Training update: 3,416/238,011 rows (1.44%) | +100 new @ 2025-10-21 15:46:39

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 **1.39%** of planned data.
+- Status: **Early version** — trained on **1.44%** 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 (1.39%) 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 (1.44%) 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**: 3,316 / 237,996 (1.39%)
+- **Trained records**: 3,416 / 238,011 (1.44%)
 - **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:a8d45d621946efc8390ed17653c6f872ad302d0ae05d54f29e5ecb490d1e773f
+oid sha256:324e96f848e0027001b5f53f4e252e1c48db22d7bfb35ecbd9639cf29853f9aa
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:427255595d637574231c22a2a7f3c4ee6bae76e92178fb1670427b2da125ed1d
+oid sha256:07ceece4cc2f27dbfd23c914ff92bec9387b22dbbebb8fe6e2fdd43d119365ac
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761058042.4142604,
-  "trained_at_readable": "2025-10-21 14:47:22",
+  "trained_at": 1761061599.380218,
+  "trained_at_readable": "2025-10-21 15:46:39",
   "samples_this_session": 100,
   "new_rows_this_session": 100,
-  "trained_rows_total": 3316,
-  "total_db_rows": 237996,
-  "percentage": 1.3933007277433234,
+  "trained_rows_total": 3416,
+  "total_db_rows": 238011,
+  "percentage": 1.435227783589834,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05