Training update: 145,693/241,061 rows (60.44%) | +56 new @ 2025-11-01 15:31:18

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**: 241,057
-- **Rows processed (cumulative)**: 145,684 (60.44%)
-- **Training date**: 2025-11-01 15:14:10
+- **Total database rows**: 241,061
+- **Rows processed (cumulative)**: 145,693 (60.44%)
+- **Training date**: 2025-11-01 15:31:18
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:649cbbe95aeedfd9ae30e64c8cda344d7805c39ef80684167a82510238333d2c
+oid sha256:2e9921e203b66e9e776a4fa0ca182bb2f0c3b31d28fda093914dfd4af31910c6
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9987d3822d95c433e081670d59daf766f36cacd709d8ac2b9ae0e4574a08fb8b
+oid sha256:5fd47c3a8a11153594543d467fd2274acb4d20501bd3b7aa6b70253ebf20b0c2
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1762010050.4914122,
-  "trained_at_readable": "2025-11-01 15:14:10",
-  "samples_this_session": 1882,
-  "new_rows_this_session": 9,
-  "trained_rows_total": 145684,
-  "total_db_rows": 241057,
-  "percentage": 60.43549865799375,
+  "trained_at": 1762011078.1206753,
+  "trained_at_readable": "2025-11-01 15:31:18",
+  "samples_this_session": 1500,
+  "new_rows_this_session": 56,
+  "trained_rows_total": 145693,
+  "total_db_rows": 241061,
+  "percentage": 60.438229327846486,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,