Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
mt5-base-teste2 – AI Model by vladjr | AlphaNeural AI
You can deploy this model and start earning money today!
vladjr
/
mt5-base-teste2
like
0
transformers
tf
mt5
text2text-generation
generated_from_keras_callback
google/mt5-base
finetune
apache-2.0
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
vladjr/mt5-base-teste2
This model is a fine-tuned version of
google/mt5-base
on an unknown dataset. It achieves the following results on the evaluation set:
Train Loss: 0.4391
Validation Loss: 0.1861
Epoch: 7
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': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5.6e-05, 'decay_steps': 6720, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, '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
Validation Loss
Epoch
6.6129
1.3261
0
2.0105
0.5885
1
1.0783
0.4373
2
0.7812
0.3385
3
0.6474
0.2718
4
0.5428
0.2227
5
0.4805
0.1945
6
0.4391
0.1861
7
Framework versions
Transformers 4.34.0
TensorFlow 2.13.0
Datasets 2.14.5
Tokenizers 0.14.1