Training update: 159,018/161,542 rows (98.44%) | +100 new @ 2025-11-07 16:03:26

README.md

@@ -25,7 +25,7 @@ pipeline_tag: fill-mask
 - Model type: fine-tuned lightweight BERT variant  
 - Languages: English & Indonesia
 - Finetuned from: `boltuix/bert-micro`
-- Status: **Early version** — trained on **98.41%** of planned data.
+- Status: **Early version** — trained on **98.44%** of planned data.
 
 **Model sources**  
 - Base model: [boltuix/bert-micro](https://huggingface.co/boltuix/bert-micro)
@@ -51,7 +51,7 @@ You can use this model to classify cybersecurity-related text — for example, w
 - Early classification of SIEM alert & events.
 
 ## 3. Bias, Risks, and Limitations 
-Because the model is based on a small subset (98.41%) of planned data, performance is preliminary and may degrade on unseen or specialized domains (industrial control, IoT logs, foreign language).
+Because the model is based on a small subset (98.44%) of planned data, performance is preliminary and may degrade on unseen or specialized domains (industrial control, IoT logs, foreign language).
 - Inherits any biases present in the base model (`boltuix/bert-micro`) and in the fine-tuning data — e.g., over-representation of certain threat types, vendor or tooling-specific vocabulary.
 - **Should not be used as sole authority for incident decisions; only as an aid to human analysts.**
 
@@ -75,9 +75,9 @@ Since cybersecurity data often contains lengthy alert descriptions and execution
 - **LR scheduler**: Linear with warmup
 
 ### Training Data
-- **Total database rows**: 161,533
-- **Rows processed (cumulative)**: 158,964 (98.41%)
-- **Training date**: 2025-11-07 15:09:23
+- **Total database rows**: 161,542
+- **Rows processed (cumulative)**: 159,018 (98.44%)
+- **Training date**: 2025-11-07 16:03:26
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d96a6a0143bc7d14555f7a1bb0e3ec0dc5200a2ba09d6f83add2c17076d6e4e
+oid sha256:3dbbad049e34da5636cb08125da16d4d41878f227042bf5dc6f9f352cfef7784
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0d7d13a6a13e9b06cf0d8d949186fef3c06917bced7bcdd91f825d5589bb848
+oid sha256:c0b7cc019e20f798c63d57205f776807b77aa61c6c0b66b014ec4d06324273e4
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1762528163.3427398,
-  "trained_at_readable": "2025-11-07 15:09:23",
-  "samples_this_session": 1410,
-  "new_rows_this_session": 54,
-  "trained_rows_total": 158964,
-  "total_db_rows": 161533,
-  "percentage": 98.40961289643603,
+  "trained_at": 1762531406.4525785,
+  "trained_at_readable": "2025-11-07 16:03:26",
+  "samples_this_session": 1485,
+  "new_rows_this_session": 100,
+  "trained_rows_total": 159018,
+  "total_db_rows": 161542,
+  "percentage": 98.43755803444306,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,