Training update: 150,790/241,442 rows (62.45%) | +417 new @ 2025-11-03 18:58:03

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 **62.42%** of planned data.
+- Status: **Early version** — trained on **62.45%** 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 (62.42%) 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 (62.45%) 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**: 241,436
-- **Rows processed (cumulative)**: 150,711 (62.42%)
-- **Training date**: 2025-11-03 18:11:02
+- **Total database rows**: 241,442
+- **Rows processed (cumulative)**: 150,790 (62.45%)
+- **Training date**: 2025-11-03 18:58:03
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67967ce814cafa066e2753b63baceddecec4cf72bad049a2fd8cb3d1cef00e01
+oid sha256:d0c14bbc9159e3b94d8bf1ce871c08df70a5462117b10b0872a676519dd70bb7
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b69b0342afab82ecbc3df398ca10f92afe39d755583ae42eba04dbd3a1684ec2
+oid sha256:4653941866fd2dd8a7a037e03da95a4ae26f10967d5f6f46386349a8dad8a21e
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1762193462.432714,
-  "trained_at_readable": "2025-11-03 18:11:02",
-  "samples_this_session": 1372,
-  "new_rows_this_session": 80,
-  "trained_rows_total": 150711,
-  "total_db_rows": 241436,
-  "percentage": 62.422753856094374,
+  "trained_at": 1762196283.971096,
+  "trained_at_readable": "2025-11-03 18:58:03",
+  "samples_this_session": 1500,
+  "new_rows_this_session": 417,
+  "trained_rows_total": 150790,
+  "total_db_rows": 241442,
+  "percentage": 62.45392268122365,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,