Training update: 17,832/238,632 rows (7.47%) | +393 new @ 2025-10-23 13:12:22

README.md

@@ -25,7 +25,8 @@ pipeline_tag: fill-mask
 - Model type: fine-tuned lightweight BERT variant  
 - Languages: English & Indonesia
 - Finetuned from: `boltuix/bert-micro`
-- Status: **Early version** — trained on **6.12%** of planned data.
+- Status: **Early version** — trained on **7.47%** of planned data.
+
 **Model sources**  
 - Base model: [boltuix/bert-micro](https://huggingface.co/boltuix/bert-micro)
 - Data: Cybersecurity Data
@@ -50,7 +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 (6.12%) 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 (7.47%) 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.**
 
@@ -74,9 +75,9 @@ Since cybersecurity data often contains lengthy alert descriptions and execution
 - **LR scheduler**: Linear with warmup
 
 ### Training Data
-- **Total database rows**: 238,556
-- **Rows processed (cumulative)**: 14,599 (6.12%)
-- **Training date**: 2025-10-23 08:23:30
+- **Total database rows**: 238,632
+- **Rows processed (cumulative)**: 17,832 (7.47%)
+- **Training date**: 2025-10-23 13:12:22
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86472796d3e4b1bb73312a0465948981442c08867a00031d1016af552cf3abc7
+oid sha256:89a59bba88488a698b4e0daaa7cea694140c2ee2aadac582cf5c574f29ffbb92
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:529ab1fc70678f54a11dd53b3a151f93741a356a27e6add95b4915f5d610f70e
+oid sha256:09b4c7c8181e5f99f8cabfbb16284680bcd4d694613243b5ee85dc0db5bfc790
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761207810.4960542,
-  "trained_at_readable": "2025-10-23 08:23:30",
-  "samples_this_session": 4716,
-  "new_rows_this_session": 3482,
-  "trained_rows_total": 14599,
-  "total_db_rows": 238556,
-  "percentage": 6.119737084793508,
+  "trained_at": 1761225142.9111428,
+  "trained_at_readable": "2025-10-23 13:12:22",
+  "samples_this_session": 5238,
+  "new_rows_this_session": 393,
+  "trained_rows_total": 17832,
+  "total_db_rows": 238632,
+  "percentage": 7.472593784572061,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,