Training update: 140,658/240,685 rows (58.44%) | +163 new @ 2025-10-31 00:20:43

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 **58.41%** of planned data.
+- Status: **Early version** — trained on **58.44%** 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 (58.41%) 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 (58.44%) 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**: 240,668
-- **Rows processed (cumulative)**: 140,581 (58.41%)
-- **Training date**: 2025-10-30 22:09:40
+- **Total database rows**: 240,685
+- **Rows processed (cumulative)**: 140,658 (58.44%)
+- **Training date**: 2025-10-31 00:20:43
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac0472099802f226d63db7c23594f65815484871ddf8e187242cd249477244f7
+oid sha256:6f613e22c01d1a71f2c6f238a2f758e841ccf942e30071fd63a3f79a42fa7d15
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:656bb16a627b4e0660d07832b0e36d30b0894d3e1c160f5a127eb8c8186a5bad
+oid sha256:c1da615b4c0fed4e30958a3429d568aaf8aa5acf97985aa9e540ef62df643f26
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761862180.2143474,
-  "trained_at_readable": "2025-10-30 22:09:40",
-  "samples_this_session": 2132,
-  "new_rows_this_session": 77,
-  "trained_rows_total": 140581,
-  "total_db_rows": 240668,
-  "percentage": 58.41283427792644,
+  "trained_at": 1761870043.4316208,
+  "trained_at_readable": "2025-10-31 00:20:43",
+  "samples_this_session": 2009,
+  "new_rows_this_session": 163,
+  "trained_rows_total": 140658,
+  "total_db_rows": 240685,
+  "percentage": 58.44070050065439,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,