Training update: 165,751/335,992 rows (49.33%) | +7 new @ 2026-03-27 17:24:55

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 **48.88%** of planned data.
+- Status: **Early version** — trained on **49.33%** 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 (48.88%) 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 (49.33%) 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**: 337,148
-- **Rows processed (cumulative)**: 164,792 (48.88%)
-- **Training date**: 2026-03-27 07:48:21
+- **Total database rows**: 335,992
+- **Rows processed (cumulative)**: 165,751 (49.33%)
+- **Training date**: 2026-03-27 17:24:55
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6909820cf3da69d442f30dbdbf9ef7ba11aa34b8a96e8a0c31230876a17bfdcf
+oid sha256:dd10ab85881afed4c9865e30279e5c05b5169c24ce79a0779ec2d18b84960172
 size 17671552

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1774597701.2824352,
-  "trained_at_readable": "2026-03-27 07:48:21",
-  "samples_this_session": 1000,
-  "new_rows_this_session": 1000,
-  "trained_rows_total": 164792,
-  "total_db_rows": 337148,
-  "percentage": 48.87823745061516,
+  "trained_at": 1774632295.1088505,
+  "trained_at_readable": "2026-03-27 17:24:55",
+  "samples_this_session": 989,
+  "new_rows_this_session": 7,
+  "trained_rows_total": 165751,
+  "total_db_rows": 335992,
+  "percentage": 49.331829329269745,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,