Training in progress, epoch 0

adapter_config.json

@@ -9,23 +9,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 256,
+  "lora_alpha": 512,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 128,
+  "r": 256,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
     "gate_proj",
-    "up_proj",
     "down_proj",
+    "q_proj",
+    "up_proj",
+    "k_proj",
     "o_proj",
-    "v_proj",
-    "k_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f029ae04116b905496dd1672892ce59b426d49ca596b0ea6ac285618c7087ad
-size 1342238560
+oid sha256:9b57398d943471b6b88420d1242ebe679d705c5c62c4da3aa88ccd9abc1f151a
+size 2684416208

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0941f2c64ffb1ebe77734f19b07cd49bf820304201b6c8896d7bd1ec46e5369b
+oid sha256:55cc212c5f02ca9658df1dca4ea923c70d739425d304eaead4935cc91a2454ad
 size 4664