Training in progress, epoch 0

adapter_config.json

@@ -10,23 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 8,
+  "lora_alpha": 4,
   "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": [
     "q_proj",
     "k_proj",
-    "o_proj",
-    "v_proj",
     "gate_proj",
+    "v_proj",
     "down_proj",
-    "up_proj"
+    "up_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:ef4594fc1a774d99d5e10fc12cb5209b13c3ca358bcdb899a13e5263e3af7a43
-size 41581360
+oid sha256:264563c99fd4ee4c9b929484fbef77fd479cfc2fe8eafe8ff7abb34e346b2b2b
+size 20814440

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bd34aa2c6e19ea6b854f4ca0b4c0bd8e372055df0919307fb234db2abaa2404
+oid sha256:7dd4280c4c6762d320115a3d3d88f7f0bc5ebf263e5eb040a31035e933a49577
 size 5432