Training update: 99,090/239,716 rows (41.34%) | +2491 new @ 2025-10-26 09:42:26

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 **39.49%** of planned data.
+- Status: **Early version** — trained on **41.34%** 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 (39.49%) 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 (41.34%) 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**: 239,680
-- **Rows processed (cumulative)**: 94,646 (39.49%)
-- **Training date**: 2025-10-26 06:34:53
+- **Total database rows**: 239,716
+- **Rows processed (cumulative)**: 99,090 (41.34%)
+- **Training date**: 2025-10-26 09:42:26
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d2f4e16580607d058e0c2f6d809070f879c900f6220498bad524c26a655f3d0
+oid sha256:37ab1c6210a5b024038b439502569c86dd3e5ea10357729d541110770195ff45
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:556eddc82b77a570273c32fff2dc581f555ae58e3ab5552dca2341dd0a14d57c
+oid sha256:af9e9e7ae746ab1d373b856e3426b71b267407560bbbd84c4b36d41051c30bbb
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761460493.9988525,
-  "trained_at_readable": "2025-10-26 06:34:53",
-  "samples_this_session": 4999,
-  "new_rows_this_session": 4678,
-  "trained_rows_total": 94646,
-  "total_db_rows": 239680,
-  "percentage": 39.48848464619493,
+  "trained_at": 1761471746.7785783,
+  "trained_at_readable": "2025-10-26 09:42:26",
+  "samples_this_session": 4925,
+  "new_rows_this_session": 2491,
+  "trained_rows_total": 99090,
+  "total_db_rows": 239716,
+  "percentage": 41.336414757463,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,