Training in progress, step 250

adapter_config.json

@@ -7,6 +7,36 @@
   "init_lora_weights": true,
   "layers_pattern": null,
   "layers_to_transform": [
+    0,
+    1,
+    2,
+    3,
+    4,
+    5,
+    6,
+    7,
+    8,
+    9,
+    10,
+    11,
+    12,
+    13,
+    14,
+    15,
+    16,
+    17,
+    18,
+    19,
+    20,
+    21,
+    22,
+    23,
+    24,
+    25,
+    26,
+    27,
+    28,
+    29,
     30,
     31,
     32,
@@ -18,15 +48,17 @@
     38,
     39
   ],
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "lora_dropout": 0.1,
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 16,
   "revision": null,
   "target_modules": [
     "c_attn",
-    "c_proj"
+    "c_proj",
+    "w1",
+    "w2"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e894f1a24c9f2b471fc9caba4b68dc158dab14bc6da9c973cd60fd2287c3ca56
-size 15873058
+oid sha256:035c8f512aa7a1520692dcffd1515b3ec9a3cea76e41479954299cc0ed2c5732
+size 223292874

tokenizer_config.json

@@ -1,6 +1,5 @@
 {
   "added_tokens_decoder": {},
-  "additional_special_tokens": [],
   "auto_map": {
     "AutoTokenizer": [
       "Qwen/Qwen-14B--tokenization_qwen.QWenTokenizer",
@@ -8,7 +7,8 @@
     ]
   },
   "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
   "model_max_length": 8192,
-  "tokenizer_class": "QWenTokenizer",
-  "tokenizer_file": null
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "QWenTokenizer"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9d00f73287665ee4c68de8b4fd6279949df866bff0b5dd4e97822d2c755b516
+oid sha256:cfb6dfd046e9c3f57b096c4bf091808f482c455a01cc715c0b2e7b00b7ef7d75
 size 4600