Training update: 85,034/239,488 rows (35.51%) | +335 new @ 2025-10-25 22:28:21

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 **34.72%** of planned data.
+- Status: **Early version** — trained on **35.51%** 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 (34.72%) 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 (35.51%) 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**: 239,461
-- **Rows processed (cumulative)**: 83,138 (34.72%)
-- **Training date**: 2025-10-25 21:27:23
+- **Total database rows**: 239,488
+- **Rows processed (cumulative)**: 85,034 (35.51%)
+- **Training date**: 2025-10-25 22:28:21
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cc1947063a9a1f46782d62acd829b83e6d05b8ae39a81fd213dfe5c50b3c39c
+oid sha256:eae3f33de11a97c9e8bc8971a2f6f5c643504b36f22b4162389df4fef26108e1
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02271fd5050c9f0396be94f8024101caeea98c636252cd2e75b77f2c9df227e7
+oid sha256:0180df554be714e8bebf27f185b256227b076e55558ecfad7822046c3bd78883
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761427643.019707,
-  "trained_at_readable": "2025-10-25 21:27:23",
-  "samples_this_session": 5001,
-  "new_rows_this_session": 1899,
-  "trained_rows_total": 83138,
-  "total_db_rows": 239461,
-  "percentage": 34.71880598510822,
+  "trained_at": 1761431301.2615037,
+  "trained_at_readable": "2025-10-25 22:28:21",
+  "samples_this_session": 4988,
+  "new_rows_this_session": 335,
+  "trained_rows_total": 85034,
+  "total_db_rows": 239488,
+  "percentage": 35.50658070550507,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,