Training update: 163,799/352,752 rows (46.43%) | +6 new @ 2026-03-12 17:29:27

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 **48.52%** of planned data.
+- Status: **Early version** — trained on **46.43%** 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 (48.52%) 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 (46.43%) 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**: 336,552
-- **Rows processed (cumulative)**: 163,286 (48.52%)
-- **Training date**: 2026-03-12 08:11:01
+- **Total database rows**: 352,752
+- **Rows processed (cumulative)**: 163,799 (46.43%)
+- **Training date**: 2026-03-12 17:29:27
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a23d19adbcf78a7f23a28e2be8da3abe97d354fa11ba750bc9fc58ae8f084bee
+oid sha256:72c5223c41db5c6af8d381be220a94a505bebb00fbfa2d5306a2c719b3a9a759
 size 17671552

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1773303061.0043788,
-  "trained_at_readable": "2026-03-12 08:11:01",
-  "samples_this_session": 1007,
-  "new_rows_this_session": 519,
-  "trained_rows_total": 163286,
-  "total_db_rows": 336552,
-  "percentage": 48.517316789084596,
+  "trained_at": 1773336567.1277254,
+  "trained_at_readable": "2026-03-12 17:29:27",
+  "samples_this_session": 1295,
+  "new_rows_this_session": 6,
+  "trained_rows_total": 163799,
+  "total_db_rows": 352752,
+  "percentage": 46.43460561527645,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,