Update README.md
Browse files
README.md
CHANGED
|
@@ -54,7 +54,9 @@ Deep learning models cannot process raw text; they require numerical tensors. We
|
|
| 54 |
2. Special Tokens: The tokenizer automatically prepends the [CLS] (Classification) token to the start of the sequence and the [SEP] (Separator) token at the end. The final hidden state corresponding to the [CLS] token is what the model uses for the binary classification decision.
|
| 55 |
|
| 56 |
3. Truncation and Padding: Transformer models require fixed-size input matrices for batch processing. Based on our EDA length distribution, we set max_length = 128.
|
|
|
|
| 57 |
o Sentences longer than 128 tokens were truncated.
|
|
|
|
| 58 |
o Sentences shorter than 128 tokens were padded with the [PAD] token (ID 0).
|
| 59 |
|
| 60 |
4. Attention Masks: To prevent the model from performing Self-Attention on meaningless padding tokens, the tokenizer generates an attention_mask (an array of 1s for real words and 0s for padding).
|
|
@@ -78,9 +80,13 @@ Accuracy, f1 score (macro and weighted)
|
|
| 78 |
### Results
|
| 79 |
|
| 80 |
When evaluated on a 80-20 split we obtained:
|
|
|
|
| 81 |
• Accuracy: 99.10%
|
|
|
|
| 82 |
• Macro Average F1-Score: 0.98
|
|
|
|
| 83 |
• Weighted Average F1-Score: 0.99
|
|
|
|
| 84 |
Meanwhile the dummy achieved 86.6% accuracy.
|
| 85 |
|
| 86 |
#### Summary
|
|
|
|
| 54 |
2. Special Tokens: The tokenizer automatically prepends the [CLS] (Classification) token to the start of the sequence and the [SEP] (Separator) token at the end. The final hidden state corresponding to the [CLS] token is what the model uses for the binary classification decision.
|
| 55 |
|
| 56 |
3. Truncation and Padding: Transformer models require fixed-size input matrices for batch processing. Based on our EDA length distribution, we set max_length = 128.
|
| 57 |
+
|
| 58 |
o Sentences longer than 128 tokens were truncated.
|
| 59 |
+
|
| 60 |
o Sentences shorter than 128 tokens were padded with the [PAD] token (ID 0).
|
| 61 |
|
| 62 |
4. Attention Masks: To prevent the model from performing Self-Attention on meaningless padding tokens, the tokenizer generates an attention_mask (an array of 1s for real words and 0s for padding).
|
|
|
|
| 80 |
### Results
|
| 81 |
|
| 82 |
When evaluated on a 80-20 split we obtained:
|
| 83 |
+
|
| 84 |
• Accuracy: 99.10%
|
| 85 |
+
|
| 86 |
• Macro Average F1-Score: 0.98
|
| 87 |
+
|
| 88 |
• Weighted Average F1-Score: 0.99
|
| 89 |
+
|
| 90 |
Meanwhile the dummy achieved 86.6% accuracy.
|
| 91 |
|
| 92 |
#### Summary
|