Training in progress, step 3

adapter_config.json

@@ -10,21 +10,21 @@
   "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",
     "q_proj",
     "gate_proj",
-    "up_proj",
     "k_proj",
-    "down_proj",
     "v_proj",
     "o_proj"
   ],

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c1c29d1f5649df700edb2931a4ba65802f1d7aede9c11934423e1b0801b9fcb
-size 9048
+oid sha256:c599b75a981b0d9f0dc6a0e91aa387a26e70ef6d36d76cb04bce8ce82a092b48
+size 14696

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f30b79b60b8c46ca02ae421a50ada3e80027f9f26343b71ced3942fb88eb24b
+oid sha256:dae77c6881efffb1525ab27d15f41925709b4eb57600c98d05461f542cc3b806
 size 6776