Training in progress, step 360

adapter_config.json

@@ -13,17 +13,19 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "lora_bias": false,
-  "lora_dropout": 0.05,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
+    "o_proj",
     "v_proj",
     "q_proj"
   ],

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c60c31f37c1d43895913e7e234fd1fec299e525d384f6eecf320c0fd7068e268
-size 10107280
+oid sha256:12f75a52f89fff0c81acab013b1eb8847492fdc85073e1454ef98b05c0f80460
+size 40400200

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e57cadfeb112302f66796c3fad11d1ebdd2f20e6ab4522f779e02cf139303b2
-size 5688
+oid sha256:6b44d96c9d348b0e20f869634d4dbcc91784b78e7e292c19580f9bcf3ac1f6aa
+size 5752