Instructions to use Rishu115/mlm-bert-train_finalTraining_changedLR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- TF-Keras
How to use Rishu115/mlm-bert-train_finalTraining_changedLR with TF-Keras:
# Note: 'keras<3.x' or 'tf_keras' must be installed (legacy), and from_pretrained_keras was removed in huggingface_hub 1.0. # See https://github.com/keras-team/tf-keras for more details. # !pip install "huggingface_hub<1.0" tf_keras from huggingface_hub import from_pretrained_keras model = from_pretrained_keras("Rishu115/mlm-bert-train_finalTraining_changedLR") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from Rishu115/mlm-bert-train_finalTraining_changedLR: direct link, hf CLI and curl.
- Browser
- Download file 1.65 kB
-
https://huggingface.co/Rishu115/mlm-bert-train_finalTraining_changedLR/resolve/main/README.md
- Command line
-
hf download hf://Rishu115/mlm-bert-train_finalTraining_changedLR/README.md
-
curl -L -o README.md https://huggingface.co/Rishu115/mlm-bert-train_finalTraining_changedLR/resolve/main/README.md
1.65 kB
metadata
tags:
- generated_from_keras_callback
model-index:
- name: Rishu115/mlm-bert-train_finalTraining_changedLR
results: []
Rishu115/mlm-bert-train_finalTraining_changedLR
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.9469
- Validation Loss: 0.8665
- Epoch: 1
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': 5e-05, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 47396, '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': 0.01}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 1.1016 | 0.8681 | 0 |
| 0.9469 | 0.8665 | 1 |
Framework versions
- Transformers 4.23.1
- TensorFlow 2.10.0
- Datasets 2.10.1
- Tokenizers 0.13.2