Downloads · 30 days
0
mbert_lstm_bot
yazidsupriadi/mbert_lstm_bot
mbert_lstm_bot is a machine learning model from yazidsupriadi. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
- Train Loss: 0.3809 - Train Accuracy: 0.8187 | Precision: 0.8006 | Recall: 0.8502 | F1: 0.8247 - Validation Accuracy: 0.8610 | Precision: 0.8526 | Recall: 0.8739 | F1: 0.8631 - ROC AUC Score: 0.9466
Access
Public
Updated Jul 10, 2025
Repo size
21.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt1.4 GB · 100%
At a glance
- Access
- Public
- Created
- May 29, 2025
- Updated
- Jul 10, 2025
- SHA
- 7de7d268
Model card
From the Hugging Face model README
Training Log: IndoBERT + LSTM for Bot Detection
Epoch 1 (2025-06-05T04:17:35.968045)
- Train Loss: 0.3809
- Train Accuracy: 0.8187 | Precision: 0.8006 | Recall: 0.8502 | F1: 0.8247
- Validation Accuracy: 0.8610 | Precision: 0.8526 | Recall: 0.8739 | F1: 0.8631
- ROC AUC Score: 0.9466
Epoch 2 (2025-06-05T04:20:39.750483)
- Train Loss: 0.3044
- Train Accuracy: 0.8594 | Precision: 0.8687 | Recall: 0.8478 | F1: 0.8582
- Validation Accuracy: 0.8692 | Precision: 0.8793 | Recall: 0.8569 | F1: 0.8680
- ROC AUC Score: 0.9548
Epoch 3 (2025-06-05T04:23:30.860537)
- Train Loss: 0.2859
- Train Accuracy: 0.8702 | Precision: 0.8870 | Recall: 0.8495 | F1: 0.8678
- Validation Accuracy: 0.8790 | Precision: 0.9145 | Recall: 0.8370 | F1: 0.8740
- ROC AUC Score: 0.9590
Epoch 4 (2025-06-05T04:26:21.222720)
- Train Loss: 0.2755
- Train Accuracy: 0.8754 | Precision: 0.8873 | Recall: 0.8608 | F1: 0.8739
- Validation Accuracy: 0.8808 | Precision: 0.8855 | Recall: 0.8754 | F1: 0.8804
- ROC AUC Score: 0.9617
Epoch 5 (2025-06-05T04:29:19.107384)
- Train Loss: 0.2692
- Train Accuracy: 0.8786 | Precision: 0.8931 | Recall: 0.8609 | F1: 0.8767
- Validation Accuracy: 0.8865 | Precision: 0.9089 | Recall: 0.8599 | F1: 0.8837
- ROC AUC Score: 0.9642
Epoch 6 (2025-06-05T04:32:16.337333)
- Train Loss: 0.2637
- Train Accuracy: 0.8811 | Precision: 0.8922 | Recall: 0.8676 | F1: 0.8798
- Validation Accuracy: 0.8865 | Precision: 0.9054 | Recall: 0.8639 | F1: 0.8842
- ROC AUC Score: 0.9647
Epoch 7 (2025-06-05T04:35:18.187117)
- Train Loss: 0.2557
- Train Accuracy: 0.8841 | Precision: 0.8964 | Recall: 0.8694 | F1: 0.8827
- Validation Accuracy: 0.8872 | Precision: 0.8989 | Recall: 0.8734 | F1: 0.8860
- ROC AUC Score: 0.9659
Epoch 8 (2025-06-05T04:38:11.179661)
- Train Loss: 0.2525
- Train Accuracy: 0.8878 | Precision: 0.8976 | Recall: 0.8762 | F1: 0.8868
- Validation Accuracy: 0.8902 | Precision: 0.9224 | Recall: 0.8529 | F1: 0.8863
- ROC AUC Score: 0.9658
Epoch 9 (2025-06-05T04:41:10.267043)
- Train Loss: 0.2471
- Train Accuracy: 0.8917 | Precision: 0.9062 | Recall: 0.8745 | F1: 0.8901
- Validation Accuracy: 0.8915 | Precision: 0.9035 | Recall: 0.8774 | F1: 0.8902
- ROC AUC Score: 0.9676
Epoch 10 (2025-06-05T04:44:06.457499)
- Train Loss: 0.2436
- Train Accuracy: 0.8908 | Precision: 0.9030 | Recall: 0.8762 | F1: 0.8894
- Validation Accuracy: 0.8895 | Precision: 0.8856 | Recall: 0.8953 | F1: 0.8904
- ROC AUC Score: 0.9682
- Created
- May 29, 2025
- Updated
- Jul 10, 2025