Training update: 137,679/240,632 rows (57.22%) | +77 new @ 2025-10-30 09:10:46

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 **56.99%** of planned data.
+- Status: **Early version** — trained on **57.22%** 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 (56.99%) 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 (57.22%) 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**: 240,631
-- **Rows processed (cumulative)**: 137,145 (56.99%)
-- **Training date**: 2025-10-30 08:01:12
+- **Total database rows**: 240,632
+- **Rows processed (cumulative)**: 137,679 (57.22%)
+- **Training date**: 2025-10-30 09:10:46
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0245a18fc29574b852370c4ec940bcd641eca5d82cd4f4357dbc054b4fdf359
+oid sha256:cdc37ea41e844d6b5dba6f457376af19f29bd62f74e1a80635f017e030c60850
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a9ca808aea863fbf81216ee369164278b428f9f9c2e5709b949584a9b394fd1
+oid sha256:94863682f00daacf22f48a9b615aac3b3c7ea5b5841d158482b10041ee5fbe9f
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761811272.3162875,
-  "trained_at_readable": "2025-10-30 08:01:12",
-  "samples_this_session": 1998,
-  "new_rows_this_session": 534,
-  "trained_rows_total": 137145,
-  "total_db_rows": 240631,
-  "percentage": 56.99390352863929,
+  "trained_at": 1761815446.3080554,
+  "trained_at_readable": "2025-10-30 09:10:46",
+  "samples_this_session": 1888,
+  "new_rows_this_session": 77,
+  "trained_rows_total": 137679,
+  "total_db_rows": 240632,
+  "percentage": 57.21558229994348,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,