Training in progress, step 50

config.json

@@ -1,11 +1,11 @@
 {
-  "_name_or_path": "/apdcephfs_qy3/share_1594716/bingzhe/pretrained/Qwen2.5-Math-7B-Instruct",
+  "_name_or_path": "/apdcephfs_qy3/share_1594716/yataobian/yang/pretrained/Qwen2.5-Math-7B",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 151643,
-  "eos_token_id": 151645,
+  "eos_token_id": 151643,
   "hidden_act": "silu",
   "hidden_size": 3584,
   "initializer_range": 0.02,
@@ -18,12 +18,13 @@
   "num_key_value_heads": 4,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
-  "rope_theta": 10000.0,
+  "rope_theta": 10000,
   "sliding_window": null,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.48.3",
   "use_cache": false,
+  "use_mrope": false,
   "use_sliding_window": false,
   "vocab_size": 152064
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9db098abd04eef4322ebe7f1626477dbd41536e5f73ceb838a457d0d4f24e567
+oid sha256:5c778cca3417ddb789a45f082c625c93823b8a35f320b9d4363beb503900dba9
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a6233a1e9c3bba1685b6c2ac65236f1d223c73bb791545a1a99a0089d932645
+oid sha256:24732c3bb8f4b9f7a507884933891c8b2ee6df584fe829ae506256afcc99149e
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bebc02a27ff7e68ae50a4646b51fd26c63fb105fa0b1a3f7006111854c51d6dc
+oid sha256:a617e9878396c6c744452cb4667db64f08fa1ba7bb6d13c2269a2c1050131873
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6db7c3660a27c20c38ff38b94d4527ba977d6eb6fcff91c87d49c59e82ad9d81
+oid sha256:8ea597628e69c61d0f0be2674a25d85b73e6586528917b161d13f3c0b54d03dc
 size 1089994880

special_tokens_map.json

@@ -15,7 +15,7 @@
     "<|video_pad|>"
   ],
   "eos_token": {
-    "content": "<|im_end|>",
+    "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -197,7 +197,7 @@
   "bos_token": null,
   "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'Please reason step by step, and put your final answer within \\\\boxed{}.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nPlease reason step by step, and put your final answer within \\\\boxed{}.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
+  "eos_token": "<|endoftext|>",
   "errors": "replace",
   "extra_special_tokens": {},
   "model_max_length": 131072,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:139d519c865fa6ddc63a0ea8620a381724994115101d36a3beb2fcce8cc37e9d
+oid sha256:c9a44e7314733e990ca1e02704e9eabc8872e01437e98c2ae5eac2089652689c
 size 7352