Training update: 67,262/239,086 rows (28.13%) | +622 new @ 2025-10-25 01:49:22

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 **27.99%** of planned data.
+- Status: **Early version** — trained on **28.13%** 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 (27.99%) 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 (28.13%) 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**: 239,035
-- **Rows processed (cumulative)**: 66,900 (27.99%)
-- **Training date**: 2025-10-24 21:33:36
+- **Total database rows**: 239,086
+- **Rows processed (cumulative)**: 67,262 (28.13%)
+- **Training date**: 2025-10-25 01:49:22
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d405728ce095203344cde8d2882e9676cc74993479d6031f8dd07d5392d75dbc
+oid sha256:edc9c1ce8152329ed9a6b1f771a8ce7a635b1631fc35259eeedada585b522dd1
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56b811994fa3d2163e8c8423dcf7a7c25a41695ddcc0bb31062967d5b87db68b
+oid sha256:b2c1409cb51b459710cd957eae0646062cc8d9d74b0a328ddd8c0c07fd9eb05e
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761341616.6732364,
-  "trained_at_readable": "2025-10-24 21:33:36",
-  "samples_this_session": 5009,
-  "new_rows_this_session": 362,
-  "trained_rows_total": 66900,
-  "total_db_rows": 239035,
-  "percentage": 27.987533206434208,
+  "trained_at": 1761356962.5277684,
+  "trained_at_readable": "2025-10-25 01:49:22",
+  "samples_this_session": 5384,
+  "new_rows_this_session": 622,
+  "trained_rows_total": 67262,
+  "total_db_rows": 239086,
+  "percentage": 28.132973072450916,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,