Training in progress, epoch 0

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "data/Qwen2.5-1.5B-Open-R1-Distill/",
+  "_name_or_path": "data/Qwen2.5-1.5B-Open-R1-Distill",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
@@ -22,7 +22,7 @@
   "sliding_window": 32768,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.49.0.dev0",
+  "transformers_version": "4.49.0",
   "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:c98c1a7f9e8b8572aff04c2ec27ea95c93b9392c0c3519ade9156f5f67641652
+oid sha256:b0c7945aaddd2ba512a2469eac221be8113e82ab59781aadf9a40527c445f672
 size 3554214752

tokenizer_config.json

@@ -202,7 +202,6 @@
   "extra_special_tokens": {},
   "model_max_length": 131072,
   "pad_token": "<|im_end|>",
-  "padding_side": "left",
   "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 sha256:31327b31e572bf69a39706dd29917f44e534225ffe1b01fe1fed49b1f3d22241
-size 7608
+oid sha256:edf528e7f0ea94d6ae13d5f913ce548faa1e5fe939aaf0e560f9c209131fd4b3
+size 8120