Model save

README.md

@@ -27,7 +27,7 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/zc096373/s1/runs/ubnzw61e) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/zc096373/s1/runs/zp9uk74s) 
 
 
 This model was trained with SFT.

added_tokens.json

@@ -1,7 +1,10 @@
 {
+  "</saving>": 151670,
   "</think>": 151668,
   "</tool_call>": 151658,
   "</tool_response>": 151666,
+  "<control>": 151671,
+  "<saving>": 151669,
   "<think>": 151667,
   "<tool_call>": 151657,
   "<tool_response>": 151665,

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e260cb8f797f09664f2efd5f9ebc9ef4d3c923f197053b7e41da06fd5a4e2074
+oid sha256:69439624d825b26d0c08c78f4a5739096a83072a36fac4b93a1236d29116a490
 size 4967376872

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad7e3a3fb8b39e2c53cd950f941d3211d9a79a1fbe5cd765364dc5955a63096b
+oid sha256:2ead046091f06e4f44bb890ae4ba3a8db01846e343fba91f92b36ed6c5b76212
 size 3155292920

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": "<|fim_pad|>"
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
-size 11422654
+oid sha256:41c8dfeb937be85b6ef72682cee777c65c594d7902ca18eba9fb6b352d74486e
+size 11423211

tokenizer_config.json

@@ -209,6 +209,30 @@
       "rstrip": false,
       "single_word": false,
       "special": false
+    },
+    "151669": {
+      "content": "<saving>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151670": {
+      "content": "</saving>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151671": {
+      "content": "<control>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
     }
   },
   "additional_special_tokens": [
@@ -232,7 +256,7 @@
   "errors": "replace",
   "extra_special_tokens": {},
   "model_max_length": 131072,
-  "pad_token": "<|endoftext|>",
+  "pad_token": "<|fim_pad|>",
   "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 sha256:2712c1dd498bbe3597d6f22669a01980a1bb6e7827cce9a4cc4ce3b54a2d9b2c
+oid sha256:df53f6869c2132314fa55454634da2694f711b9c6c6e8e59c24c41db112cef98
 size 5880