Training update: 53,044/238,978 rows (22.20%) | +2512 new @ 2025-10-24 16:35:55

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 **21.13%** of planned data.
+- Status: **Early version** — trained on **22.20%** 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 (21.13%) 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 (22.20%) 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**: 238,960
-- **Rows processed (cumulative)**: 50,495 (21.13%)
-- **Training date**: 2025-10-24 15:51:43
+- **Total database rows**: 238,978
+- **Rows processed (cumulative)**: 53,044 (22.20%)
+- **Training date**: 2025-10-24 16:35:55
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe9d8b43eb07692d68d6ff6e039b37fde877eb9abf41ece4c4ea320ab9352820
+oid sha256:6b6d41d198d4f91a2ba3adea6d80f2c23e5e0263406dfb4065f0ca8d053dbf90
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84c08c7151f02ea39e00e34153987920f6a69a1664216947e762aebffc996d08
+oid sha256:82d332f6e9c2b96cb41eb02e9545646360ba3bbfbc280163191b3455994341b4
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761321103.4699993,
-  "trained_at_readable": "2025-10-24 15:51:43",
-  "samples_this_session": 4621,
-  "new_rows_this_session": 2600,
-  "trained_rows_total": 50495,
-  "total_db_rows": 238960,
-  "percentage": 21.131151657181118,
+  "trained_at": 1761323755.4606252,
+  "trained_at_readable": "2025-10-24 16:35:55",
+  "samples_this_session": 4996,
+  "new_rows_this_session": 2512,
+  "trained_rows_total": 53044,
+  "total_db_rows": 238978,
+  "percentage": 22.19618542292596,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,