Training in progress, step 150

adapter_config.json

@@ -10,23 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 8,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 4,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "q_proj",
-    "down_proj",
-    "v_proj",
+    "up_proj",
     "gate_proj",
+    "v_proj",
     "k_proj",
-    "up_proj"
+    "o_proj",
+    "down_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01a742c2056287a3329a44426eda37458f23296f011b4ed53c6334585d6741a3
-size 83945296
+oid sha256:0fd7e85b83a3efada449a0358e71243a0d9a75097fcec2a0ce8ef70f99b01767
+size 42002136

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdc4c339d5730e6ec9d0d548b10a92b6b67b7c212c9d1c201a554ed13523e0a6
+oid sha256:cda6572949e2823163e920fde2833ddb39e3300db4fceb5dc6cf9e08468745fc
 size 6712