Training in progress, step 100

adapter_config.json

@@ -9,23 +9,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 128,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 128,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "v_proj",
-    "gate_proj",
     "k_proj",
+    "q_proj",
     "o_proj",
     "up_proj",
-    "q_proj",
-    "down_proj"
+    "down_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6818f82548be6f3fd008327a96a7b20b01650a873b4356f1108aee46e83d021
-size 167832240
+oid sha256:a062568ec243d8f444fd9dec7249f1eef4aabb5359904d7ed2b123b2c4ef7dd3
+size 1342238560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c954f900ff11b6141cfa039d8ddf6d7f455c9b383d89fd93a22486b8c717bfd
+oid sha256:e3cba20d79f1f449940dbf2000bc1e4e4e0b02993915f88637775ed2674e361b
 size 5176