Training update: 144,636/240,871 rows (60.05%) | +159 new @ 2025-11-01 04:57:29

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 **60.04%** of planned data.
+- Status: **Early version** — trained on **60.05%** 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 (60.04%) 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 (60.05%) 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**: 240,850
-- **Rows processed (cumulative)**: 144,616 (60.04%)
-- **Training date**: 2025-11-01 03:02:27
+- **Total database rows**: 240,871
+- **Rows processed (cumulative)**: 144,636 (60.05%)
+- **Training date**: 2025-11-01 04:57:29
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bba73c3280aa021f110922f8d3cd2f62b1bc493b417c56903d4dc0e9c0b57f0e
+oid sha256:0b0b471cc7c7881f0a278a7041ab563abb7e0bf7906dcfaebd3739e6128fd30b
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1efb1720397c9400eacc2019cea650b6381658c291378f62feb2c78311f461fe
+oid sha256:306ffbec0c096bc9f539e4145d0a71ae13655fab4bc19fd1fef12bad7f482fad
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761966147.0506997,
-  "trained_at_readable": "2025-11-01 03:02:27",
-  "samples_this_session": 1504,
-  "new_rows_this_session": 20,
-  "trained_rows_total": 144616,
-  "total_db_rows": 240850,
-  "percentage": 60.04401079510069,
+  "trained_at": 1761973049.9750097,
+  "trained_at_readable": "2025-11-01 04:57:29",
+  "samples_this_session": 1629,
+  "new_rows_this_session": 159,
+  "trained_rows_total": 144636,
+  "total_db_rows": 240871,
+  "percentage": 60.04707914194734,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,