Training update: 4,916/238,208 rows (2.06%) | +100 new @ 2025-10-22 07:57:31

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 **2.02%** of planned data.
+- Status: **Early version** — trained on **2.06%** 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 (2.02%) 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 (2.06%) 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**: 4,816 / 238,196 (2.02%)
+- **Trained records**: 4,916 / 238,208 (2.06%)
 - **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:d9d3121317e353087773e0db02f008a842f661e7a8493a275be9e4e8075e1d9d
+oid sha256:20f629088173d8a28bccf1f87adf9de0048695ffc01646091b042655fa9b0c90
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0795cc46f141dd4acbf6368024e715bfab653354928d6ad5a0a084a0302a962
+oid sha256:a438a26a3cea30686f8c8e79d376f95f779366deda539326d6ab1dfcdf84c032
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761116343.042544,
-  "trained_at_readable": "2025-10-22 06:59:03",
-  "samples_this_session": 2099,
+  "trained_at": 1761119851.7242322,
+  "trained_at_readable": "2025-10-22 07:57:31",
+  "samples_this_session": 1776,
   "new_rows_this_session": 100,
-  "trained_rows_total": 4816,
-  "total_db_rows": 238196,
-  "percentage": 2.021864347008346,
+  "trained_rows_total": 4916,
+  "total_db_rows": 238208,
+  "percentage": 2.063742611499194,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05