
Train Accuracy: 0.9913
Validation Loss: 0.8905
Validation Accuracy: 0.8291
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': 'Adam', 'clipnorm': 1.0, 'learning_rate': 3e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
training_precision: float32
Training results
Train Loss
Train Accuracy
Validation Loss
Validation Accuracy
Epoch
0.3395
0.8513
0.4071
0.8372
0
0.1095
0.9606
0.6561
0.8291
1
0.0487
0.9835
0.7597
0.8304
2
0.0329
0.9890
0.7814
0.8273
3
0.0256
0.9913
0.8905
0.8291
4
Framework versions
Transformers 4.16.2
TensorFlow 2.8.0
Tokenizers 0.11.0
