Training in progress, step 20

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: qwen-coder-7b-finetuned
 tags:
 - generated_from_trainer
-- trl
 - sft
+- trl
 licence: license
 ---
 

adapter_config.json

@@ -30,8 +30,11 @@
   "revision": null,
   "target_modules": [
     "v_proj",
-    "o_proj",
     "k_proj",
+    "gate_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj",
     "q_proj"
   ],
   "target_parameters": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18232cf87a37c3d8e51bec32728bb0c237dd20a07fb84cfac98abe3f04f494be
-size 40400200
+oid sha256:8047deb424cd171492a00e21b3ca4c8caa8ba9b3443e4e0e7a78e03a7b7bd07f
+size 161533192

special_tokens_map.json

@@ -21,11 +21,5 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "pad_token": "<|im_end|>"
 }

tokenizer_config.json

@@ -200,7 +200,7 @@
   "errors": "replace",
   "extra_special_tokens": {},
   "model_max_length": 32768,
-  "pad_token": "<|endoftext|>",
+  "pad_token": "<|im_end|>",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2b74435ffc33e05ba9e96b66800638ebae20ae459a116682e76ccecc0d34b9b
-size 6225
+oid sha256:1b9a61aa89d843518722012e9b26116edf6430de079d43b2dc4c5baf990b1ced
+size 6289