Training update: 76,837/239,377 rows (32.10%) | +428 new @ 2025-10-25 16:49:48

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 **31.57%** of planned data.
+- Status: **Early version** — trained on **32.10%** 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 (31.57%) 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 (32.10%) 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**: 239,365
-- **Rows processed (cumulative)**: 75,572 (31.57%)
-- **Training date**: 2025-10-25 15:45:15
+- **Total database rows**: 239,377
+- **Rows processed (cumulative)**: 76,837 (32.10%)
+- **Training date**: 2025-10-25 16:49:48
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8a3c07ef9e2a8cd5e7564a6e0c8f84a85ab2792d5ac8fdb72918c3b3e16d915
+oid sha256:cf85782bb0a16349ca09823e282d023325d5a59d455fe9e4e60af7a648f0d8d0
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81a0e76e8792f87c9a8f0ee1ed6af4c5673426eb5ab7bd1e7bdf801c1e581532
+oid sha256:ae4cfcffab7c43cbcfd579129a86e5cd8d2b0aea58342189efed223e072dc049
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761407115.937705,
-  "trained_at_readable": "2025-10-25 15:45:15",
-  "samples_this_session": 5000,
-  "new_rows_this_session": 1265,
-  "trained_rows_total": 75572,
-  "total_db_rows": 239365,
-  "percentage": 31.57186723205147,
+  "trained_at": 1761410988.9699244,
+  "trained_at_readable": "2025-10-25 16:49:48",
+  "samples_this_session": 5017,
+  "new_rows_this_session": 428,
+  "trained_rows_total": 76837,
+  "total_db_rows": 239377,
+  "percentage": 32.098739644995135,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,