Training update: 153,489/241,654 rows (63.52%) | +32 new @ 2025-11-05 10:12:41

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 **63.46%** of planned data.
+- Status: **Early version** — trained on **63.52%** 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 (63.46%) 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 (63.52%) 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**: 241,650
-- **Rows processed (cumulative)**: 153,349 (63.46%)
-- **Training date**: 2025-11-05 09:06:06
+- **Total database rows**: 241,654
+- **Rows processed (cumulative)**: 153,489 (63.52%)
+- **Training date**: 2025-11-05 10:12:41
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30088c3d61b1d32ccf6833222ebb8ec0a140616c5f9045424a0192a96971333b
+oid sha256:ed2747eb84180d09f3581f715ffbdce69c8f9927d1b91b160eb1ccc115c487ed
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ee550335387df9a993f0c3dec9e07093345b5686ef9c4ad0b9bd0af2bbc7c68
+oid sha256:47046ef7cb7c029456c1fd7f5488a7a5ab5a44c08934090eeb0dff9b049db956
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1762333566.4803362,
-  "trained_at_readable": "2025-11-05 09:06:06",
-  "samples_this_session": 1633,
-  "new_rows_this_session": 142,
-  "trained_rows_total": 153349,
-  "total_db_rows": 241650,
-  "percentage": 63.4591351127664,
+  "trained_at": 1762337561.5791628,
+  "trained_at_readable": "2025-11-05 10:12:41",
+  "samples_this_session": 1401,
+  "new_rows_this_session": 32,
+  "trained_rows_total": 153489,
+  "total_db_rows": 241654,
+  "percentage": 63.516018770639015,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,