Training in progress, step 3

adapter_config.json

@@ -10,23 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 8,
-  "lora_dropout": 0.1,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 4,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "up_proj",
     "v_proj",
-    "k_proj",
-    "gate_proj",
     "o_proj",
-    "q_proj"
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "down_proj",
+    "k_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:a7e711b7b4034b2f3bd9799e3738e807081a18d9dd9d4402e426cefbb04d49c9
-size 9048
+oid sha256:ab90251ab6e27a57801a12d18af11f2f9f07fcab223af845d95de1a0b405501c
+size 14696

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a34c87415c9e639533cb4d7b940fdf4014edaec46abd1ff3438eb94417519db3
+oid sha256:525897d6fc230472c14ab0a00d3e93c0465a5d3840498e66ad09e713ff0af362
 size 6776