Training in progress, epoch 0

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "Qwen/Qwen2.5-Math-7B",
+  "_name_or_path": "chenggong1995/Qwen-2.5-Math-7B-Max-v3-accuracy",
   "architectures": [
     "Qwen2ForCausalLM"
   ],

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ddb2a1429edd0fcd9451f9ec5675ca007b376c36bc248a6752e6dabc4ab3bdb
+oid sha256:4abc207d6f28e5b82e2730ceb021926fb0be38b45f040a02a1180ea8f3063bf3
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc0522bfa5e8d0b1b54a89f67c154a40ad972fa8788cf9f77bf151ee5413f117
+oid sha256:18b6fb64c20fa4ed771880768cf889e0bb39c2159d0fddd327cb3c69328e1f08
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d563e69c75196bedcee0b2e4c2bd061579bc2b874953a139dc612d53701c183
+oid sha256:ec0e1eb8cfcfcf86affa85864ae6b6c9609346745c532a00f20074f3af13393e
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8785c59f49861da218f52ded868b2db82073951e660b6bc29d91a496f7222c03
+oid sha256:9237062e9287012626cabcfd8ab8326a5966a02c46210c8c40668b9829b96e30
 size 1089994880

tokenizer_config.json

@@ -200,8 +200,11 @@
   "eos_token": "<|endoftext|>",
   "errors": "replace",
   "extra_special_tokens": {},
+  "max_length": null,
   "model_max_length": 131072,
+  "pad_to_multiple_of": null,
   "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
   "padding_side": "left",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f4460816a5463a332f4789c7810e6692cc7424fbad8caf0042d05411861e8db
+oid sha256:5585f91af0391afe960a524dd81cbe5167e34017c1abead845bc6ddb41420cd5
 size 8056