Training update: 5,847/238,343 rows (2.45%) | +100 new @ 2025-10-22 17:46:55

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 **2.41%** of planned data.
+- Status: **Early version** — trained on **2.45%** 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 (2.41%) 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 (2.45%) 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**: 5,747 / 238,334 (2.41%)
+- **Trained records**: 5,847 / 238,343 (2.45%)
 - **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:cb553fc7a62b35dc723f310d239de98985513a40670a8cc05c933b03586d3547
+oid sha256:f98caed8982ea1611b761fabcdcac912de18afac923c20bb85669221e7a25c4c
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3ab1cb73e66a90a6c25e489d7d39dbecc508cb3f7fb1364e697dc51b323d2cc
+oid sha256:6c275241009a8d3d8c4ee87ab9bf0e003f684f9c693cf6bd62482831fdd11392
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761151671.0591826,
-  "trained_at_readable": "2025-10-22 16:47:51",
+  "trained_at": 1761155215.335573,
+  "trained_at_readable": "2025-10-22 17:46:55",
   "samples_this_session": 100,
   "new_rows_this_session": 100,
-  "trained_rows_total": 5747,
-  "total_db_rows": 238334,
-  "percentage": 2.411321926372234,
+  "trained_rows_total": 5847,
+  "total_db_rows": 238343,
+  "percentage": 2.4531872133857506,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05