Training update: 107,713/240,147 rows (44.85%) | +916 new @ 2025-10-27 05:44:49

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 **44.73%** of planned data.
+- Status: **Early version** — trained on **44.85%** 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 (44.73%) 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 (44.85%) 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**: 240,129
-- **Rows processed (cumulative)**: 107,403 (44.73%)
-- **Training date**: 2025-10-27 04:56:21
+- **Total database rows**: 240,147
+- **Rows processed (cumulative)**: 107,713 (44.85%)
+- **Training date**: 2025-10-27 05:44:49
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2eb3e7d75e36dc974f6ea3b22cc4281eed867649a46634145c95dd01273bdd4
+oid sha256:75e701f52fbfb986281d2852d4e769d9ad5bd709d0ce6de31aad1a319d733073
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e76974c45081afeaa6f62774569e9e0712cf16d036b784981f3967b74ce045a
+oid sha256:1a964e25dd1a59fe43ff5b96f29f3c7421c7d51d7ddc3e6b1b1f4d6d867af74d
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761540981.655126,
-  "trained_at_readable": "2025-10-27 04:56:21",
-  "samples_this_session": 4994,
-  "new_rows_this_session": 310,
-  "trained_rows_total": 107403,
-  "total_db_rows": 240129,
-  "percentage": 44.727209125095264,
+  "trained_at": 1761543889.4080493,
+  "trained_at_readable": "2025-10-27 05:44:49",
+  "samples_this_session": 4991,
+  "new_rows_this_session": 916,
+  "trained_rows_total": 107713,
+  "total_db_rows": 240147,
+  "percentage": 44.852944238320696,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,