Training update: 122,551/240,531 rows (50.95%) | +750 new @ 2025-10-28 13:06:48

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 **49.90%** of planned data.
+- Status: **Early version** — trained on **50.95%** 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 (49.90%) 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 (50.95%) 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**: 240,527
-- **Rows processed (cumulative)**: 120,021 (49.90%)
-- **Training date**: 2025-10-28 12:06:33
+- **Total database rows**: 240,531
+- **Rows processed (cumulative)**: 122,551 (50.95%)
+- **Training date**: 2025-10-28 13:06:48
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cb14d5355e8fc7b28135e86f9ae326c99595e222a4cf28080f4a1309703d505
+oid sha256:b99b022a2745dd48655ce494f7397e4ab40b7d42a97e7a650396403bc84c1779
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c74be4330746d295b42f323acc0069d6190f061db231704124957517b8034ae
+oid sha256:8dd0eff7d186ecf0dd3b6efd8849f856825919c84066b07e3c99f322d3a0f4da
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761653193.9023457,
-  "trained_at_readable": "2025-10-28 12:06:33",
-  "samples_this_session": 2999,
-  "new_rows_this_session": 2531,
-  "trained_rows_total": 120021,
-  "total_db_rows": 240527,
-  "percentage": 49.899179717869515,
+  "trained_at": 1761656808.0219753,
+  "trained_at_readable": "2025-10-28 13:06:48",
+  "samples_this_session": 3000,
+  "new_rows_this_session": 750,
+  "trained_rows_total": 122551,
+  "total_db_rows": 240531,
+  "percentage": 50.95018937267961,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,