Training update: 143,277/240,760 rows (59.51%) | +41 new @ 2025-10-31 15:09:54

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**: 240,754
-- **Rows processed (cumulative)**: 143,265 (59.51%)
-- **Training date**: 2025-10-31 14:28:33
+- **Total database rows**: 240,760
+- **Rows processed (cumulative)**: 143,277 (59.51%)
+- **Training date**: 2025-10-31 15:09:54
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2846db7bb3139b1b83099e530bdf79ed7be61a04f044730dd246eafa9f871453
+oid sha256:dd54b0c2386cade9040e0aea0526dedf136e506e6af895b673639f155cfccfec
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbe131427c3ae52eb7cf9317c13cbd77c78117fb86c0f429d0394386d8ad5a28
+oid sha256:c9163be8699386610337d539cc5f0c7fcfbc633f40be383125221c91498046b4
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761920913.0535781,
-  "trained_at_readable": "2025-10-31 14:28:33",
-  "samples_this_session": 1504,
-  "new_rows_this_session": 12,
-  "trained_rows_total": 143265,
-  "total_db_rows": 240754,
-  "percentage": 59.50679947165987,
+  "trained_at": 1761923394.485243,
+  "trained_at_readable": "2025-10-31 15:09:54",
+  "samples_this_session": 1618,
+  "new_rows_this_session": 41,
+  "trained_rows_total": 143277,
+  "total_db_rows": 240760,
+  "percentage": 59.51030071440439,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,