Training update: 151,462/241,466 rows (62.73%) | +90 new @ 2025-11-03 23:19:33

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 **62.64%** of planned data.
+- Status: **Early version** — trained on **62.73%** 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 (62.64%) 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 (62.73%) 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**: 241,457
-- **Rows processed (cumulative)**: 151,242 (62.64%)
-- **Training date**: 2025-11-03 22:32:08
+- **Total database rows**: 241,466
+- **Rows processed (cumulative)**: 151,462 (62.73%)
+- **Training date**: 2025-11-03 23:19:33
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32de9d77b9e5ed9be25f56062204fec1e4a69d99a4732da2442fc02c0d1f08c9
+oid sha256:0f3e06a33be9a584281a1cc9e7582fd6dd483afe1a83ca2b07340e39ccb0b5cf
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bd10a03c042c2d17dc1718fbe03585461bd3fb52b2a476d4d5c90e69f85aae0
+oid sha256:5a9c0130249cd1ff462d84983a6c67a2dcee30e75d42b82f125b1483303e60a7
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1762209128.8171966,
-  "trained_at_readable": "2025-11-03 22:32:08",
-  "samples_this_session": 1826,
-  "new_rows_this_session": 220,
-  "trained_rows_total": 151242,
-  "total_db_rows": 241457,
-  "percentage": 62.63723975697536,
+  "trained_at": 1762211973.7031536,
+  "trained_at_readable": "2025-11-03 23:19:33",
+  "samples_this_session": 1621,
+  "new_rows_this_session": 90,
+  "trained_rows_total": 151462,
+  "total_db_rows": 241466,
+  "percentage": 62.72601525680634,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,