YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
Kubler-Ross Grief Stage Classification
This model is a fine-tuned version of dbmdz/bert-base-turkish-128k-cased
on the Kübler-Ross grief stages dataset.
It classifies text into one of five stages of grief: denial, anger, bargaining, depression, acceptance.
Results on the Test Set:
Metric | Value |
---|---|
Accuracy | 0.5200 |
Precision Macro | 0.2089 |
Recall Macro | 0.2618 |
F1 Macro | 0.2315 |
Precision Micro | 0.5200 |
Recall Micro | 0.5200 |
F1 Micro | 0.5200 |
MCC | 0.2140 |
Training Procedure
- Learning Rate: 1e-5
- Batch Size: 16
- Epochs: 10
This model was trained on a balanced dataset of texts categorized into the five stages of grief.
- Downloads last month
- 3
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.