Training in progress, epoch 1

adapter_config.json

@@ -13,7 +13,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 256,
+  "lora_alpha": 32,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -21,13 +21,13 @@
     "ln_f"
   ],
   "peft_type": "LORA",
-  "r": 256,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "k_proj",
-    "q_proj",
     "v_proj",
+    "q_proj",
     "o_proj"
   ],
   "task_type": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f6da6ac85b9395859e1a2f919488582f5682f5c9bdf70efe70b0a656bd66f87
-size 872450448
+oid sha256:319f0379c7a99bcb4b3681cff522ce7a289056d331b2800bc26ed97464cd37ed
+size 109086416

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e5001166a9212ddcdcb61d27c9cbb555c34b6a12bbc32051bc8479329b261bb
+oid sha256:39a198044511cffa638cbdcca3533581d44cca4ed19a592ccbfc0e5aeacb94a9
 size 5048