Training update: 4,216/238,116 rows (1.77%) | +100 new @ 2025-10-22 00:48:08

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 **1.73%** of planned data.
+- Status: **Early version** — trained on **1.77%** 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 (1.73%) 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 (1.77%) 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**: 4,116 / 238,106 (1.73%)
+- **Trained records**: 4,216 / 238,116 (1.77%)
 - **Learning rate**: 5e-05
 - **Epochs**: 3
 - **Batch size**: 16

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2334e0587a89ce8c8fca791003a242d5c591bf560cbd546d299ad9f0882aa45d
+oid sha256:4bb2a121dbca2e46b7c63532347c772d6d3febdef2cb41c5a8f73f6d89e0d90e
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e213f5fba067ce7aed5ab8b0dbbcb577da99cdaaebdf9c44bc1b8e3025fd55f
+oid sha256:3feaefd4e84fc7e3ccc7ba1d108377e9350220514bcd07c9324ce6b67e36f31c
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761091232.1250167,
-  "trained_at_readable": "2025-10-22 00:00:32",
-  "samples_this_session": 2060,
+  "trained_at": 1761094088.7016032,
+  "trained_at_readable": "2025-10-22 00:48:08",
+  "samples_this_session": 160,
   "new_rows_this_session": 100,
-  "trained_rows_total": 4116,
-  "total_db_rows": 238106,
-  "percentage": 1.7286418653876847,
+  "trained_rows_total": 4216,
+  "total_db_rows": 238116,
+  "percentage": 1.7705656066790976,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05