Training in progress, epoch 0

adapter_config.json

@@ -20,12 +20,12 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "down_proj",
-    "o_proj",
-    "up_proj",
     "q_proj",
+    "v_proj",
+    "o_proj",
     "gate_proj",
-    "v_proj"
+    "down_proj",
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4123dd4b3f6910cccf9da4229c608b8f47385d85ccec8c0e022c40a026712b94
+oid sha256:1bb1dfbb5311e807c7c35bf7f7e8ed67f9da478d556b78e5f53ab77612b424c8
 size 1803907984

runs/Jul19_14-02-26_llm-dpo-workbench-0/events.out.tfevents.1721397754.llm-dpo-workbench-0.251.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:767a3b73bfb375dafac9aa2e8c579e95f5562f42a2b5f87197d11e1b246ea768
+size 5743

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe5dcd2155d81c37b552dcad51615bd4eafc6e118c1a78b652496e17c839c2ae
+oid sha256:31ad647a82ec7ff29de3b90a00189707c4ec83b13b0c3f2bfb19ed6e715d5bd3
 size 4728