Upload README.md with huggingface_hub

README.md

@@ -1,81 +1,26 @@
----
-library_name: transformers
-license: mit
-base_model: dbmdz/bert-base-turkish-128k-cased
-tags:
-- generated_from_trainer
-metrics:
-- accuracy
-model-index:
-- name: kubler-ross
-  results: []
----
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
+# Kubler-Ross Grief Stage Classification
 
-# kubler-ross
+This model is a fine-tuned version of `dbmdz/bert-base-turkish-128k-cased` on the Kübler-Ross grief stages dataset.
 
-This model is a fine-tuned version of [dbmdz/bert-base-turkish-128k-cased](https://huggingface.co/dbmdz/bert-base-turkish-128k-cased) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.1257
-- Accuracy: 0.5567
-- Precision Macro: 0.2228
-- Recall Macro: 0.2807
-- F1 Macro: 0.2482
-- Precision Micro: 0.5567
-- Recall Micro: 0.5567
-- F1 Micro: 0.5567
-- Mcc: 0.2773
+It classifies text into one of five stages of grief: denial, anger, bargaining, depression, acceptance.
 
-## Model description
+### Results on the Test Set:
 
-More information needed
+| 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 |
 
-## Intended uses & limitations
+### Training Procedure
+- **Learning Rate**: 1e-5
+- **Batch Size**: 16
+- **Epochs**: 10
 
-More information needed
-
-## Training and evaluation data
-
-More information needed
-
-## Training procedure
-
-### Training hyperparameters
-
-The following hyperparameters were used during training:
-- learning_rate: 1e-05
-- train_batch_size: 16
-- eval_batch_size: 16
-- seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 32
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 500
-- num_epochs: 10
-- mixed_precision_training: Native AMP
-
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision Macro | Recall Macro | F1 Macro | Precision Micro | Recall Micro | F1 Micro | Mcc     |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------------:|:------------:|:--------:|:---------------:|:------------:|:--------:|:-------:|
-| No log        | 1.0   | 44   | 1.6846          | 0.1133   | 0.1320          | 0.2258       | 0.0722   | 0.1133          | 0.1133       | 0.1133   | 0.0093  |
-| 1.7493        | 2.0   | 88   | 1.5106          | 0.3067   | 0.1782          | 0.2023       | 0.1790   | 0.3067          | 0.3067       | 0.3067   | -0.0303 |
-| 1.5805        | 3.0   | 132  | 1.3827          | 0.3867   | 0.1539          | 0.1919       | 0.1657   | 0.3867          | 0.3867       | 0.3867   | -0.0240 |
-| 1.4186        | 4.0   | 176  | 1.2970          | 0.4133   | 0.1660          | 0.2051       | 0.1761   | 0.4133          | 0.4133       | 0.4133   | 0.0183  |
-| 1.3134        | 5.0   | 220  | 1.2696          | 0.4067   | 0.1592          | 0.1985       | 0.1451   | 0.4067          | 0.4067       | 0.4067   | -0.0092 |
-| 1.2891        | 6.0   | 264  | 1.2582          | 0.4567   | 0.1828          | 0.2263       | 0.1933   | 0.4567          | 0.4567       | 0.4567   | 0.1016  |
-| 1.2485        | 7.0   | 308  | 1.2519          | 0.42     | 0.1674          | 0.2106       | 0.1860   | 0.42            | 0.42         | 0.42     | 0.0364  |
-| 1.2244        | 8.0   | 352  | 1.2252          | 0.4933   | 0.1967          | 0.2475       | 0.2187   | 0.4933          | 0.4933       | 0.4933   | 0.1649  |
-| 1.2244        | 9.0   | 396  | 1.2089          | 0.4933   | 0.2054          | 0.2510       | 0.2192   | 0.4933          | 0.4933       | 0.4933   | 0.1844  |
-| 1.1633        | 10.0  | 440  | 1.1257          | 0.5567   | 0.2228          | 0.2807       | 0.2482   | 0.5567          | 0.5567       | 0.5567   | 0.2773  |
-
-
-### Framework versions
-
-- Transformers 4.44.2
-- Pytorch 2.4.1+cu121
-- Datasets 3.0.1
-- Tokenizers 0.19.1
+This model was trained on a balanced dataset of texts categorized into the five stages of grief.