End of training

README.md

@@ -1,26 +1,81 @@
+---
+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: []
+---
 
-# Kubler-Ross Grief Stage Classification
+<!-- 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. -->
 
-This model is a fine-tuned version of `dbmdz/bert-base-turkish-128k-cased` on the Kübler-Ross grief stages dataset.
+# kubler-ross
 
-It classifies text into one of five stages of grief: denial, anger, bargaining, depression, acceptance.
+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
 
-### Results on the Test Set:
+## Model description
 
-| Metric            | Value   |
-|-------------------|---------|
-| **Accuracy**      | 0.5800 |
-| **Precision Macro**| 0.4307 |
-| **Recall Macro**   | 0.3236 |
-| **F1 Macro**      | 0.3256 |
-| **Precision Micro**| 0.5800 |
-| **Recall Micro**   | 0.5800 |
-| **F1 Micro**      | 0.5800 |
-| **MCC**           | 0.3217 |
+More information needed
 
-### Training Procedure
-- **Learning Rate**: 1e-5
-- **Batch Size**: 16
-- **Epochs**: 10
+## Intended uses & limitations
 
-This model was trained on a balanced dataset of texts categorized into the five stages of grief.
+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

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0dcdd1d60e8afffd25d0c53806ca90fd99af073889e6a64dc9bb5fbf8d5cd09
+oid sha256:6f3427cd1d62d3a7f464ddd4ba3eae8c68f0fc3cd0aa55480707bda1a61991f7
 size 737420300