Training in progress, step 300

adapter_config.json

@@ -16,17 +16,17 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "up_proj",
-    "k_proj",
-    "down_proj",
     "o_proj",
+    "gate_proj",
     "v_proj",
-    "q_proj"
+    "down_proj",
+    "q_proj",
+    "k_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:f03d53216b0cd42a6eceb76209b91dab325f3e4524c782d57cb45340c3c9e094
-size 161533192
+oid sha256:eb335fdbd28a0df97d672c90e4dfca58e73676366b6c1a1a01a6339ddd6b2f82
+size 323014168

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70ffd422e9be4099adfd602242186247986e8b54b0ff08e9be5ab98a0dbd347c
+oid sha256:6ad1f07e31ab4977d8c6b92d0c6ed1d0cace60d19ab7adf1ac2a63fddf50c004
 size 5560