Training in progress, step 10

adapter_config.json

@@ -16,7 +16,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "lora_bias": false,
   "lora_dropout": 0.1,
   "megatron_config": null,
@@ -25,12 +25,17 @@
   "peft_type": "LORA",
   "peft_version": "0.18.1",
   "qalora_group_size": 16,
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "v_proj",
-    "q_proj"
+    "gate_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "up_proj",
+    "down_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c5280a53ef5899573753a72bdd4a89674cea2adc12832f2837b242ca6d5679d
-size 11815504
+oid sha256:c89756c1c17efb6a1da6c1827f6de228b93167169ee776c1c13845a67a29007b
+size 132187888

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15e0504aa766675d680ebb909ec2a820055ddc31f791f6e4fa10940539840ecf
+oid sha256:974a75e377a137058e498e723ccbd097e2d4e7da9d7ff8e9473f52d872722ff3
 size 5137