Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
gpt2-turkish-cased – AI Model by Bilgekul | AlphaNeural AI
You can deploy this model and start earning money today!
Bilgekul
/
gpt2-turkish-cased
like
0
transformers
tf
gpt2
text-generation
generated_from_keras_callback
openai-community/gpt2
finetune
mit
autotrain_compatible
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
gpt2-turkish-cased
This model is a fine-tuned version of
gpt2
on an unknown dataset. It achieves the following results on the evaluation set:
Train Loss: 5.6730
Train Accuracy: 0.0648
Validation Loss: 5.8539
Validation Accuracy: 0.0679
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': {'module': 'transformers.optimization_tf', 'class_name': 'WarmUp', 'config': {'initial_learning_rate': 3e-05, 'decay_schedule_fn': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': -887, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}, 'registered_name': 'WarmUp'}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
training_precision: mixed_float16
Training results
Train Loss
Train Accuracy
Validation Loss
Validation Accuracy
Epoch
5.8656
0.0678
5.9010
0.0905
0
5.8246
0.0667
5.8885
0.0885
1
5.7815
0.0670
5.8787
0.0806
2
5.7354
0.0657
5.8628
0.0741
3
5.6730
0.0648
5.8539
0.0679
4
Framework versions
Transformers 4.42.4
TensorFlow 2.15.0
Datasets 2.20.0
Tokenizers 0.19.1
