Training in progress, step 200

adapter_config.json

@@ -13,20 +13,21 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 8,
+  "lora_alpha": 32,
   "lora_bias": false,
-  "lora_dropout": 0.1,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
   "qalora_group_size": 16,
-  "r": 4,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "c_proj",
-    "c_attn"
+    "c_fc",
+    "c_attn",
+    "c_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f50837c144ee9af6be74cc68bfc76c214180ecfd174b4338571ebdb6b6d7397
-size 1631040
+oid sha256:1e45121682c0f97e75daad84c4e3f6088d1c964982f3ebecc6bcc18485c976e4
+size 9449344

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c00de7c767d53f692594fe8c07370a53e76791f9cd5ff673e3871cc7ba1823df
+oid sha256:6924268a72ca523e7197a24923fd2b3365de29bbad6e69bc0ffe77b8bc435390
 size 6737