Training in progress, epoch 0

adapter_config.json

@@ -10,23 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
-  "lora_dropout": 0.05,
+  "lora_alpha": 8,
+  "lora_dropout": 0.1,
   "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",
     "gate_proj",
     "q_proj",
-    "up_proj",
+    "down_proj",
     "v_proj",
+    "o_proj",
     "k_proj",
-    "down_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:b533b7117bc0e3c81f20822c894195616054d12b9a0cdcfb40e420186d215d2a
-size 14696
+oid sha256:1d88b1e51271dd31989fdcb683c1f1b908065dbdaece123315139618413ff168
+size 9048

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:746519a0d96e6801b9e01fd3392d353e8f9467d5d8a337d4d558559fbbc2a9f0
+oid sha256:c263e05fe207b407c6cd11bb652d63a63732b2d1b47dcaa717b61ddd3b2908e5
 size 6776