Training update: 163,816/335,866 rows (48.77%) | +991 new @ 2026-03-15 17:22:20

README.md

@@ -76,8 +76,8 @@ Since cybersecurity data often contains lengthy alert descriptions and execution
 
 ### Training Data
 - **Total database rows**: 335,866
-- **Rows processed (cumulative)**: 163,814 (48.77%)
-- **Training date**: 2026-03-14 17:26:47
+- **Rows processed (cumulative)**: 163,816 (48.77%)
+- **Training date**: 2026-03-15 17:22:20
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7d7286417d3c5f2ba8c3a09c415fa6af3260a51519987b8eff6f051c40ccf56
+oid sha256:b1ff239bc6a7bcabd5f15674b312395a289b90f64d824dbbb5b8e2f97bb1d641
 size 17671552

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1773509207.672224,
-  "trained_at_readable": "2026-03-14 17:26:47",
-  "samples_this_session": 890,
-  "new_rows_this_session": 2,
-  "trained_rows_total": 163814,
+  "trained_at": 1773595340.8177426,
+  "trained_at_readable": "2026-03-15 17:22:20",
+  "samples_this_session": 1000,
+  "new_rows_this_session": 991,
+  "trained_rows_total": 163816,
   "total_db_rows": 335866,
-  "percentage": 48.77361805005568,
+  "percentage": 48.77421352563225,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,