Training update: 141,997/240,697 rows (58.99%) | +542 new @ 2025-10-31 03:44:58

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 **58.97%** of planned data.
+- Status: **Early version** — trained on **58.99%** 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 (58.97%) 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 (58.99%) 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**: 240,686
-- **Rows processed (cumulative)**: 141,932 (58.97%)
-- **Training date**: 2025-10-31 02:08:58
+- **Total database rows**: 240,697
+- **Rows processed (cumulative)**: 141,997 (58.99%)
+- **Training date**: 2025-10-31 03:44:58
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c15ec030beb15863b4c38fddfda42625e79c52a1301558808dfeb174b424eae2
+oid sha256:7cc5070ccbd7f74a7c18671e1c49fc0bf0883eeba898cac981d4fda96f2dd168
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6c265d2b715d0a1b41b740d3550cf2707e0a630bf71d1a2b5f84e50c54cdb16
+oid sha256:24a10ceb262fe69e428e740f8e2522ae261b994fa89a9fe99f91b358f276d8c3
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761876538.048882,
-  "trained_at_readable": "2025-10-31 02:08:58",
-  "samples_this_session": 2509,
-  "new_rows_this_session": 65,
-  "trained_rows_total": 141932,
-  "total_db_rows": 240686,
-  "percentage": 58.96977805107069,
+  "trained_at": 1761882298.3396115,
+  "trained_at_readable": "2025-10-31 03:44:58",
+  "samples_this_session": 1589,
+  "new_rows_this_session": 542,
+  "trained_rows_total": 141997,
+  "total_db_rows": 240697,
+  "percentage": 58.99408800275866,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,