Training in progress, epoch 0

adapter_config.json

@@ -16,17 +16,17 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 4,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
+    "gate_proj",
+    "down_proj",
     "q_proj",
     "up_proj",
     "o_proj",
-    "v_proj",
-    "k_proj",
-    "down_proj",
-    "gate_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9044947ba35724f563f1ac1eb94cf5c74aa7faad540b060c22174e41c298e26
-size 9838816
+oid sha256:7fc7117e1fe5641ce4d83f84bda0ac7dc467793595ebbb97858cac5f663ba018
+size 19644912

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac5e990410fb21b4b81439a433f7dd46c99d7cb7eb91b024b025b066f52ff15f
+oid sha256:481a43b343d8cfa6f845d95536af55de959175b3efcf59099a0d4bf8aa8cf6d4
 size 5176