Training in progress, step 232

adapter_config.json

@@ -10,13 +10,13 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
-  "lora_dropout": 0.01,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efff5f5e6f0f5a3099d350893706dcc50c1c750a2f00762eaf49fb772f0daf45
-size 13648432
+oid sha256:1f2d55e9461da188f1b59f4da124fdc6db7c8f90b31aa34a6a06c73e9c56fdc0
+size 54543184

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa07c243c3027e556a408665d066b19b695f86f0a20f7da878906eb4ac14c17f
+oid sha256:42f4484e67fedf051f0f6b1ff88e712c146ba91ca7fcbb21246bc0f2a085b360
 size 5688