Training update: 136,215/240,622 rows (56.61%) | +16 new @ 2025-10-30 01:17:38

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 **56.56%** of planned data.
+- Status: **Early version** — trained on **56.61%** 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 (56.56%) 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 (56.61%) 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**: 240,616
-- **Rows processed (cumulative)**: 136,082 (56.56%)
-- **Training date**: 2025-10-30 00:27:40
+- **Total database rows**: 240,622
+- **Rows processed (cumulative)**: 136,215 (56.61%)
+- **Training date**: 2025-10-30 01:17:38
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86759d836afc553992619bd8543d7a3da57f0118922e72d9cb7b836fee340945
+oid sha256:94f420af7ee05fa039b577cfd8a15852134c698ee268366c2f14fc9c850a5e75
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:182c64a0757579059f32ac513ba3cc832bc33e1cf0c2e3fe529ba5806693dcd3
+oid sha256:7f09ecb28d4cd45610908a5f4f4e57c951cc055cf60b094ad640b784fdaae8cf
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761784060.9851012,
-  "trained_at_readable": "2025-10-30 00:27:40",
-  "samples_this_session": 1995,
-  "new_rows_this_session": 133,
-  "trained_rows_total": 136082,
-  "total_db_rows": 240616,
-  "percentage": 56.55567377065531,
+  "trained_at": 1761787058.2839193,
+  "trained_at_readable": "2025-10-30 01:17:38",
+  "samples_this_session": 2089,
+  "new_rows_this_session": 16,
+  "trained_rows_total": 136215,
+  "total_db_rows": 240622,
+  "percentage": 56.609536950071075,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,