Training update: 35,285/238,808 rows (14.78%) | +266 new @ 2025-10-24 02:02:47

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 **14.44%** of planned data.
+- Status: **Early version** — trained on **14.78%** 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 (14.44%) 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 (14.78%) 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**: 238,791
-- **Rows processed (cumulative)**: 34,480 (14.44%)
-- **Training date**: 2025-10-24 01:05:52
+- **Total database rows**: 238,808
+- **Rows processed (cumulative)**: 35,285 (14.78%)
+- **Training date**: 2025-10-24 02:02:47
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3d2af8b4046160add6884eadb42561e05309f46ca29a4e5dac577a138314d61
+oid sha256:b734b3043d42a2613cc91a3b10f65a1416356e31804fa009a66edb68056b9f8a
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09cb58cbc41c70239655f313b297f096a5b7a4f22129e762696cfe26a4c33144
+oid sha256:cb5415976be00c4671fca234f039c484362f7ce531c997d9847a5d1fe1b441cc
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761267952.9568763,
-  "trained_at_readable": "2025-10-24 01:05:52",
-  "samples_this_session": 4896,
-  "new_rows_this_session": 823,
-  "trained_rows_total": 34480,
-  "total_db_rows": 238791,
-  "percentage": 14.439405170211609,
+  "trained_at": 1761271367.0529475,
+  "trained_at_readable": "2025-10-24 02:02:47",
+  "samples_this_session": 4992,
+  "new_rows_this_session": 266,
+  "trained_rows_total": 35285,
+  "total_db_rows": 238808,
+  "percentage": 14.775468158520653,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,