Training update: 5,452/238,304 rows (2.29%) | +100 new @ 2025-10-22 13:46:56

README.md

@@ -21,7 +21,7 @@ library_name: transformers
 - Model type: fine-tuned lightweight BERT variant  
 - Languages: English & Indonesia
 - Finetuned from: `boltuix/bert-micro`
-- Status: **Early version** — trained on **2.25%** of planned data.
+- Status: **Early version** — trained on **2.29%** of planned data.
 
 **Model sources**  
 - Base model: [boltuix/bert-micro](https://huggingface.co/boltuix/bert-micro)
@@ -42,7 +42,7 @@ You can use this model to classify cybersecurity-related text — for example, w
 - Not tested for non-cybersecurity domains or out-of-distribution data.
 
 ## 3. Bias, Risks, and Limitations 
-Because the model is based on a small subset (2.25%) 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 (2.29%) 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.
@@ -62,7 +62,7 @@ predicted_class = logits.argmax(dim=-1).item()
 ```
 
 ## 5. Training Details
-- **Trained records**: 5,352 / 238,301 (2.25%)
+- **Trained records**: 5,452 / 238,304 (2.29%)
 - **Learning rate**: 5e-05
 - **Epochs**: 3
 - **Batch size**: 16

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d340c06c95a5843b65254f84e6c7f74d4d9e89b2e1fca2d880fa7feb382028b
+oid sha256:83597f686df9ea7ac1cb1702cf6ff61d7c05c6dbee5bc84290141393eb7f004e
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1227bbd65d1743350ae87b8900d3e7308e875dc3e5bde540662c18abac307d77
+oid sha256:cef1fdb0132472721b13753338890f488f703a10c2954e4df7169a232be51f25
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761137204.7482285,
-  "trained_at_readable": "2025-10-22 12:46:44",
+  "trained_at": 1761140816.952946,
+  "trained_at_readable": "2025-10-22 13:46:56",
   "samples_this_session": 100,
   "new_rows_this_session": 100,
-  "trained_rows_total": 5352,
-  "total_db_rows": 238301,
-  "percentage": 2.2458990940029624,
+  "trained_rows_total": 5452,
+  "total_db_rows": 238304,
+  "percentage": 2.287834027125017,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05