Training update: 136,667/240,631 rows (56.80%) | +85 new @ 2025-10-30 06:07:33

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 **56.79%** of planned data.
+- Status: **Early version** — trained on **56.80%** 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 (56.79%) 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 (56.80%) 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.**
 
@@ -76,8 +76,8 @@ Since cybersecurity data often contains lengthy alert descriptions and execution
 
 ### Training Data
 - **Total database rows**: 240,631
-- **Rows processed (cumulative)**: 136,643 (56.79%)
-- **Training date**: 2025-10-30 05:20:50
+- **Rows processed (cumulative)**: 136,667 (56.80%)
+- **Training date**: 2025-10-30 06:07:33
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f177494418d8ca4563824b393a8d7824bed8d789a3ff8bdb6447b1d1a969f6a3
+oid sha256:1a7492f91a4edda1a13ece6196fa88b1acde9f184fc8e2151a7c4b2a45ac7cab
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01728d7be4d833cdcd4a9f522f8d193577c6228ea6007143ab0eb55422f7ba55
+oid sha256:eb165bff65527d5afdfcdc87436c8e4985055e25c278409d5f365b1a85a1578d
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761801650.7870038,
-  "trained_at_readable": "2025-10-30 05:20:50",
-  "samples_this_session": 1966,
-  "new_rows_this_session": 24,
-  "trained_rows_total": 136643,
+  "trained_at": 1761804453.0552475,
+  "trained_at_readable": "2025-10-30 06:07:33",
+  "samples_this_session": 1993,
+  "new_rows_this_session": 85,
+  "trained_rows_total": 136667,
   "total_db_rows": 240631,
-  "percentage": 56.78528535392364,
+  "percentage": 56.79525913120088,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,