Training update: 145,278/241,043 rows (60.27%) | +406 new @ 2025-11-01 12:57:39

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 **60.11%** of planned data.
+- Status: **Early version** — trained on **60.27%** 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 (60.11%) 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 (60.27%) 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**: 241,039
-- **Rows processed (cumulative)**: 144,892 (60.11%)
-- **Training date**: 2025-11-01 12:07:34
+- **Total database rows**: 241,043
+- **Rows processed (cumulative)**: 145,278 (60.27%)
+- **Training date**: 2025-11-01 12:57:39
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc3fca23875f5c940d7fcfabe79b7550bb9b43c1fe2f4950d900284305a23e6f
+oid sha256:f0e2acef83a998434c445e2e7f9aec59d8989899990452d79828c81f79f60ad7
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:639225a09662c301d54ad8015478fb4467a9329888de972e9d542013eed43316
+oid sha256:ed179b474606029a094eb216dcafb24b7be12521289a950da667e5a5b050acd0
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761998854.7673814,
-  "trained_at_readable": "2025-11-01 12:07:34",
-  "samples_this_session": 1533,
-  "new_rows_this_session": 386,
-  "trained_rows_total": 144892,
-  "total_db_rows": 241039,
-  "percentage": 60.111434249229376,
+  "trained_at": 1762001859.696942,
+  "trained_at_readable": "2025-11-01 12:57:39",
+  "samples_this_session": 1501,
+  "new_rows_this_session": 406,
+  "trained_rows_total": 145278,
+  "total_db_rows": 241043,
+  "percentage": 60.27057412992703,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,