Training update: 2,816/237,957 rows (1.18%) | +100 new @ 2025-10-21 11:35:25

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 **1.14%** of planned data.
+- Status: **Early version** — trained on **1.18%** 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 (1.14%) 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 (1.18%) 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.
@@ -62,7 +62,7 @@ predicted_class = logits.argmax(dim=-1).item()
 ```
 
 ## 5. Training Details
-- **Trained records**: 2,716 / 237,957 (1.14%)
+- **Trained records**: 2,816 / 237,957 (1.18%)
 - **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:a80a710dad2196946b67c1658b8588883fa1ac6ea411a59a2a50f219eb673981
+oid sha256:e9e3347af98dfbfe1a40e863ac25d6d1880a2b31ead3e65af349605c16374c8e
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6965cd18c5a43fb1e0a484c7d9186fc21266e64657bcda0c47bd52d155e51e23
+oid sha256:fbec7b30cda87e9c8cce1556f98bc89cdc670d545874f2a1142b97be4daa527d
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761046312.2121968,
-  "trained_at_readable": "2025-10-21 11:31:52",
+  "trained_at": 1761046525.349451,
+  "trained_at_readable": "2025-10-21 11:35:25",
   "samples_this_session": 100,
   "new_rows_this_session": 100,
-  "trained_rows_total": 2716,
+  "trained_rows_total": 2816,
   "total_db_rows": 237957,
-  "percentage": 1.141382686787949,
+  "percentage": 1.1834070861542212,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05