Training in progress, step 250

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cd5b1e97441f28e41b7068fb8d44e6daa1c46739d5a705fd9b6d59c4a47cb30
+oid sha256:c103b7bb5bb1e6eaaa9d9f8954d133de26470d51bebaf248ccdf281c1581d4f2
 size 22573704

tokenizer_config.json

@@ -2059,6 +2059,6 @@
   ],
   "model_max_length": 131072,
   "pad_token": "<|finetune_right_pad_id|>",
-  "padding_side": "right",
+  "padding_side": "left",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3f81ebf358e6f998efaa2938cc05340e75c0835e6ac5fcb57cd4dd34147d1b9
+oid sha256:272164c88984542290312d0615c0a72c0c48939096ec2e5d7f55fd4acf8b7655
 size 5624