Training in progress, step 10

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/apdcephfs_qy3/share_1594716/bingzhe/pretrained/Qwen2.5-3B",
+  "_name_or_path": "/apdcephfs_qy3/share_1594716/yataobian/yang/output/data/Qwen2.5-3B-GRPO-Natural-Reasoning",
   "architectures": [
     "Qwen2ForCausalLM"
   ],

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1739e94dbd09441d7b7867362a50ec2e5dad345a82c431f4d15eeb0c49503080
+oid sha256:1fbb33360192d2d19821f50a90e5b575305b22f3686eea2d7f066e0fc6d2d8c8
 size 4957560304

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99ea90419917fc731e409e2eb221cf5c09cb43e56014158ce2d8466c5c8df4e5
+oid sha256:94cf94547745d6a841feb529f56a47de08382b7ad6430dc41cbb4e6c8aca0f25
 size 1214366696

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:a7c545d13cb753635a7d8bdb1d41f5d84218ea058a4ceb6af73131978ea42aa2
+oid sha256:070b0e2b55a898d76266352a4f77851ca5aec7a66e8e6db24fc993c8ee36f5b3
 size 7608