Training update: 156,415/241,863 rows (64.67%) | +74 new @ 2025-11-06 17:09:13

README.md

@@ -75,9 +75,9 @@ Since cybersecurity data often contains lengthy alert descriptions and execution
 - **LR scheduler**: Linear with warmup
 
 ### Training Data
-- **Total database rows**: 241,859
-- **Rows processed (cumulative)**: 156,410 (64.67%)
-- **Training date**: 2025-11-06 16:40:00
+- **Total database rows**: 241,863
+- **Rows processed (cumulative)**: 156,415 (64.67%)
+- **Training date**: 2025-11-06 17:09:13
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2df9e3d8c0c5a8885ced85d33db6fb599234704e8db32ebe12bc6b08d5817e8
+oid sha256:2046aadb0d836ab1e32541977f893e06e29f41c66155241f2a0d6ef367fdba2b
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3039df84eee2c6466b38827d500688e456477ad82063ee6509417bb01ecf3f30
+oid sha256:7197c66093af396a77057538c0ed58acb34185d9ecb9074578b1959a04891784
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1762447200.0691257,
-  "trained_at_readable": "2025-11-06 16:40:00",
-  "samples_this_session": 1443,
-  "new_rows_this_session": 5,
-  "trained_rows_total": 156410,
-  "total_db_rows": 241859,
-  "percentage": 64.66991098119152,
+  "trained_at": 1762448953.5587277,
+  "trained_at_readable": "2025-11-06 17:09:13",
+  "samples_this_session": 1509,
+  "new_rows_this_session": 74,
+  "trained_rows_total": 156415,
+  "total_db_rows": 241863,
+  "percentage": 64.67090873759112,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,