Training in progress, epoch 0

adapter_config.json

@@ -15,19 +15,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 8,
+  "lora_alpha": 16,
   "lora_bias": false,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 4,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "out_proj",
-    "o_proj"
+    "o_proj",
+    "linear_2",
+    "linear_1",
+    "self_attn.v_proj",
+    "self_attn.k_proj",
+    "self_attn.q_proj"
   ],
   "task_type": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d0d825efe2d7c62fa3cc8a6a1817eec6d36d8346a8b323429aa71f652619d4c
-size 5791896
+oid sha256:a026449da2d6c4ec39e4b67e13a53e5fc1b17ea037d3cd473b77872e178c4357
+size 43502040