update

adapter_config.json

@@ -11,21 +11,21 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 512,
-  "lora_dropout": 0.0,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 256,
+  "r": 128,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "k_proj",
-    "q_proj",
     "gate_proj",
     "up_proj",
+    "v_proj",
     "down_proj",
+    "k_proj",
+    "q_proj",
     "o_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60a18267cfee34cb5d293b560b7bc952305da9fdf52c745114a19384b6b78552
-size 2583745128
+oid sha256:40d46cc1a5263321dc53bad5948019602f62d8168b8194137721d3082a340626
+size 1291899160

tokenizer_config.json

@@ -199,7 +199,7 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",
-  "model_max_length": 131072,
+  "model_max_length": 8192,
   "pad_token": "<|endoftext|>",
   "padding_side": "right",
   "split_special_tokens": false,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84d4dc6dd7b6d540738b5f00cf8f126e521de7e38a97ceb1d7b8835681dd8c88
-size 5432
+oid sha256:ca7479a9cc1e8c3c3d642379c3e5643af511d79157c8ec5e34e7c9d326caa97b
+size 5560