Text Classification
Transformers
PyTorch
English
bert
Generated from Trainer
Eval Results (legacy)
text-embeddings-inference
Instructions to use KarelDO/lstm.CEBaB_confounding.uniform.sa.5-class.seed_43 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use KarelDO/lstm.CEBaB_confounding.uniform.sa.5-class.seed_43 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="KarelDO/lstm.CEBaB_confounding.uniform.sa.5-class.seed_43")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("KarelDO/lstm.CEBaB_confounding.uniform.sa.5-class.seed_43") model = AutoModelForSequenceClassification.from_pretrained("KarelDO/lstm.CEBaB_confounding.uniform.sa.5-class.seed_43", device_map="auto") - Notebooks
- Google Colab
- Kaggle
lstm.CEBaB_confounding.uniform.sa.5-class.seed_43
This model is a fine-tuned version of lstm on the OpenTable OPENTABLE dataset. It achieves the following results on the evaluation set:
- Loss: 0.9442
- Accuracy: 0.6115
- Macro-f1: 0.5879
- Weighted-macro-f1: 0.6055
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:
- learning_rate: 0.001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 43
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
Training results
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.2+cu102
- Datasets 2.5.2
- Tokenizers 0.12.1
- Downloads last month
- 2
Evaluation results
- Accuracy on OpenTable OPENTABLEself-reported0.611