Training in progress, epoch 0

adapter_config.json

@@ -10,18 +10,18 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
-  "lora_dropout": 0.1,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 64,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "v_proj",
+    "k_proj",
     "q_proj",
     "o_proj"
   ],

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1d17deff5bd14d274f0da04c2d0991be81ab21d88a23f7b955d9bdbf3e762f6
-size 100689136
+oid sha256:d019983ea80b1afc46a025a395ee31698cf452eb1e5efd53cb63497627864fdf
+size 50357440

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d66edaedb9e734043ae795c5d8cf4d46192c39145e12b17277f670f600d93fa
+oid sha256:f5dc67d2a010f1dd1a3eb4a51e7e213f0755bb410d16c92b4b42ff8fee046cab
 size 4984