Training in progress, step 2

adapter_config.json

@@ -12,23 +12,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 2,
+  "lora_alpha": 128,
   "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 2,
+  "r": 128,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "down_proj",
-    "gate_proj",
     "v_proj",
+    "gate_proj",
     "q_proj",
     "up_proj",
+    "k_proj",
     "o_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:191958c95672f0378a046b839a8c2ddaa4da6b264f1e6ab072026f512e44b386
-size 12208024
+oid sha256:517f79aef9d14691e8e685bf47a5048152a3ce8c457b67f8ed60e7f8c1a817ac
+size 778096664

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:598b707700e4270f3954f68e1e478e3f3488c8d62e4ef082efea63c96de0db92
+oid sha256:e13f29b3ecc64b576ac884f0128b02452af3832f309e05a187492ed36b0969f8
 size 14264