Training update: 141,932/240,686 rows (58.97%) | +65 new @ 2025-10-31 02:08:58

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 **58.51%** of planned data.
+- Status: **Early version** — trained on **58.97%** 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 (58.51%) 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 (58.97%) 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**: 240,685
-- **Rows processed (cumulative)**: 140,821 (58.51%)
-- **Training date**: 2025-10-31 01:00:11
+- **Total database rows**: 240,686
+- **Rows processed (cumulative)**: 141,932 (58.97%)
+- **Training date**: 2025-10-31 02:08:58
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6412570b7be8fd9802744a2ed29ca0b10abecd0e0068a29c90d9e3610e50c105
+oid sha256:c15ec030beb15863b4c38fddfda42625e79c52a1301558808dfeb174b424eae2
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31dcb0d62b412f08509ff55604662444de86dfa0293a07a899b7889fc256e6b3
+oid sha256:e6c265d2b715d0a1b41b740d3550cf2707e0a630bf71d1a2b5f84e50c54cdb16
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761872411.680345,
-  "trained_at_readable": "2025-10-31 01:00:11",
-  "samples_this_session": 2002,
-  "new_rows_this_session": 1111,
-  "trained_rows_total": 140821,
-  "total_db_rows": 240685,
-  "percentage": 58.50842387352764,
+  "trained_at": 1761876538.048882,
+  "trained_at_readable": "2025-10-31 02:08:58",
+  "samples_this_session": 2509,
+  "new_rows_this_session": 65,
+  "trained_rows_total": 141932,
+  "total_db_rows": 240686,
+  "percentage": 58.96977805107069,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,