Training update: 75,127/239,359 rows (31.39%) | +445 new @ 2025-10-25 15:02:20

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 **31.11%** of planned data.
+- Status: **Early version** — trained on **31.39%** 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 (31.11%) 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 (31.39%) 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**: 239,291
-- **Rows processed (cumulative)**: 74,451 (31.11%)
-- **Training date**: 2025-10-25 11:01:16
+- **Total database rows**: 239,359
+- **Rows processed (cumulative)**: 75,127 (31.39%)
+- **Training date**: 2025-10-25 15:02:20
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6d6efaa1090ec99a848db185c5ec8b7e45db24e06b843aa18d3a22bd3f27c7c
+oid sha256:ddfbb016355be9a9f1986a1d75a35cb31b572c4dbb730b40bbe9c5fdad84b20c
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48586d093e69f22b765879f449181c87bcd2f217ae03e28cbe443eefd8e5f17f
+oid sha256:63178afcad6fd5fb68e4769a93a4a361ee91fc7f4a8cbb5de4cd1fdb979ae7ee
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761390076.0663939,
-  "trained_at_readable": "2025-10-25 11:01:16",
-  "samples_this_session": 5606,
-  "new_rows_this_session": 681,
-  "trained_rows_total": 74451,
-  "total_db_rows": 239291,
-  "percentage": 31.113163470418865,
+  "trained_at": 1761404540.3838744,
+  "trained_at_readable": "2025-10-25 15:02:20",
+  "samples_this_session": 5008,
+  "new_rows_this_session": 445,
+  "trained_rows_total": 75127,
+  "total_db_rows": 239359,
+  "percentage": 31.386745432592882,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,