Training in progress, epoch 1

adapter_config.json

@@ -12,24 +12,24 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 64,
+  "lora_alpha": 32,
   "lora_bias": false,
-  "lora_dropout": 0.1,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 128,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
     "down_proj",
-    "gate_proj",
-    "q_proj",
+    "v_proj",
     "k_proj",
-    "up_proj",
-    "o_proj"
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4421fd7e640a9d0945fad266ea5c431349da33a6991350b3e958cb4d400e537b
-size 1347775120
+oid sha256:e7c690ea2bba63091c0e8fff1be19ed93887f175ffa09b146ce790e3eba19101
+size 676685576

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:325eff1171656cf92f550a0f196b4dd95e0b943a247704a9dc61f592b3ceca42
+oid sha256:039363826b8019c94ac7ebc50e3e6f8b916962fe26803cf421bd8dbf6dcfa055
 size 5688