Seth/Mortdecai
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

361 training examples, default to 1 epoch

Browse Source 
Ingested 128 new examples from bot-driven data collection.
Dropped: 86 duplicates, 19 language mismatches, 10 prompt leaks, 19 empty.
Changed default epochs from 3 to 1 (previous run overfit at loss 0.10).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Seth Freiberg
2026-03-18 18:03:33 -04:00
parent 17a2a95f56
commit 62419976e5
2 changed files with 129 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
training/scripts/train_lora.py
+1 -1
View File
@@ -107,7 +107,7 @@ def main():
parser.add_argument("--rank", type=int, default=16, help="LoRA rank")
parser.add_argument("--alpha", type=int, default=32, help="LoRA alpha")
parser.add_argument("--lr", type=float, default=2e-4, help="Learning rate")
parser.add_argument("--epochs", type=int, default=3, help="Training epochs")
parser.add_argument("--epochs", type=int, default=1, help="Training epochs")
parser.add_argument("--batch-size", type=int, default=2, help="Per-device batch size")
parser.add_argument("--grad-accum", type=int, default=4, help="Gradient accumulation steps")
parser.add_argument("--max-seq-len", type=int, default=2048, help="Max sequence length")