Model save

README.md

@@ -1,11 +1,9 @@
 ---
 base_model: flyingbugs/Qwen2.5-Math-7B-Instruct
-datasets: flyingbugs/OpenR1-Math-220k-pruned-keep-0.4-end-start-0.5-acc
 library_name: transformers
 model_name: Qwen2.5-Math-7B-Instruct-Math220k-acc-0.4
 tags:
 - generated_from_trainer
-- open-r1
 - trl
 - sft
 licence: license
@@ -13,7 +11,7 @@ licence: license
 
 # Model Card for Qwen2.5-Math-7B-Instruct-Math220k-acc-0.4
 
-This model is a fine-tuned version of [flyingbugs/Qwen2.5-Math-7B-Instruct](https://huggingface.co/flyingbugs/Qwen2.5-Math-7B-Instruct) on the [flyingbugs/OpenR1-Math-220k-pruned-keep-0.4-end-start-0.5-acc](https://huggingface.co/datasets/flyingbugs/OpenR1-Math-220k-pruned-keep-0.4-end-start-0.5-acc) dataset.
+This model is a fine-tuned version of [flyingbugs/Qwen2.5-Math-7B-Instruct](https://huggingface.co/flyingbugs/Qwen2.5-Math-7B-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/jjh233/huggingface/runs/h7afgvyi) 
+[<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/jjh233/huggingface/runs/ax6orkva) 
 
 
 This model was trained with SFT.
@@ -39,7 +37,7 @@ This model was trained with SFT.
 - TRL: 0.16.0.dev0
 - Transformers: 4.51.3
 - Pytorch: 2.5.1
-- Datasets: 3.5.0
+- Datasets: 3.5.1
 - Tokenizers: 0.21.1
 
 ## Citations

all_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 2.074186974392379e+19,
-    "train_loss": 0.4476111942836326,
-    "train_runtime": 54710.37,
+    "train_loss": 0.0,
+    "train_runtime": 2.0281,
     "train_samples": 93733,
-    "train_samples_per_second": 0.546,
-    "train_steps_per_second": 0.034
+    "train_samples_per_second": 14722.581,
+    "train_steps_per_second": 920.069
 }

config.json

@@ -22,7 +22,7 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.51.3",
-  "use_cache": true,
+  "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 152064
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 2.074186974392379e+19,
-    "train_loss": 0.4476111942836326,
-    "train_runtime": 54710.37,
+    "train_loss": 0.0,
+    "train_runtime": 2.0281,
     "train_samples": 93733,
-    "train_samples_per_second": 0.546,
-    "train_steps_per_second": 0.034
+    "train_samples_per_second": 14722.581,
+    "train_steps_per_second": 920.069
 }

trainer_state.json

@@ -13075,10 +13075,10 @@
       "epoch": 2.995983935742972,
       "step": 1866,
       "total_flos": 2.074186974392379e+19,
-      "train_loss": 0.4476111942836326,
-      "train_runtime": 54710.37,
-      "train_samples_per_second": 0.546,
-      "train_steps_per_second": 0.034
+      "train_loss": 0.0,
+      "train_runtime": 2.0281,
+      "train_samples_per_second": 14722.581,
+      "train_steps_per_second": 920.069
     }
   ],
   "logging_steps": 1,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f779950e8181487f62770f29c1ca519d674111423a591fc26e192e08d58e82e
+oid sha256:139397af30de64c5b4dbc96de5303d534cd1d83f94368d66b1243ea3277972b9
 size 7480