Training update: 6,047/238,361 rows (2.54%) | +100 new @ 2025-10-22 19:48:30

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 **2.50%** of planned data.
+- Status: **Early version** — trained on **2.54%** 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 (2.50%) 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 (2.54%) 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**: 5,947 / 238,352 (2.50%)
+- **Trained records**: 6,047 / 238,361 (2.54%)
 - **Learning rate**: 5e-05
 - **Epochs**: 3
 - **Batch size**: 16

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25285c65ca2e8bb5da4dbd647a6602fd7cc3e08dc18439f6670fd43795c4f9a2
+oid sha256:cfea31dbc2354a647a2c52486c4bc63117dce3990885cc934d56956db51d3c5c
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b36eacc69f9cd4b33e11792ccec4c06e149262649b2dd10a5a38c631611b480
+oid sha256:835f0ac04fe8fee99bd5470bf78c93832fdf252a6135263a58ce7d93571e0009
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761158802.018987,
-  "trained_at_readable": "2025-10-22 18:46:42",
-  "samples_this_session": 100,
+  "trained_at": 1761162510.4223697,
+  "trained_at_readable": "2025-10-22 19:48:30",
+  "samples_this_session": 205,
   "new_rows_this_session": 100,
-  "trained_rows_total": 5947,
-  "total_db_rows": 238352,
-  "percentage": 2.4950493387930455,
+  "trained_rows_total": 6047,
+  "total_db_rows": 238361,
+  "percentage": 2.5369083029522446,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05