Model save

README.md

@@ -1,11 +1,9 @@
 ---
 base_model: Qwen/Qwen2.5-Math-1.5B
-datasets: HuggingFaceH4/Bespoke-Stratos-17k
 library_name: transformers
 model_name: Qwen2.5-Math-1.5B-Open-R1-Distill-bi
 tags:
 - generated_from_trainer
-- open-r1
 - trl
 - sft
 licence: license
@@ -13,7 +11,7 @@ licence: license
 
 # Model Card for Qwen2.5-Math-1.5B-Open-R1-Distill-bi
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-Math-1.5B](https://huggingface.co/Qwen/Qwen2.5-Math-1.5B) on the [HuggingFaceH4/Bespoke-Stratos-17k](https://huggingface.co/datasets/HuggingFaceH4/Bespoke-Stratos-17k) dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-Math-1.5B](https://huggingface.co/Qwen/Qwen2.5-Math-1.5B).
 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/fandou-team/huggingface/runs/fgwx3x79) 
+[<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/fandou-team/huggingface/runs/7riusew9) 
 
 
 This model was trained with SFT.

all_results.json

@@ -1,17 +1,17 @@
 {
-    "eval_reasoning_loss": 0.858944296836853,
-    "eval_reasoning_runtime": 27.4191,
-    "eval_reasoning_samples_per_second": 4.705,
-    "eval_reasoning_steps_per_second": 1.204,
+    "eval_reasoning_loss": 0.8391534090042114,
+    "eval_reasoning_runtime": 29.4383,
+    "eval_reasoning_samples_per_second": 4.382,
+    "eval_reasoning_steps_per_second": 1.121,
     "eval_samples": 100,
-    "eval_utility_loss": 1.4312485456466675,
-    "eval_utility_runtime": 10.2853,
-    "eval_utility_samples_per_second": 4.764,
-    "eval_utility_steps_per_second": 1.264,
+    "eval_utility_loss": 1.158387541770935,
+    "eval_utility_runtime": 11.0695,
+    "eval_utility_samples_per_second": 4.427,
+    "eval_utility_steps_per_second": 1.174,
     "total_flos": 0.0,
-    "train_loss": 2.3145499420024835,
-    "train_runtime": 31780.9844,
+    "train_loss": 2.300789678476194,
+    "train_runtime": 31930.6254,
     "train_samples": 16610,
-    "train_samples_per_second": 0.68,
+    "train_samples_per_second": 0.677,
     "train_steps_per_second": 0.085
 }

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_mrope": false,
   "use_sliding_window": false,
   "vocab_size": 151936

eval_results.json

@@ -1,11 +1,11 @@
 {
-    "eval_reasoning_loss": 0.858944296836853,
-    "eval_reasoning_runtime": 27.4191,
-    "eval_reasoning_samples_per_second": 4.705,
-    "eval_reasoning_steps_per_second": 1.204,
+    "eval_reasoning_loss": 0.8391534090042114,
+    "eval_reasoning_runtime": 29.4383,
+    "eval_reasoning_samples_per_second": 4.382,
+    "eval_reasoning_steps_per_second": 1.121,
     "eval_samples": 100,
-    "eval_utility_loss": 1.4312485456466675,
-    "eval_utility_runtime": 10.2853,
-    "eval_utility_samples_per_second": 4.764,
-    "eval_utility_steps_per_second": 1.264
+    "eval_utility_loss": 1.158387541770935,
+    "eval_utility_runtime": 11.0695,
+    "eval_utility_samples_per_second": 4.427,
+    "eval_utility_steps_per_second": 1.174
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76e87fb37f0503c459587389f62ef8089353218c3427e2dc5facf4f98d3a85de
+oid sha256:1ca616972cfbaac7c9aa32ac2a6025ea2566f025fa936fecd75167fd9a45bf3d
 size 3087467144

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 2.3145499420024835,
-    "train_runtime": 31780.9844,
+    "train_loss": 2.300789678476194,
+    "train_runtime": 31930.6254,
     "train_samples": 16610,
-    "train_samples_per_second": 0.68,
+    "train_samples_per_second": 0.677,
     "train_steps_per_second": 0.085
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1dd270b7f8d93ad9d6ffe7c93f5ee0225a4a2134afae64c9fa5e1cd078b815c
+oid sha256:177e05ad3e6e7b32c5999314e3e3535d1ba1226c31b12030694cf61410ccc3b9
 size 6008