Model save

README.md

@@ -1,11 +1,9 @@
 ---
 base_model: Qwen/Qwen2.5-1.5B-Instruct
-datasets: open-r1/OpenR1-Math-220k
 library_name: transformers
 model_name: Qwen2.5-1.5B-Open-R1-Distill
 tags:
 - generated_from_trainer
-- open-r1
 - trl
 - sft
 licence: license
@@ -13,7 +11,7 @@ licence: license
 
 # Model Card for Qwen2.5-1.5B-Open-R1-Distill
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on the [open-r1/OpenR1-Math-220k](https://huggingface.co/datasets/open-r1/OpenR1-Math-220k) dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -29,7 +27,7 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/demolwang-salesforce/huggingface/runs/w6tquw8y) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/demolwang-salesforce/huggingface/runs/iocm1ddw) 
 
 
 This model was trained with SFT.

all_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 488621249396736.0,
-    "train_loss": 0.5791952503261282,
-    "train_runtime": 3212.9467,
+    "train_loss": 0.0,
+    "train_runtime": 2.3155,
     "train_samples": 93733,
-    "train_samples_per_second": 10.676,
-    "train_steps_per_second": 0.083
+    "train_samples_per_second": 14813.438,
+    "train_steps_per_second": 115.74
 }

config.json

@@ -23,7 +23,7 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.50.0.dev0",
-  "use_cache": true,
+  "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 488621249396736.0,
-    "train_loss": 0.5791952503261282,
-    "train_runtime": 3212.9467,
+    "train_loss": 0.0,
+    "train_runtime": 2.3155,
     "train_samples": 93733,
-    "train_samples_per_second": 10.676,
-    "train_steps_per_second": 0.083
+    "train_samples_per_second": 14813.438,
+    "train_steps_per_second": 115.74
 }

trainer_state.json

@@ -383,10 +383,10 @@
       "epoch": 1.0,
       "step": 268,
       "total_flos": 488621249396736.0,
-      "train_loss": 0.5791952503261282,
-      "train_runtime": 3212.9467,
-      "train_samples_per_second": 10.676,
-      "train_steps_per_second": 0.083
+      "train_loss": 0.0,
+      "train_runtime": 2.3155,
+      "train_samples_per_second": 14813.438,
+      "train_steps_per_second": 115.74
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c35f0d032c411942a77ff20d5fd4d489af6f2f4d3f558b6118520cbad04d15b5
+oid sha256:06f14f099397f56ed55a92acaa309b8cda8aa3e25f6cde4269808b8537418cdb
 size 7480