Training update: 134,666/240,607 rows (55.97%) | +44 new @ 2025-10-29 19:10:48

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 **55.78%** of planned data.
+- Status: **Early version** — trained on **55.97%** 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 (55.78%) 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 (55.97%) 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**: 240,607
-- **Rows processed (cumulative)**: 134,211 (55.78%)
-- **Training date**: 2025-10-29 18:03:06
+- **Rows processed (cumulative)**: 134,666 (55.97%)
+- **Training date**: 2025-10-29 19:10:48
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87342bfb6e42844e7ee4cd03f0cb490f26fdfb874a62e274ec94e89d55835404
+oid sha256:49e0694c01c308d190e57b70880252a7f13a9145bee5e1b166979c8016daaf8f
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33f87f146c476b69e77086ff53ff4e8b13e8bf48693c5fba3a7fefbcda9704ae
+oid sha256:6de46613aa26960d54a77ab0e2d3dd86df5e9fee32b7938f8c7816921e1fd45a
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761760986.6947248,
-  "trained_at_readable": "2025-10-29 18:03:06",
-  "samples_this_session": 2006,
-  "new_rows_this_session": 455,
-  "trained_rows_total": 134211,
+  "trained_at": 1761765048.2928042,
+  "trained_at_readable": "2025-10-29 19:10:48",
+  "samples_this_session": 1899,
+  "new_rows_this_session": 44,
+  "trained_rows_total": 134666,
   "total_db_rows": 240607,
-  "percentage": 55.7801726466811,
+  "percentage": 55.9692777018125,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,