Training in progress, epoch 0

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
+  "_name_or_path": "/dengwenbo/224015062/open-r1-main/data/Qwen2.5-1.5B-Open-R1-Distill",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
@@ -23,7 +23,7 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.49.0",
-  "use_cache": true,
+  "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:175a0465357f8f85e18cf2af55d5468ab756f79a919f1eb81fd5d3a9be44b8e6
+oid sha256:8ed11b891ce188a84c33064c8e9118704a03168043400f9ccd0c216c075fc07f
 size 3554214752

special_tokens_map.json

@@ -22,7 +22,7 @@
     "single_word": false
   },
   "pad_token": {
-    "content": "<|endoftext|>",
+    "content": "<|im_end|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
-size 11422063
+oid sha256:63a2951d5edfa5cc0a2346ef872f8c77a2920274cfc3b503b04e3799104dee80
+size 11422060

tokenizer_config.json

@@ -201,7 +201,7 @@
   "errors": "replace",
   "extra_special_tokens": {},
   "model_max_length": 131072,
-  "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 sha256:137cd08454ccd0a5edffb59f99f53f77ebc0d9d2a9d31ef17675ac85147d839f
+oid sha256:c6ae1b0edde2fb221a1a75daac02aad68b90a4413c3a441c1bef158e2ad0fe9c
 size 7992