Training update: 138,687/240,643 rows (57.63%) | +247 new @ 2025-10-30 14:05:58

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**: 240,640
-- **Rows processed (cumulative)**: 138,673 (57.63%)
-- **Training date**: 2025-10-30 13:26:27
+- **Total database rows**: 240,643
+- **Rows processed (cumulative)**: 138,687 (57.63%)
+- **Training date**: 2025-10-30 14:05:58
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfcb3402d930aca50804608c575c3c8e054a09fd809ce376218717734fc38cbf
+oid sha256:e41f118a3a931c2c705cfad3d6cbec3c968fc6cf85a2e1f0a9a7a95e8c597da0
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c30f88375ca334a9a4c35ad92134065bd3479f99b472ce4b8485eaa911cec23c
+oid sha256:1bb44a785e53dff41a420152d79b99884e11e26be4b37cc011b4774192341bb1
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761830787.8483543,
-  "trained_at_readable": "2025-10-30 13:26:27",
-  "samples_this_session": 2080,
-  "new_rows_this_session": 14,
-  "trained_rows_total": 138673,
-  "total_db_rows": 240640,
-  "percentage": 57.62674534574468,
+  "trained_at": 1761833158.3716147,
+  "trained_at_readable": "2025-10-30 14:05:58",
+  "samples_this_session": 1988,
+  "new_rows_this_session": 247,
+  "trained_rows_total": 138687,
+  "total_db_rows": 240643,
+  "percentage": 57.63184468278737,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,