Training update: 161,063/163,697 rows (98.39%) | +3 new @ 2025-11-10 23:13:57

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 **98.37%** of planned data.
+- Status: **Early version** — trained on **98.39%** 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 (98.37%) 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 (98.39%) 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**: 163,690
-- **Rows processed (cumulative)**: 161,020 (98.37%)
-- **Training date**: 2025-11-10 22:02:51
+- **Total database rows**: 163,697
+- **Rows processed (cumulative)**: 161,063 (98.39%)
+- **Training date**: 2025-11-10 23:13:57
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acce098b787a13369b20e9151ec6e5c636d0d633c93f175e9abcd04d83d67029
+oid sha256:8abd93e5c9507d047ae90f5645f256ecc1780c9ea0e7a646c20055de63a1118f
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5defe945884b2bc62241c645b7909ed47a10a909d5ffd0e0f929c7f1b941d013
+oid sha256:6ebb5d1d578d1d4abaef7fb9db0ef4dd5da1ee07a65afb2f3de0aed2ce3647ec
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1762812171.5920143,
-  "trained_at_readable": "2025-11-10 22:02:51",
-  "samples_this_session": 1624,
-  "new_rows_this_session": 43,
-  "trained_rows_total": 161020,
-  "total_db_rows": 163690,
-  "percentage": 98.3688679821614,
+  "trained_at": 1762816437.4065814,
+  "trained_at_readable": "2025-11-10 23:13:57",
+  "samples_this_session": 1332,
+  "new_rows_this_session": 3,
+  "trained_rows_total": 161063,
+  "total_db_rows": 163697,
+  "percentage": 98.39092958331551,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,