Model save

README.md

@@ -1,11 +1,9 @@
 ---
 base_model: Qwen/Qwen2.5-Math-1.5B
-datasets: open-r1/Mixture-of-Thoughts
 library_name: transformers
 model_name: OpenR1-Distill-1.5B
 tags:
 - generated_from_trainer
-- open-r1
 - trl
 - sft
 licence: license
@@ -13,7 +11,7 @@ licence: license
 
 # Model Card for OpenR1-Distill-1.5B
 
-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 [open-r1/Mixture-of-Thoughts](https://huggingface.co/datasets/open-r1/Mixture-of-Thoughts) 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/erxin/huggingface/runs/3yf4ea9k) 
+[<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/erxin/huggingface/runs/b44q077d) 
 
 
 This model was trained with SFT.

all_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 3095443507642368.0,
-    "train_loss": 0.40876835717547333,
-    "train_runtime": 153672.2596,
+    "train_loss": 0.0,
+    "train_runtime": 1.5969,
     "train_samples": 93733,
-    "train_samples_per_second": 1.83,
-    "train_steps_per_second": 0.029
+    "train_samples_per_second": 176085.951,
+    "train_steps_per_second": 2752.136
 }

config.json

@@ -22,7 +22,7 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.52.3",
-  "use_cache": true,
+  "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 3095443507642368.0,
-    "train_loss": 0.40876835717547333,
-    "train_runtime": 153672.2596,
+    "train_loss": 0.0,
+    "train_runtime": 1.5969,
     "train_samples": 93733,
-    "train_samples_per_second": 1.83,
-    "train_steps_per_second": 0.029
+    "train_samples_per_second": 176085.951,
+    "train_steps_per_second": 2752.136
 }

trainer_state.json

@@ -35173,10 +35173,10 @@
       "epoch": 3.0,
       "step": 4395,
       "total_flos": 3095443507642368.0,
-      "train_loss": 0.40876835717547333,
-      "train_runtime": 153672.2596,
-      "train_samples_per_second": 1.83,
-      "train_steps_per_second": 0.029
+      "train_loss": 0.0,
+      "train_runtime": 1.5969,
+      "train_samples_per_second": 176085.951,
+      "train_steps_per_second": 2752.136
     }
   ],
   "logging_steps": 1,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:520380e29d6ae59e97af08b3e7fabd37eeec09a2c96704beccb17de2c7f3d664
+oid sha256:a0709d9aa7c008433d83d5cd484d90901e491262ee9faadb1f217cd107b6b483
 size 12152