Training update: 33,961/238,761 rows (14.22%) | +521 new @ 2025-10-23 22:25:33

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 **13.30%** of planned data.
+- Status: **Early version** — trained on **14.22%** 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 (13.30%) 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 (14.22%) 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**: 238,752
-- **Rows processed (cumulative)**: 31,751 (13.30%)
-- **Training date**: 2025-10-23 21:39:20
+- **Total database rows**: 238,761
+- **Rows processed (cumulative)**: 33,961 (14.22%)
+- **Training date**: 2025-10-23 22:25:33
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a1ebc20d679ce88ee28bd5a1515840f46e90f1389e9fd698c56e9eee3e4feec
+oid sha256:a0e2ea4d980a51fba23abcd110041bbd124dbac944d98e5c1c159bf34d474449
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c46d47e9438f392e202f04157772741702b3434922b99503fd7fbe1d9918f67f
+oid sha256:76621ee669aa099c889512a3c2ab983183cac57f0a69ea905bd2f4870021ce6f
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761255560.2094407,
-  "trained_at_readable": "2025-10-23 21:39:20",
-  "samples_this_session": 5010,
-  "new_rows_this_session": 2214,
-  "trained_rows_total": 31751,
-  "total_db_rows": 238752,
-  "percentage": 13.298736764508778,
+  "trained_at": 1761258333.378663,
+  "trained_at_readable": "2025-10-23 22:25:33",
+  "samples_this_session": 4997,
+  "new_rows_this_session": 521,
+  "trained_rows_total": 33961,
+  "total_db_rows": 238761,
+  "percentage": 14.223847278240584,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,