Training update: 149,460/241,343 rows (61.93%) | +76 new @ 2025-11-03 04:05:21

README.md

@@ -25,7 +25,7 @@ pipeline_tag: fill-mask
 - Model type: fine-tuned lightweight BERT variant  
 - Languages: English & Indonesia
 - Finetuned from: `boltuix/bert-micro`
-- Status: **Early version** — trained on **61.88%** of planned data.
+- Status: **Early version** — trained on **61.93%** of planned data.
 
 **Model sources**  
 - Base model: [boltuix/bert-micro](https://huggingface.co/boltuix/bert-micro)
@@ -51,7 +51,7 @@ You can use this model to classify cybersecurity-related text — for example, w
 - Early classification of SIEM alert & events.
 
 ## 3. Bias, Risks, and Limitations 
-Because the model is based on a small subset (61.88%) 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 (61.93%) 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.**
 
@@ -75,9 +75,9 @@ Since cybersecurity data often contains lengthy alert descriptions and execution
 - **LR scheduler**: Linear with warmup
 
 ### Training Data
-- **Total database rows**: 241,330
-- **Rows processed (cumulative)**: 149,331 (61.88%)
-- **Training date**: 2025-11-03 03:02:37
+- **Total database rows**: 241,343
+- **Rows processed (cumulative)**: 149,460 (61.93%)
+- **Training date**: 2025-11-03 04:05:21
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:925c0873f96cb5c74caae210dd9095a135c9a72ec4359d660c82a1de31ea8b59
+oid sha256:f50334b9480073e824c809c33b7ccabc249d5f39db706877140fb92f8bc7a176
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dce111d17489900b1eddaa06ec5fdf43c26a8ccead36506f8e6d41a27d95510a
+oid sha256:08a33babc00bfe9c30c205f83e9551a5cfc38c245284639bf306df12e3b49891
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1762138957.5496552,
-  "trained_at_readable": "2025-11-03 03:02:37",
-  "samples_this_session": 1492,
-  "new_rows_this_session": 129,
-  "trained_rows_total": 149331,
-  "total_db_rows": 241330,
-  "percentage": 61.87834086106162,
+  "trained_at": 1762142721.1101353,
+  "trained_at_readable": "2025-11-03 04:05:21",
+  "samples_this_session": 1500,
+  "new_rows_this_session": 76,
+  "trained_rows_total": 149460,
+  "total_db_rows": 241343,
+  "percentage": 61.92845866671086,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,