Training update: 6,243/238,379 rows (2.62%) | +100 new @ 2025-10-22 21:46:55

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 **2.58%** of planned data.
+- Status: **Early version** — trained on **2.62%** 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 (2.58%) 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 (2.62%) 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**: 6,147 / 238,361 (2.58%)
+- **Trained records**: 6,243 / 238,379 (2.62%)
 - **Learning rate**: 5e-05
 - **Epochs**: 3
 - **Batch size**: 16

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26e64ba2c61270d13b4d5d3c3812ab7e961d4c8ad4f4bc1023469b05f85b7038
+oid sha256:27dc4ff420e0c33ac93af6ca4e381979c8c4de072d70c2d20eae195763920fcf
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc05ea73af9a34c4cc88fb0ff461f7b58d7870d39c99883ecf8a52a8ebc2e729
+oid sha256:a990743b85cb006de398748e1bf1a61ec8076f38973ec92396e8482626a7fdbe
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761166147.2372897,
-  "trained_at_readable": "2025-10-22 20:49:07",
-  "samples_this_session": 397,
+  "trained_at": 1761169615.6602223,
+  "trained_at_readable": "2025-10-22 21:46:55",
+  "samples_this_session": 100,
   "new_rows_this_session": 100,
-  "trained_rows_total": 6147,
-  "total_db_rows": 238361,
-  "percentage": 2.578861474821804,
+  "trained_rows_total": 6243,
+  "total_db_rows": 238379,
+  "percentage": 2.6189387487991813,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05