Training update: 111,175/240,305 rows (46.26%) | +170 new @ 2025-10-27 10:34:15

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 **46.10%** of planned data.
+- Status: **Early version** — trained on **46.26%** 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 (46.10%) 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 (46.26%) 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**: 240,195
-- **Rows processed (cumulative)**: 110,722 (46.10%)
-- **Training date**: 2025-10-27 08:14:47
+- **Total database rows**: 240,305
+- **Rows processed (cumulative)**: 111,175 (46.26%)
+- **Training date**: 2025-10-27 10:34:15
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b2cba3c46b932b608d96a5a09053a9a599e3139ac745a099c8104d515560f53
+oid sha256:defea304f4a4de2adb86cae17b42ba9aef2ca2729de5cd97e77010c7d40c466c
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a4c17374b12785504ed0fe47e534c972cde02fe082a7abf8c86d087b9f049f6
+oid sha256:26520bd63c278080a08942a514683a1f2f89040b0ae5f8a255bf58081ad0c4e0
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761552887.2556503,
-  "trained_at_readable": "2025-10-27 08:14:47",
-  "samples_this_session": 5383,
-  "new_rows_this_session": 453,
-  "trained_rows_total": 110722,
-  "total_db_rows": 240195,
-  "percentage": 46.09671308728325,
+  "trained_at": 1761561255.8776634,
+  "trained_at_readable": "2025-10-27 10:34:15",
+  "samples_this_session": 5008,
+  "new_rows_this_session": 170,
+  "trained_rows_total": 111175,
+  "total_db_rows": 240305,
+  "percentage": 46.26412267743076,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,