Training update: 161,802/164,043 rows (98.63%) | +1019 new @ 2025-11-12 10:16:01

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**: 164,041
-- **Rows processed (cumulative)**: 161,787 (98.63%)
-- **Training date**: 2025-11-12 09:50:07
+- **Total database rows**: 164,043
+- **Rows processed (cumulative)**: 161,802 (98.63%)
+- **Training date**: 2025-11-12 10:16:01
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c344286b5e67a552f8328978ab9bc3b02136bb73b0473b9c411bf3da3b2e865
+oid sha256:870e17a14e304365550bc0b58afb5a00ade83939c9d8541a5bb7eea239760e09
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cfbb0ff17e332b77aa1e4f74fe77db6a3926ea27ba45d0cff0e33737637f883
+oid sha256:5f3bfffa55ac0a1238e32294a79cd935b14e7189ff2f0fbac34c5586d6ed8302
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1762941007.9919815,
-  "trained_at_readable": "2025-11-12 09:50:07",
-  "samples_this_session": 1540,
-  "new_rows_this_session": 15,
-  "trained_rows_total": 161787,
-  "total_db_rows": 164041,
-  "percentage": 98.62595326778062,
+  "trained_at": 1762942561.2009058,
+  "trained_at_readable": "2025-11-12 10:16:01",
+  "samples_this_session": 1602,
+  "new_rows_this_session": 1019,
+  "trained_rows_total": 161802,
+  "total_db_rows": 164043,
+  "percentage": 98.63389477149283,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,