Training update: 144,818/240,898 rows (60.12%) | +14 new @ 2025-11-01 08:15:37

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**: 240,889
-- **Rows processed (cumulative)**: 144,813 (60.12%)
-- **Training date**: 2025-11-01 07:45:18
+- **Total database rows**: 240,898
+- **Rows processed (cumulative)**: 144,818 (60.12%)
+- **Training date**: 2025-11-01 08:15:37
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a844673428409e543983c372627d5f992fa6f8a3914255b8cacf84039007ccec
+oid sha256:b8d969124a8d6c13e583aba8df6b5ed264816af44a7d101c5ae8f0e1722c1bd9
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:128f00e255942745b762e3668246e9cbd3013351593ca9e81432b9c4f937e2df
+oid sha256:c8f828ad3982a16399ba2e17c5e183e96f2792abfb782b0f5976a40fae09319a
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761983118.6748946,
-  "trained_at_readable": "2025-11-01 07:45:18",
-  "samples_this_session": 1447,
-  "new_rows_this_session": 5,
-  "trained_rows_total": 144813,
-  "total_db_rows": 240889,
-  "percentage": 60.11607005716326,
+  "trained_at": 1761984937.657739,
+  "trained_at_readable": "2025-11-01 08:15:37",
+  "samples_this_session": 1573,
+  "new_rows_this_session": 14,
+  "trained_rows_total": 144818,
+  "total_db_rows": 240898,
+  "percentage": 60.11589967538128,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,