Training update: 159,231/161,575 rows (98.55%) | +116 new @ 2025-11-08 01:34:00

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 **98.49%** of planned data.
+- Status: **Early version** — trained on **98.55%** 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 (98.49%) 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 (98.55%) 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**: 161,550
-- **Rows processed (cumulative)**: 159,118 (98.49%)
-- **Training date**: 2025-11-07 17:35:50
+- **Total database rows**: 161,575
+- **Rows processed (cumulative)**: 159,231 (98.55%)
+- **Training date**: 2025-11-08 01:34:00
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8e14620836543642cfad3e837a29f93fb49870f8703b706e8b81feb1d855d1a
+oid sha256:c08a1415ba57f96f100eb89fc4d99ea31a9a8060d6027a7a36fdd814bbdc34c2
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f483a0f349e6c0ad6bc85825e5a698300cc3a2e049c9a20a397bcdcbae82b61a
+oid sha256:abcb69ab881fdb9466a3516e0043a05217f63a67211e9b912ec6842ea0d0daf6
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1762536950.2322094,
-  "trained_at_readable": "2025-11-07 17:35:50",
-  "samples_this_session": 1500,
-  "new_rows_this_session": 113,
-  "trained_rows_total": 159118,
-  "total_db_rows": 161550,
-  "percentage": 98.49458372021046,
+  "trained_at": 1762565640.186049,
+  "trained_at_readable": "2025-11-08 01:34:00",
+  "samples_this_session": 1479,
+  "new_rows_this_session": 116,
+  "trained_rows_total": 159231,
+  "total_db_rows": 161575,
+  "percentage": 98.54928051988242,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,