Training update: 153,055/241,626 rows (63.34%) | +14 new @ 2025-11-05 04:30:05

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 **63.31%** of planned data.
+- Status: **Early version** — trained on **63.34%** 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 (63.31%) 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 (63.34%) 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**: 241,601
-- **Rows processed (cumulative)**: 152,957 (63.31%)
-- **Training date**: 2025-11-05 01:07:36
+- **Total database rows**: 241,626
+- **Rows processed (cumulative)**: 153,055 (63.34%)
+- **Training date**: 2025-11-05 04:30:05
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70ef68712170be27f94521906b33eef8374afb7badcdb53ce498cf7e07e75c37
+oid sha256:9efc497ff7a0958d08a5be1aab16f7aa9945c1f6f566ee1fc0c0e58e9f84fd12
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1cd9783825ea31044407771fed350ba1278ed500d1ab9cc0562bb4c3ed47a42
+oid sha256:a7e2eec58b3af5074a8d73e4029d483e1fec1b2e31ddc26df7f089ade7c4990d
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1762304856.034139,
-  "trained_at_readable": "2025-11-05 01:07:36",
-  "samples_this_session": 1500,
-  "new_rows_this_session": 99,
-  "trained_rows_total": 152957,
-  "total_db_rows": 241601,
-  "percentage": 63.3097545126055,
+  "trained_at": 1762317005.448509,
+  "trained_at_readable": "2025-11-05 04:30:05",
+  "samples_this_session": 1143,
+  "new_rows_this_session": 14,
+  "trained_rows_total": 153055,
+  "total_db_rows": 241626,
+  "percentage": 63.34376267454661,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,