Training in progress, step 1

adapter_config.json

@@ -15,21 +15,21 @@
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": [
-    "embed_tokens",
-    "lm_head"
+    "lm_head",
+    "embed_tokens"
   ],
   "peft_type": "LORA",
   "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "o_proj",
+    "q_proj",
+    "k_proj",
     "down_proj",
     "v_proj",
-    "k_proj",
+    "o_proj",
     "gate_proj",
-    "q_proj"
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42976362c21dffb447ac6788fbd5f0a2112a143ba6c343160b8eaf2fd4aafc59
+oid sha256:c9e03116dffd536444df58811b56af3638e9c9a709e72b2a5c1012ee66cc535a
 size 13437096688

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:475a07c58092990825b02a3c4f7892f00c38f0543c87e3e078098cea99d492a8
-size 17210956
+oid sha256:97259a2ef98adbd9197e93d7931212a327b6b0a496e1308e287d8766d90866ff
+size 17210857

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26796fcf37f1e7259bc28771d3a495ff3848440b843933b956ba4a29aeeead5d
+oid sha256:a544ac86ab3e79953dd09c6d5fa8aa8ce2cd380e092bd7b51429b4cddaa75d9d
 size 5624