Training update: 147,671/241,265 rows (61.21%) | +12 new @ 2025-11-02 16:04:53

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 **61.20%** of planned data.
+- Status: **Early version** — trained on **61.21%** 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 (61.20%) 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 (61.21%) 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**: 241,260
-- **Rows processed (cumulative)**: 147,658 (61.20%)
-- **Training date**: 2025-11-02 15:03:19
+- **Total database rows**: 241,265
+- **Rows processed (cumulative)**: 147,671 (61.21%)
+- **Training date**: 2025-11-02 16:04:53
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d36d9bd011545034ae44adc9b3f58694227da43c8ae26b642e22d57c06b8c87
+oid sha256:fdca13d9528e3f0d80b9a9bfedf3284e512ad2d1cb5884ba6010218d1abb397b
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13d610b0316fd02bf142d3eb93f86ef928f4c770b16616262036e01244257709
+oid sha256:e994dbc566b5f5bbe2071e15d6a86894fc4585ec873326569d5ce21d99afb93a
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1762095799.4709258,
-  "trained_at_readable": "2025-11-02 15:03:19",
-  "samples_this_session": 1508,
-  "new_rows_this_session": 13,
-  "trained_rows_total": 147658,
-  "total_db_rows": 241260,
-  "percentage": 61.20285169526652,
+  "trained_at": 1762099493.476111,
+  "trained_at_readable": "2025-11-02 16:04:53",
+  "samples_this_session": 1656,
+  "new_rows_this_session": 12,
+  "trained_rows_total": 147671,
+  "total_db_rows": 241265,
+  "percentage": 61.20697158725882,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,