Training update: 161,466/163,981 rows (98.47%) | +3 new @ 2025-11-11 21:20:21

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 **98.46%** of planned data.
+- Status: **Early version** — trained on **98.47%** 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 (98.46%) 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 (98.47%) 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**: 163,981
-- **Rows processed (cumulative)**: 161,461 (98.46%)
-- **Training date**: 2025-11-11 20:49:43
+- **Rows processed (cumulative)**: 161,466 (98.47%)
+- **Training date**: 2025-11-11 21:20:21
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d50c5571755f967aaa8e368f7e48be83a615c1a7108cf466f27be9851c0162e2
+oid sha256:5966f3f07663ddccba1fab5dbf7a7644f8a90eb3f7fca4e526a66741438f0ac8
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58b8ecd2389b2533a4c225a5d8314e11f05fefad10c840cb13fec7f29196f49f
+oid sha256:9cef16c35115878aa5e3759080050f7633142168fdc2704bddd02883072e3d5c
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1762894183.3307393,
-  "trained_at_readable": "2025-11-11 20:49:43",
-  "samples_this_session": 1654,
-  "new_rows_this_session": 5,
-  "trained_rows_total": 161461,
+  "trained_at": 1762896021.6303897,
+  "trained_at_readable": "2025-11-11 21:20:21",
+  "samples_this_session": 1329,
+  "new_rows_this_session": 3,
+  "trained_rows_total": 161466,
   "total_db_rows": 163981,
-  "percentage": 98.4632365944835,
+  "percentage": 98.4662857282246,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,