Training update: 151,888/241,494 rows (62.90%) | +51 new @ 2025-11-04 04:08:20

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 **62.87%** of planned data.
+- Status: **Early version** — trained on **62.90%** 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 (62.87%) 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 (62.90%) 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**: 241,487
-- **Rows processed (cumulative)**: 151,828 (62.87%)
-- **Training date**: 2025-11-04 03:09:45
+- **Total database rows**: 241,494
+- **Rows processed (cumulative)**: 151,888 (62.90%)
+- **Training date**: 2025-11-04 04:08:20
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7420c8f3f51c9bd8ea91a643392bcdc12ef134279304a4a95424eb3f0d02ff67
+oid sha256:e9b87d83ff7b14bb6f30cef021d4d9bd1eeb75249d4bae0503ef359943ced726
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19eb1835ee612ca9c4b19284295fbdb3b2dccc47598cc71ef4fcc9a9bd588ad0
+oid sha256:10df022ee1eeac72dc7523f3d7af36341bf08e5149cfb877aac180d828826ae6
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1762225785.4628348,
-  "trained_at_readable": "2025-11-04 03:09:45",
-  "samples_this_session": 1501,
-  "new_rows_this_session": 60,
-  "trained_rows_total": 151828,
-  "total_db_rows": 241487,
-  "percentage": 62.872121480659416,
+  "trained_at": 1762229300.3653386,
+  "trained_at_readable": "2025-11-04 04:08:20",
+  "samples_this_session": 1779,
+  "new_rows_this_session": 51,
+  "trained_rows_total": 151888,
+  "total_db_rows": 241494,
+  "percentage": 62.89514439282136,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,