Training update: 145,758/241,094 rows (60.46%) | +389 new @ 2025-11-01 20:18:45

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**: 241,070
-- **Rows processed (cumulative)**: 145,749 (60.46%)
-- **Training date**: 2025-11-01 16:46:34
+- **Total database rows**: 241,094
+- **Rows processed (cumulative)**: 145,758 (60.46%)
+- **Training date**: 2025-11-01 20:18:45
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abda68ad57e5483ed8c3ce14ba93237298bdb04fe18730af737425d0b8083400
+oid sha256:d61c9aac1585f8979ad27395d255e5868a3ebeda175171dd7a49c16011482c46
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca3bf8775071ea03c35b4339152d237d84b2177bad53a04ea13fe0e5cb785b7d
+oid sha256:fa223db2d4e6cb512be578bd4fbb9ceac81f8ddd861bae464850bc85462d75a5
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1762015594.5029786,
-  "trained_at_readable": "2025-11-01 16:46:34",
-  "samples_this_session": 1584,
-  "new_rows_this_session": 9,
-  "trained_rows_total": 145749,
-  "total_db_rows": 241070,
-  "percentage": 60.45920272120131,
+  "trained_at": 1762028325.9490368,
+  "trained_at_readable": "2025-11-01 20:18:45",
+  "samples_this_session": 1204,
+  "new_rows_this_session": 389,
+  "trained_rows_total": 145758,
+  "total_db_rows": 241094,
+  "percentage": 60.45691721901001,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,