Training update: 156,929/241,883 rows (64.88%) | +304 new @ 2025-11-06 19:58:47

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 **64.70%** of planned data.
+- Status: **Early version** — trained on **64.88%** 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 (64.70%) 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 (64.88%) 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**: 241,877
-- **Rows processed (cumulative)**: 156,489 (64.70%)
-- **Training date**: 2025-11-06 19:03:25
+- **Total database rows**: 241,883
+- **Rows processed (cumulative)**: 156,929 (64.88%)
+- **Training date**: 2025-11-06 19:58:47
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5979a682703181609f8d58335b7f99d1bc198af635fdd1cd8cdb4c002ea1283
+oid sha256:507aaf0a2ddc5e06a34a88be7233f33496d633cab193be0993c020faea9c95e6
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18ce33a4483adebc2c0d724f9d2bd0140494ec8b667dba7abeaf4663747fa0eb
+oid sha256:272c5b56d25149558bf6037fe13fb94e11b89db8f596e8d660b569d22166b501
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1762455805.2145913,
-  "trained_at_readable": "2025-11-06 19:03:25",
-  "samples_this_session": 1610,
-  "new_rows_this_session": 440,
-  "trained_rows_total": 156489,
-  "total_db_rows": 241877,
-  "percentage": 64.69775960508854,
+  "trained_at": 1762459127.9613194,
+  "trained_at_readable": "2025-11-06 19:58:47",
+  "samples_this_session": 1426,
+  "new_rows_this_session": 304,
+  "trained_rows_total": 156929,
+  "total_db_rows": 241883,
+  "percentage": 64.87806088067371,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,