Training in progress, step 10

adapter_config.json

@@ -10,7 +10,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 16,
   "lora_dropout": 0.0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
     "gate_proj",
     "up_proj",
-    "down_proj",
-    "v_proj",
-    "k_proj",
+    "q_proj",
     "o_proj",
-    "q_proj"
+    "k_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57172ea18817b8072c000a44cc5c171c4ce052649f6a6f35de186b20091edc0b
+oid sha256:63002af514817e2febd9fdf5fb5c3e19fbe85a35ff3e5367342f238cc64c3d84
 size 80013120

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9ce59f0a7ee563dfba53a0edb375b9b5a6ab744dffd8cea54c8cb28f5ca3440
+oid sha256:1d084b8c72bde113bc93dcdd2db429269f664d9595d7b2aa78f117eba13424ad
 size 5560