Training update: 160,531/163,628 rows (98.11%) | +151 new @ 2025-11-10 14:04:17

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 **97.87%** of planned data.
+- Status: **Early version** — trained on **98.11%** 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 (97.87%) 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 (98.11%) 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**: 163,625
-- **Rows processed (cumulative)**: 160,144 (97.87%)
-- **Training date**: 2025-11-10 12:58:04
+- **Total database rows**: 163,628
+- **Rows processed (cumulative)**: 160,531 (98.11%)
+- **Training date**: 2025-11-10 14:04:17
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c63a626b5f6f0b9ff9769e5d400db107e59ab61028c6d45eb79b105d3181eed
+oid sha256:4f71c45a9536f3e4957e911a03fa92d76f91a6167406851ecbea74d15ee6488c
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fe0cbde3e5a46bb7de3345a71d3105851b810fc88126d646173518903fe32ff
+oid sha256:dc671b6041c2b98673dd09895439d3f6a125260f6004a8a89217246ec943146d
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1762779484.4204166,
-  "trained_at_readable": "2025-11-10 12:58:04",
-  "samples_this_session": 1500,
-  "new_rows_this_session": 387,
-  "trained_rows_total": 160144,
-  "total_db_rows": 163625,
-  "percentage": 97.8725744843392,
+  "trained_at": 1762783457.0859187,
+  "trained_at_readable": "2025-11-10 14:04:17",
+  "samples_this_session": 1720,
+  "new_rows_this_session": 151,
+  "trained_rows_total": 160531,
+  "total_db_rows": 163628,
+  "percentage": 98.1072921504877,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,