Training in progress, step 300

adapter_config.json

@@ -18,21 +18,21 @@
   "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",
-    "gate_proj",
     "v_proj",
     "k_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj",
     "up_proj",
-    "o_proj",
-    "down_proj"
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e015deb7ab983e657277d18f34a19f4371089fcc010cd46cf2cff09384af20e
+oid sha256:9126a9bb391910436ca58697c47e61edf63c0efc1ea9ea1ed04d1d024e83cf82
 size 9855413232

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd9a8afe1a070116a862b90bcba128f7b2ae3fae82b6255f148856ba77cf70b2
+oid sha256:8b72fb8b25d225dd52a08c75aac6aff07cd9964580b3cd7fee3a8865fafb6a94
 size 5624