Training in progress, step 75

adapter_config.json

@@ -11,7 +11,7 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 16,
-  "lora_dropout": 0.005,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
+    "v_proj",
+    "gate_proj",
+    "k_proj",
     "o_proj",
-    "down_proj",
     "q_proj",
-    "k_proj",
-    "gate_proj",
-    "v_proj"
+    "down_proj",
+    "up_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:d45bd642e9d0e302ff187a6a8b8f8dcb437499624cac0ba93fff440e65c5f8c1
+oid sha256:35e231b9aa95521e3106c70c0eee12b0ca26281b5b60e687488267b10e001f2b
 size 167832240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef54dad93ca4760454115c255264ecb01c2e6838592b38cf59d6ef5a71ca73f4
+oid sha256:be928b88e5a6832a2c69dba0813b990375959c7861a41535e5947c8446b5c82a
 size 6264