Training update: 131,151/240,589 rows (54.51%) | +586 new @ 2025-10-29 10:03:02

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**: 240,588
-- **Rows processed (cumulative)**: 131,135 (54.51%)
-- **Training date**: 2025-10-29 09:25:31
+- **Total database rows**: 240,589
+- **Rows processed (cumulative)**: 131,151 (54.51%)
+- **Training date**: 2025-10-29 10:03:02
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8b89ae78310a5b388430c4db8d66e7b4f23673ff46236038153dddfa9617345
+oid sha256:d78d2418861d05ad41ffc5ee411c9413cc3c18249ddb7ec781008e80600cade9
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94419b756e805d7e4684846f1de27953ed8eb08d0a00fea53a2d3e0dcec95589
+oid sha256:ddde6324921bd25aad8ff4dd167c0313b594a2a9dabe684ef97d64f18c8124df
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761729931.0954366,
-  "trained_at_readable": "2025-10-29 09:25:31",
-  "samples_this_session": 1907,
-  "new_rows_this_session": 16,
-  "trained_rows_total": 131135,
-  "total_db_rows": 240588,
-  "percentage": 54.506043526692935,
+  "trained_at": 1761732182.4046257,
+  "trained_at_readable": "2025-10-29 10:03:02",
+  "samples_this_session": 2006,
+  "new_rows_this_session": 586,
+  "trained_rows_total": 131151,
+  "total_db_rows": 240589,
+  "percentage": 54.512467319786026,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,