Instructions to use edgertej/poebert-balanced with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use edgertej/poebert-balanced with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="edgertej/poebert-balanced")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("edgertej/poebert-balanced") model = AutoModelForMaskedLM.from_pretrained("edgertej/poebert-balanced", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from edgertej/poebert-balanced: direct link, hf CLI and curl.
- Browser
- Download file 1.43 kB
-
https://huggingface.co/edgertej/poebert-balanced/resolve/main/README.md
- Command line
-
hf download hf://edgertej/poebert-balanced/README.md
-
curl -L -o README.md https://huggingface.co/edgertej/poebert-balanced/resolve/main/README.md
1.43 kB
metadata
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: edgertej/poebert-balanced
results: []
edgertej/poebert-balanced
This model is a fine-tuned version of bert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 3.8393
- Validation Loss: 3.5576
- 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', 'learning_rate': 3e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 4.1167 | 3.7102 | 0 |
| 3.8640 | 3.6570 | 1 |
| 3.9454 | 3.6030 | 2 |
| 3.8175 | 3.5792 | 3 |
| 3.8393 | 3.5576 | 4 |
Framework versions
- Transformers 4.19.2
- TensorFlow 2.9.1
- Datasets 2.4.0
- Tokenizers 0.12.1