Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
ja-en-JESC-v3.0-wth-lr-decay – AI Model by Prgrg | AlphaNeural AI
You can deploy this model and start earning money today!
Prgrg
/
ja-en-JESC-v3.0-wth-lr-decay
like
0
transformers
tf
marian
text2text-generation
generated_from_keras_callback
apache-2.0
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Prgrg/ja-en-JESC-v3.0-wth-lr-decay
This model is a fine-tuned version of
Prgrg/ja-en-JESC-v2.0
on an unknown dataset. It achieves the following results on the evaluation set:
Train Loss: 2.3059
Validation Loss: 2.6161
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': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 0.0001, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.0001, 'decay_steps': 124000, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, '
passive_serialization
': True}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.001}
training_precision: mixed_float16
Training results
Train Loss
Validation Loss
Epoch
2.4918
2.6481
0
2.4369
2.6314
1
2.3852
2.6192
2
2.3416
2.6137
3
2.3059
2.6161
4
Framework versions
Transformers 4.26.1
TensorFlow 2.11.0
Datasets 2.10.1
Tokenizers 0.13.2
