Training update: 102,211/239,828 rows (42.62%) | +252 new @ 2025-10-26 11:35:04

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 **42.36%** of planned data.
+- Status: **Early version** — trained on **42.62%** 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 (42.36%) 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 (42.62%) 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**: 239,813
-- **Rows processed (cumulative)**: 101,579 (42.36%)
-- **Training date**: 2025-10-26 10:31:40
+- **Total database rows**: 239,828
+- **Rows processed (cumulative)**: 102,211 (42.62%)
+- **Training date**: 2025-10-26 11:35:04
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5330a83f284d2981d26ea903274b15765e5b3b1f966d983edd2c6d9c04025faf
+oid sha256:78c8be23078ecac38d67b4b35fdb850a3b0197b6ebf3051cab5bf0df4b911fc6
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45d07b8d89ddaff6deec292da8f08b18d5b015b587304f5ed47456a7000fdd6d
+oid sha256:f4f8508a352f83e6635fb226ba4fbfba0d43fb4c5946f954dca43893181fe6aa
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761474700.817493,
-  "trained_at_readable": "2025-10-26 10:31:40",
-  "samples_this_session": 5005,
-  "new_rows_this_session": 633,
-  "trained_rows_total": 101579,
-  "total_db_rows": 239813,
-  "percentage": 42.357586953167676,
+  "trained_at": 1761478504.5765448,
+  "trained_at_readable": "2025-10-26 11:35:04",
+  "samples_this_session": 4995,
+  "new_rows_this_session": 252,
+  "trained_rows_total": 102211,
+  "total_db_rows": 239828,
+  "percentage": 42.61845989625898,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,