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/tianyufan0504_/huggingface/runs/i1ph2gnv) 
+[<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/tianyufan0504_/huggingface/runs/rpxoig1h) 
 
 
 This model was trained with SFT.

all_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 103624402944.0,
-    "train_loss": 0.8838785322088945,
-    "train_runtime": 262.5643,
+    "train_loss": 0.0,
+    "train_runtime": 1.3161,
     "train_samples": 93733,
-    "train_samples_per_second": 0.145,
-    "train_steps_per_second": 0.072
+    "train_samples_per_second": 28.873,
+    "train_steps_per_second": 14.436
 }

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": 103624402944.0,
-    "train_loss": 0.8838785322088945,
-    "train_runtime": 262.5643,
+    "train_loss": 0.0,
+    "train_runtime": 1.3161,
     "train_samples": 93733,
-    "train_samples_per_second": 0.145,
-    "train_steps_per_second": 0.072
+    "train_samples_per_second": 28.873,
+    "train_steps_per_second": 14.436
 }

trainer_state.json

@@ -33,10 +33,10 @@
       "epoch": 1.0,
       "step": 19,
       "total_flos": 103624402944.0,
-      "train_loss": 0.8838785322088945,
-      "train_runtime": 262.5643,
-      "train_samples_per_second": 0.145,
-      "train_steps_per_second": 0.072
+      "train_loss": 0.0,
+      "train_runtime": 1.3161,
+      "train_samples_per_second": 28.873,
+      "train_steps_per_second": 14.436
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70b9559e7ae3e72df3c164171607c63ff555179a6d77ced060fba2d80b15a7be
+oid sha256:731373450af87f1999d74787fc5b845cc8390e9e3d691df04d0a6fbb5199364f
 size 7480