Training update: 147,386/241,215 rows (61.10%) | +81 new @ 2025-11-02 10:15:56

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**: 241,202
-- **Rows processed (cumulative)**: 147,383 (61.10%)
-- **Training date**: 2025-11-02 09:58:43
+- **Total database rows**: 241,215
+- **Rows processed (cumulative)**: 147,386 (61.10%)
+- **Training date**: 2025-11-02 10:15:56
 
 ### Post-Training Metrics
 - **Final training loss**: 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0501a130456aeb2a336349ff271487d9d7892ac67b763bf02b763241e3fa4e37
+oid sha256:04fe230e9a34e7e6fe36c0fa990fb47c45898e40cdea6877e7f60a0663b12c5b
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8607ba692f32356c51cfafd0b60ad0f5abcfa37227ca22723396037353ebeac3
+oid sha256:1ad2ad99e949e6252b6785faef65461a66abf17edf16eea1cedf9fdb066a8c2a
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1762077523.6613498,
-  "trained_at_readable": "2025-11-02 09:58:43",
-  "samples_this_session": 1341,
-  "new_rows_this_session": 3,
-  "trained_rows_total": 147383,
-  "total_db_rows": 241202,
-  "percentage": 61.103556355254106,
+  "trained_at": 1762078556.3879557,
+  "trained_at_readable": "2025-11-02 10:15:56",
+  "samples_this_session": 1548,
+  "new_rows_this_session": 81,
+  "trained_rows_total": 147386,
+  "total_db_rows": 241215,
+  "percentage": 61.1015069543768,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,