Training update: 56,813/239,009 rows (23.77%) | +4214 new @ 2025-10-24 19:00:49

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 **23.25%** of planned data.
+- Status: **Early version** — trained on **23.77%** 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 (23.25%) 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 (23.77%) 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**: 238,990
-- **Rows processed (cumulative)**: 55,556 (23.25%)
-- **Training date**: 2025-10-24 17:24:55
+- **Total database rows**: 239,009
+- **Rows processed (cumulative)**: 56,813 (23.77%)
+- **Training date**: 2025-10-24 19:00:49
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26c9478c44575e399ad5dbc2db94c29dfd59b2195ff93fc2c055e1964db452ae
+oid sha256:8e753ee8683fbf4ee5b98d096c96216a1d1de1cdc8f4a41363da4c08f6394aea
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edf2bf0465643a14e9361afc2aa6911177173bb8f46eb68945bc07ac325ec287
+oid sha256:82c1889adab8d4ee65c96585fd9c4126e01fac0f1807c9bb92cf7cf8e68935d5
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761326695.0104125,
-  "trained_at_readable": "2025-10-24 17:24:55",
-  "samples_this_session": 4998,
-  "new_rows_this_session": 1257,
-  "trained_rows_total": 55556,
-  "total_db_rows": 238990,
-  "percentage": 23.246160927235447,
+  "trained_at": 1761332449.0565672,
+  "trained_at_readable": "2025-10-24 19:00:49",
+  "samples_this_session": 4990,
+  "new_rows_this_session": 4214,
+  "trained_rows_total": 56813,
+  "total_db_rows": 239009,
+  "percentage": 23.77023459367639,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,