Update README.md

README.md

@@ -9,6 +9,12 @@ widget:
 model-index:
 - name: distilbert-base-indonesian-finetuned-PRDECT-ID
   results: []
+datasets:
+- SEACrowd/prdect_id
+language:
+- id
+metrics:
+- perplexity
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,59 +22,65 @@ should probably proofread and complete it, then remove this comment. -->
 
 # distilbert-base-indonesian-finetuned-PRDECT-ID
 
-This model is a fine-tuned version of [cahya/distilbert-base-indonesian](https://huggingface.co/cahya/distilbert-base-indonesian) on an unknown dataset.
-Perplexity: ~31
+This model is a fine-tuned version of [cahya/distilbert-base-indonesian](https://huggingface.co/cahya/distilbert-base-indonesian) on 
+[The PRDECT-ID Dataset] (https://www.kaggle.com/datasets/jocelyndumlao/prdect-id-indonesian-emotion-classification), it is a compilation of Indonesian product reviews that come with emotion and sentiment labels. 
+These reviews were gathered from one of Indonesia's largest e-commerce platforms, Tokopedia.
 
-## Model description
-
-More information needed
-
-## Intended uses & limitations
-
-More information needed
 
 ## Training and evaluation data
 
-More information needed
+I split my dataframe `df` into training, validation, and testing sets (`train_df`, `val_df`, `test_df`) 
+using the `train_test_split` function from `sklearn.model_selection`. 
+I set the test size to 20% for the initial split and further divided the remaining data equally between validation and testing sets. 
+This process ensures that each split (`val_df` and `test_df`) maintains the same class distribution as the original dataset (`stratify=df['label']`). 
 
-## Training procedure
 
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 16
-- eval_batch_size: 16
-- seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 500
-- num_epochs: 20
-
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 0.9507        | 1.0   | 41   | 0.8377          |
-| 0.0765        | 2.0   | 82   | 0.0212          |
-| 0.0025        | 3.0   | 123  | 0.0020          |
-| 0.0013        | 4.0   | 164  | 0.0013          |
-| 0.0009        | 5.0   | 205  | 0.0009          |
-| 0.0007        | 6.0   | 246  | 0.0007          |
-| 0.0005        | 7.0   | 287  | 0.0006          |
-| 0.0004        | 8.0   | 328  | 0.0005          |
-| 0.0003        | 9.0   | 369  | 0.0004          |
-| 0.0002        | 10.0  | 410  | 0.0003          |
-| 0.0002        | 11.0  | 451  | 0.0003          |
-| 0.0002        | 12.0  | 492  | 0.0003          |
-| 0.0002        | 13.0  | 533  | 0.0002          |
-| 0.0001        | 14.0  | 574  | 0.0002          |
-| 0.0001        | 15.0  | 615  | 0.0002          |
-| 0.0001        | 16.0  | 656  | 0.0002          |
-| 0.0001        | 17.0  | 697  | 0.0002          |
-| 0.0001        | 18.0  | 738  | 0.0002          |
-| 0.0001        | 19.0  | 779  | 0.0002          |
-| 0.0001        | 20.0  | 820  | 0.0002          |
+- num_train_epochs: 5
+- per_device_train_batch_size: 16
+- per_device_eval_batch_size: 16
+- warmup_steps: 500
+- weight_decay: 0.01
+- logging_dir: ./logs
+- logging_steps: 10
+- eval_strategy: epoch
+- save_strategy: epoch
+
+### Training and Evaluation Results
+
+The following table summarizes the training and validation loss over the epochs:
+
+| Epoch | Training Loss | Validation Loss |
+|-------|----------------|-----------------|
+| 1     | 0.000100       | 0.000062        |
+| 2     | 0.000000       | 0.000038        |
+| 3     | 0.000000       | 0.000025        |
+| 4     | 0.000000       | 0.000017        |
+| 5     | 0.000000       | 0.000014        |
+
+Train output:
+- global_step: 235
+- training_loss: 3.9409913424219185e-05
+- train_runtime: 44.6774
+- train_samples_per_second: 83.04
+- train_steps_per_second: 5.26
+- total_flos: 122954683514880.0
+- train_loss: 3.9409913424219185e-05
+- epoch: 5.0
+
+Evaluation:
+- eval_loss: 1.3968576240586117e-05
+- eval_runtime: 0.3321
+- eval_samples_per_second: 270.973
+- eval_steps_per_second: 18.065
+- epoch: 5.0
+
+Perplexity: 1.0000139686738017
+
+These results indicate excellent model performance and generalization capabilities.
+
 
 
 ### Framework versions
@@ -76,4 +88,4 @@ The following hyperparameters were used during training:
 - Transformers 4.41.2
 - Pytorch 2.1.2
 - Datasets 2.19.2
-- Tokenizers 0.19.1
+- Tokenizers 0.19.1