Training update: 148,208/241,289 rows (61.42%) | +486 new @ 2025-11-02 19:12:52

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 **61.29%** of planned data.
+- Status: **Early version** — trained on **61.42%** 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 (61.29%) 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 (61.42%) 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**: 241,285
-- **Rows processed (cumulative)**: 147,873 (61.29%)
-- **Training date**: 2025-11-02 18:09:56
+- **Total database rows**: 241,289
+- **Rows processed (cumulative)**: 148,208 (61.42%)
+- **Training date**: 2025-11-02 19:12:52
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eedc4863ec4f4e7aad4d698def60ce056ded9ea9347a459b972491c7e5296177
+oid sha256:a6f1ef4959d4e886fd9df4acfc5edb93c5a7cc0af182ad69e6a172785fea4099
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff0c8f1ba08a57b64e3a5594ae6eb2db6bdc88cd6265a49d8be48bc5317a54d8
+oid sha256:b2fa9d898b7e56b02072422feb85812e864f34d79450b1d25d3fae0456c70516
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1762106996.1314166,
-  "trained_at_readable": "2025-11-02 18:09:56",
-  "samples_this_session": 1385,
-  "new_rows_this_session": 335,
-  "trained_rows_total": 147873,
-  "total_db_rows": 241285,
-  "percentage": 61.285616594483706,
+  "trained_at": 1762110772.5712543,
+  "trained_at_readable": "2025-11-02 19:12:52",
+  "samples_this_session": 1458,
+  "new_rows_this_session": 486,
+  "trained_rows_total": 148208,
+  "total_db_rows": 241289,
+  "percentage": 61.42343828355209,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,