Training update: 157,476/241,907 rows (65.10%) | +5 new @ 2025-11-06 23:41:20

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 **65.07%** of planned data.
+- Status: **Early version** — trained on **65.10%** 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 (65.07%) 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 (65.10%) 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**: 241,904
-- **Rows processed (cumulative)**: 157,415 (65.07%)
-- **Training date**: 2025-11-06 22:01:34
+- **Total database rows**: 241,907
+- **Rows processed (cumulative)**: 157,476 (65.10%)
+- **Training date**: 2025-11-06 23:41:20
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83a6f7f2b49483f366ab4ae56c527fb9bd177a52b17171b02a66e1943cf9debf
+oid sha256:fdc4f7d201bb321e2c81fd57bb6e669553c7580bec7a3c23725eea0ba9349aad
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a26435ae94a69db886251e5d3bded26e4e95329258fe8d1982395a00b9a2d26
+oid sha256:d31fc40ddaf002d120c78171c14b278b40092e5625ffcb6bf9a34fe24fe0a209
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1762466494.3969994,
-  "trained_at_readable": "2025-11-06 22:01:34",
-  "samples_this_session": 1829,
-  "new_rows_this_session": 61,
-  "trained_rows_total": 157415,
-  "total_db_rows": 241904,
-  "percentage": 65.07333487664528,
+  "trained_at": 1762472480.0458539,
+  "trained_at_readable": "2025-11-06 23:41:20",
+  "samples_this_session": 1437,
+  "new_rows_this_session": 5,
+  "trained_rows_total": 157476,
+  "total_db_rows": 241907,
+  "percentage": 65.09774417441413,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,