Training update: 30,934/238,725 rows (12.96%) | +331 new @ 2025-10-23 19:53:04

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 **11.72%** of planned data.
+- Status: **Early version** — trained on **12.96%** 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 (11.72%) 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 (12.96%) 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**: 238,710
-- **Rows processed (cumulative)**: 27,973 (11.72%)
-- **Training date**: 2025-10-23 18:32:18
+- **Total database rows**: 238,725
+- **Rows processed (cumulative)**: 30,934 (12.96%)
+- **Training date**: 2025-10-23 19:53:04
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b858d03c0a32120214c3c1a0cdbed51d9a7c04ae20bbf6eeb5d5bf260d8dac02
+oid sha256:62c552e0d46223b613afbf08609972588f6728e9c181ccb10ac0aee3e6d1fc1b
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fa7811e3bef6de24cbac2aaeae678e4c70fa310817d83f7d50dc88851d5b6cc
+oid sha256:6d296e3b1f4c4cba9e074ee1b966e12da4515c071ed49300997820acc70de16c
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761244338.9756114,
-  "trained_at_readable": "2025-10-23 18:32:18",
-  "samples_this_session": 5116,
-  "new_rows_this_session": 2963,
-  "trained_rows_total": 27973,
-  "total_db_rows": 238710,
-  "percentage": 11.718403083239076,
+  "trained_at": 1761249184.45561,
+  "trained_at_readable": "2025-10-23 19:53:04",
+  "samples_this_session": 5008,
+  "new_rows_this_session": 331,
+  "trained_rows_total": 30934,
+  "total_db_rows": 238725,
+  "percentage": 12.958006073934444,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,