Training in progress, step 10

adapter_config.json

@@ -10,8 +10,8 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 8,
-  "lora_dropout": 0.05,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj",
+    "k_proj",
     "out_proj",
-    "k_proj"
+    "q_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a6ec087144f6baef2aebbe8fd65d72fb56ede8c1b945389b556bd2dba1ef0d1
-size 7247616
+oid sha256:4426b6aabf26fbbb663fee3a0fd1c2178996bf8c0302e12c9e806662e04c6a49
+size 14472920

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee0d144032be044d5aa5dd8e87648a21d904a32edcc759fe572d36cf9fd76979
-size 17519064
+oid sha256:c97408e641b3b2eaf2c5b435a6983a141578e964e955b6d716919101320b0623
+size 17519063

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa689eec189e7a0603e31635e0253280e236784e9780e703d2ac671cc63e818e
+oid sha256:35d19ebb097d22afd24b90ad5b193f41940c7f3fe786ba1d499290b8d6b11279
 size 5112