Training in progress, step 1

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45307d268ee3181141aafb953a9e07514f34bfba9164005f1e1ebf9ac3bdd4d2
+oid sha256:2089287fcda45fe6aedc375d0ed6792ade3939a7d362d9a8b2b1c3b4985c1239
 size 13437096688

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a544ac86ab3e79953dd09c6d5fa8aa8ce2cd380e092bd7b51429b4cddaa75d9d
+oid sha256:45b39469b075dc612673b9fb65b8af2df842d57c45451c3b51241df048d6e167
 size 5624