Training in progress, step 500

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: tiny-chatbot-model-dpo
 tags:
 - generated_from_trainer
-- dpo
 - trl
+- dpo
 licence: license
 ---
 

adapter_config.json

@@ -13,7 +13,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 8,
+  "lora_alpha": 16,
   "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
@@ -21,7 +21,7 @@
   "modules_to_save": null,
   "peft_type": "LORA",
   "qalora_group_size": 16,
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c64e9d0a4dcf84f1b6f21cf721a94949609585e6b293236ba5fd469fc8280c35
-size 4517152
+oid sha256:c7068c0f0d61cbd1366edacd7b6b2492cfefac4339534f0ade28ea83253ba125
+size 9022864

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e54ace875f7ffed8c1a9c0ac98a2492431ae14f5e352093df1ec35df75359083
+oid sha256:65aa4b6f08f73417197297cdfe1bf04367830e1dec817b7f48751c7cabbf5b76
 size 6328