Training update: 71,837/239,228 rows (30.03%) | +712 new @ 2025-10-25 07:55:13

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 **28.54%** of planned data.
+- Status: **Early version** — trained on **30.03%** 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 (28.54%) 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 (30.03%) 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**: 239,222
-- **Rows processed (cumulative)**: 68,278 (28.54%)
-- **Training date**: 2025-10-25 06:35:46
+- **Total database rows**: 239,228
+- **Rows processed (cumulative)**: 71,837 (30.03%)
+- **Training date**: 2025-10-25 07:55:13
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ff435d5a70a2d938155681bef682ceed17590bd4d31b4884b64c21c8d95a428
+oid sha256:4759ab190acc4583ef931bd0327f5b01503767bccfe90d06aa9a9c3b42d4d680
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:328e56502898105214684ca9ff2397a399faf0647b3b9b1ff7a868ef3b8f62ab
+oid sha256:4fce00991e09ebe4234e8f7fb333dcf83ac402ec03d7c3c89ea11e2c9607ee9b
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761374146.0584118,
-  "trained_at_readable": "2025-10-25 06:35:46",
-  "samples_this_session": 5253,
-  "new_rows_this_session": 3616,
-  "trained_rows_total": 68278,
-  "total_db_rows": 239222,
-  "percentage": 28.54168930951167,
+  "trained_at": 1761378913.401753,
+  "trained_at_readable": "2025-10-25 07:55:13",
+  "samples_this_session": 5001,
+  "new_rows_this_session": 712,
+  "trained_rows_total": 71837,
+  "total_db_rows": 239228,
+  "percentage": 30.028675573093448,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,