Training update: 163,169/164,092 rows (99.44%) | +8 new @ 2025-11-12 23:57:52

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 **99.43%** of planned data.
+- Status: **Early version** — trained on **99.44%** 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 (99.43%) 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 (99.44%) 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.**
 
@@ -76,8 +76,8 @@ Since cybersecurity data often contains lengthy alert descriptions and execution
 
 ### Training Data
 - **Total database rows**: 164,092
-- **Rows processed (cumulative)**: 163,159 (99.43%)
-- **Training date**: 2025-11-12 22:03:35
+- **Rows processed (cumulative)**: 163,169 (99.44%)
+- **Training date**: 2025-11-12 23:57:52
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06f7f9e918f48c63f57598c9a783a7018ebcd102b35f44aea07de756467ca849
+oid sha256:1b3c248ac8c8b0edfe8733c45b2121f7f7f1deed20748bee043e5da5deb5f210
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b05e2b1ad3856ceb6247f83714242886a97cc325113ec36441674f1cd21733f3
+oid sha256:5043bde02ba81be489cc0ec8d2be34284c738ca292d7120b572d18da071d1a95
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1762985015.88524,
-  "trained_at_readable": "2025-11-12 22:03:35",
-  "samples_this_session": 1700,
-  "new_rows_this_session": 10,
-  "trained_rows_total": 163159,
+  "trained_at": 1762991872.9996276,
+  "trained_at_readable": "2025-11-12 23:57:52",
+  "samples_this_session": 1353,
+  "new_rows_this_session": 8,
+  "trained_rows_total": 163169,
   "total_db_rows": 164092,
-  "percentage": 99.43141652243864,
+  "percentage": 99.43751066474904,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,