Training update: 118,652/240,509 rows (49.33%) | +135 new @ 2025-10-28 08:17:07

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 **48.10%** of planned data.
+- Status: **Early version** — trained on **49.33%** 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 (48.10%) 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 (49.33%) 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**: 240,470
-- **Rows processed (cumulative)**: 115,656 (48.10%)
-- **Training date**: 2025-10-28 07:10:16
+- **Total database rows**: 240,509
+- **Rows processed (cumulative)**: 118,652 (49.33%)
+- **Training date**: 2025-10-28 08:17:07
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93296b1150be48ce04bf2e246884d1f2a201140cd51271260daba3f6312e8c82
+oid sha256:78096307571e14b176a0c438952ee2aa9879d4b4d4983cc36182d52370760dcd
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67b04b8dee509dffd9b5806e6319c20926dedfff9d1a0218ff1c1f0bee789ce1
+oid sha256:acf29b62bd406ec3dc5d1085da703f99f7841cf42d1dcb111ae7232ccc6d50cc
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761635416.4934978,
-  "trained_at_readable": "2025-10-28 07:10:16",
-  "samples_this_session": 3000,
-  "new_rows_this_session": 3000,
-  "trained_rows_total": 115656,
-  "total_db_rows": 240470,
-  "percentage": 48.09581236744708,
+  "trained_at": 1761639427.0460968,
+  "trained_at_readable": "2025-10-28 08:17:07",
+  "samples_this_session": 3034,
+  "new_rows_this_session": 135,
+  "trained_rows_total": 118652,
+  "total_db_rows": 240509,
+  "percentage": 49.333704767804946,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,