Model save

README.md

@@ -1,16 +1,14 @@
 ---
-datasets: HuggingFaceH4/Bespoke-Stratos-17k
 library_name: transformers
 model_name: Qwen2.5-1.5B-Open-R1-Distill
 tags:
 - generated_from_trainer
-- open-r1
 licence: license
 ---
 
 # Model Card for Qwen2.5-1.5B-Open-R1-Distill
 
-This model is a fine-tuned version of [None](https://huggingface.co/None) on the [HuggingFaceH4/Bespoke-Stratos-17k](https://huggingface.co/datasets/HuggingFaceH4/Bespoke-Stratos-17k) dataset.
+This model is a fine-tuned version of [None](https://huggingface.co/None).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -26,7 +24,7 @@ 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/2741919970-hustvl/huggingface/runs/902j0zxa) 
+[<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/2741919970-hustvl/huggingface/runs/bi9iyx1a) 
 
 
 This model was trained with SFT.

all_results.json

@@ -5,9 +5,9 @@
     "eval_samples_per_second": 4.386,
     "eval_steps_per_second": 0.57,
     "total_flos": 0.0,
-    "train_loss": 0.8600422314672648,
-    "train_runtime": 45916.2025,
+    "train_loss": 0.0,
+    "train_runtime": 1.7052,
     "train_samples": 16610,
-    "train_samples_per_second": 1.085,
-    "train_steps_per_second": 0.068
+    "train_samples_per_second": 29222.257,
+    "train_steps_per_second": 1826.171
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.8600422314672648,
-    "train_runtime": 45916.2025,
+    "train_loss": 0.0,
+    "train_runtime": 1.7052,
     "train_samples": 16610,
-    "train_samples_per_second": 1.085,
-    "train_steps_per_second": 0.068
+    "train_samples_per_second": 29222.257,
+    "train_steps_per_second": 1826.171
 }

trainer_state.json

@@ -5265,13 +5265,12 @@
     },
     {
       "epoch": 2.9979530403371464,
-      "mean_token_accuracy": 0.7530115023255348,
       "step": 3114,
       "total_flos": 0.0,
-      "train_loss": 0.8600422314672648,
-      "train_runtime": 45916.2025,
-      "train_samples_per_second": 1.085,
-      "train_steps_per_second": 0.068
+      "train_loss": 0.0,
+      "train_runtime": 1.7052,
+      "train_samples_per_second": 29222.257,
+      "train_steps_per_second": 1826.171
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94813ecb2a33c5b400e7811558a662a9fcf98cc391aefbf4e3cfc933725373e1
+oid sha256:8b4991faf9f8db3f48d99aaa3a2ab1e0bc345711a08aadfe6dafe56ebf13c922
 size 8568