Training update: 133,994/240,604 rows (55.69%) | +5 new @ 2025-10-29 16:27:34

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 **55.68%** of planned data.
+- Status: **Early version** — trained on **55.69%** 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 (55.68%) 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 (55.69%) 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**: 240,601
-- **Rows processed (cumulative)**: 133,976 (55.68%)
-- **Training date**: 2025-10-29 15:20:30
+- **Total database rows**: 240,604
+- **Rows processed (cumulative)**: 133,994 (55.69%)
+- **Training date**: 2025-10-29 16:27:34
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29e5d6ba23289e0cdca065d435685aac3f01e3706c09183fd5fd9d11b53e3630
+oid sha256:a50635d393a4cc3fed5de0770fad3b074c5cedd50bb44499092a848918b5f647
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c776832b6d096c8e17630cf8805615e5c7c757391d3736117226789ab2c4b491
+oid sha256:270ff26da987430ed62e236e477374bbf8043e69f6a4d442c3695bbabcb8c1cc
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761751230.1751382,
-  "trained_at_readable": "2025-10-29 15:20:30",
-  "samples_this_session": 2290,
-  "new_rows_this_session": 18,
-  "trained_rows_total": 133976,
-  "total_db_rows": 240601,
-  "percentage": 55.683891588148015,
+  "trained_at": 1761755254.3836477,
+  "trained_at_readable": "2025-10-29 16:27:34",
+  "samples_this_session": 2063,
+  "new_rows_this_session": 5,
+  "trained_rows_total": 133994,
+  "total_db_rows": 240604,
+  "percentage": 55.690678459210986,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,