Update README.md

README.md

@@ -26,7 +26,62 @@ model-index:
 metrics:
 - accuracy
 - f1
-pipeline_tag: text-classification
 ---
 
-This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on a subset of the [amazon-polarity dataset](https://huggingface.co/datasets/amazon_polarity).
+# distilbert-sentiment
+
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on a subset of the [amazon-polarity dataset](https://huggingface.co/datasets/amazon_polarity).
+It achieves the following results on the evaluation set:
+- Loss: 0.119
+- Accuracy: 0.958
+- F1_score: 0.957
+
+## Model description
+
+This sentiment classifier has been trained on 180_000 samples for the training set, 20_000 samples for the validation set and 20_000 samples for the test set.
+
+## Intended uses & limitations
+```python
+from transformers import pipeline
+
+# Create the pipeline
+sentiment_classifier = pipeline('text-classification', model='AdamCodd/distilbert-base-uncased-finetuned-sentiment-amazon')
+
+# Now you can use the pipeline to classify emotions
+result = sentiment_classifier("This product doesn't fit me at all.")
+print(result)
+#[{'label': 'negative', 'score': 0.9994848966598511}]
+```
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 3e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 1270
+- optimizer: AdamW with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 150
+- num_epochs: 2
+- weight_decay: 0.01
+
+### Training results
+
+| key | value |
+| --- | ----- |
+| eval_loss | 0.119 |
+| eval_accuracy | 0.958 |
+| eval_f1_score | 0.957 |
+
+### Framework versions
+
+- Transformers 4.34.0
+- Pytorch lightning 2.0.9
+- Tokenizers 0.13.3