Training update: 6,637/238,430 rows (2.78%) | +100 new @ 2025-10-23 01:52:36

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 **2.74%** of planned data.
+- Status: **Early version** — trained on **2.78%** 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 (2.74%) 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 (2.78%) 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**: 6,537 / 238,415 (2.74%)
+- **Trained records**: 6,637 / 238,430 (2.78%)
 - **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:f4760f9dd70efa6dec61d2af1684f9b0b9610e84e2029907e9caae944ab41772
+oid sha256:d499c86d2c0ea3b54f75177498a11c5825510248cb35dd5973adec65d52440d6
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bca474218067de6683c8f24d214d03c7c3aa5756a7c651d9f813db1a9bf21133
+oid sha256:32e79d532c7f5a7b4ae209d8f8bf38545aa96797d1142502dfe93c3287200d0a
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761180505.4150164,
-  "trained_at_readable": "2025-10-23 00:48:25",
-  "samples_this_session": 400,
+  "trained_at": 1761184356.7112105,
+  "trained_at_readable": "2025-10-23 01:52:36",
+  "samples_this_session": 956,
   "new_rows_this_session": 100,
-  "trained_rows_total": 6537,
-  "total_db_rows": 238415,
-  "percentage": 2.741857685128872,
+  "trained_rows_total": 6637,
+  "total_db_rows": 238430,
+  "percentage": 2.783626221532525,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05