Training update: 113,424/240,407 rows (47.18%) | +210 new @ 2025-10-28 01:03:05

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 **46.64%** of planned data.
+- Status: **Early version** — trained on **47.18%** 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 (46.64%) 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 (47.18%) 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**: 240,378
-- **Rows processed (cumulative)**: 112,102 (46.64%)
-- **Training date**: 2025-10-27 21:01:03
+- **Total database rows**: 240,407
+- **Rows processed (cumulative)**: 113,424 (47.18%)
+- **Training date**: 2025-10-28 01:03:05
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f93e6292eb4fc7818c6cd57531bc4e5044c9fbd04ca0c779ed96c2e29dacca8d
+oid sha256:79b8e855c55e1225d3d1128ba549b4208e9a0a0bae5983fd2fdb7922571272c4
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e59906949d85802b629781380e0f3a129612a44bca0a6360716301cda8db6be8
+oid sha256:30c9d607e30d7f4aa3eec3e150b92c5575a27a632000c23b28985e602d26ad31
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761598863.056816,
-  "trained_at_readable": "2025-10-27 21:01:03",
-  "samples_this_session": 4875,
-  "new_rows_this_session": 1324,
-  "trained_rows_total": 112102,
-  "total_db_rows": 240378,
-  "percentage": 46.63571541488822,
+  "trained_at": 1761613385.1778495,
+  "trained_at_readable": "2025-10-28 01:03:05",
+  "samples_this_session": 4513,
+  "new_rows_this_session": 210,
+  "trained_rows_total": 113424,
+  "total_db_rows": 240407,
+  "percentage": 47.17999059927539,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,