Training update: 161,076/163,729 rows (98.38%) | +6 new @ 2025-11-11 02:00:47

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**: 163,718
-- **Rows processed (cumulative)**: 161,072 (98.38%)
-- **Training date**: 2025-11-11 01:03:42
+- **Total database rows**: 163,729
+- **Rows processed (cumulative)**: 161,076 (98.38%)
+- **Training date**: 2025-11-11 02:00:47
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d809c8703693877a9cfa35b677a89f5ef871f990ef1035eb2aaabf3ffef8d409
+oid sha256:74d8ca1463c1a0de878c6fc935349d0dddbd34319fd13f90f763be3ec15fe520
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c60a622c634eeeda43b5ba15a8acb44a97ca9302b8e968c17e90ee5de97ca478
+oid sha256:e40072afddbc7f8b54297fa8a6a86fc39ded8e82788647f0ab2d412b8de84e86
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1762823022.502494,
-  "trained_at_readable": "2025-11-11 01:03:42",
-  "samples_this_session": 1341,
-  "new_rows_this_session": 4,
-  "trained_rows_total": 161072,
-  "total_db_rows": 163718,
-  "percentage": 98.38380630107868,
+  "trained_at": 1762826447.746993,
+  "trained_at_readable": "2025-11-11 02:00:47",
+  "samples_this_session": 1538,
+  "new_rows_this_session": 6,
+  "trained_rows_total": 161076,
+  "total_db_rows": 163729,
+  "percentage": 98.37963952629039,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,