Training update: 126,384/240,549 rows (52.54%) | +157 new @ 2025-10-28 21:54:11

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 **52.35%** of planned data.
+- Status: **Early version** — trained on **52.54%** 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 (52.35%) 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 (52.54%) 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**: 240,549
-- **Rows processed (cumulative)**: 125,925 (52.35%)
-- **Training date**: 2025-10-28 21:23:14
+- **Rows processed (cumulative)**: 126,384 (52.54%)
+- **Training date**: 2025-10-28 21:54:11
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a985a2569f59819b62224aaed772b6e762edfb388c9226329726ebbc3d2b0fa3
+oid sha256:ca8623435679caeeacb3ceedc951264ddcdc3b4d6383bf71dbd144ba1c7c5aba
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8c4dbe361c931a542dbce35dcd6c9cee0ef7d752f93c128332d7ad4fff17028
+oid sha256:840c6edee498a0cc0ddd21f6459969a121aa44ec7d7d874174bdf7b012d71936
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761686594.441283,
-  "trained_at_readable": "2025-10-28 21:23:14",
-  "samples_this_session": 3243,
-  "new_rows_this_session": 459,
-  "trained_rows_total": 125925,
+  "trained_at": 1761688451.9819922,
+  "trained_at_readable": "2025-10-28 21:54:11",
+  "samples_this_session": 2997,
+  "new_rows_this_session": 157,
+  "trained_rows_total": 126384,
   "total_db_rows": 240549,
-  "percentage": 52.34900165870571,
+  "percentage": 52.53981517279224,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,