Training in progress, step 25

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
+    "up_proj",
     "v_proj",
-    "down_proj",
+    "q_proj",
     "k_proj",
+    "gate_proj",
     "o_proj",
-    "up_proj",
-    "gate_proj"
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cf0659e85d018f49de4b2e14fc677a2312ed172a52e0b53c88a51f2da1cbde7
+oid sha256:c018962df37a9bc57f0478db68aa5c133135e1e1c25520e963bba776af7a71f5
 size 167832240

tokenizer_config.json

@@ -2059,6 +2059,6 @@
   ],
   "model_max_length": 8192,
   "pad_token": "<|reserved_special_token_250|>",
-  "padding_side": "left",
+  "padding_side": "right",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00002c8b6c4c2f45e0db07954f18097260a84b704330ff0c4b000aaf7ee2f6bc
+oid sha256:34e5495b3e5640fa7e0a1964207ba07f1fd2e95d0694b279e1c55c996b264768
 size 5432