Training in progress, step 500

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": [
-    "v_proj",
-    "down_proj",
-    "q_proj",
     "o_proj",
-    "gate_proj",
+    "q_proj",
     "up_proj",
-    "k_proj"
+    "v_proj",
+    "k_proj",
+    "gate_proj",
+    "down_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:d17951e04128aea66ba1ffdc6f4981944f81830c9d1aea42ff22dd232a1770d4
+oid sha256:a1d1fe5b471a83471852a26bf4beb8aac24a8716654559e9bea603e2bb75e703
 size 574792512

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7d9882cc87efee23f03068bbfe90b7fb6df939b68c50d74bca388701b2230f4
+oid sha256:b835f42d027e4593d4715f555e0ccce2a0f927fb2fee713144e47ff18cbd8de4
 size 5496