Model save

README.md

@@ -1,10 +1,8 @@
 ---
-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
@@ -12,7 +10,7 @@ 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 [open-r1/OpenR1-Math-220k](https://huggingface.co/datasets/open-r1/OpenR1-Math-220k) 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
@@ -28,7 +26,7 @@ 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/648848014/huggingface/runs/94h4qzbt) 
+[<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/648848014/huggingface/runs/3n5lktnf) 
 
 
 This model was trained with SFT.

all_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 2.5375909456379904e+17,
-    "train_loss": 0.8519784138752864,
-    "train_runtime": 3243.3529,
+    "train_loss": 0.0,
+    "train_runtime": 2.0428,
     "train_samples": 3472,
-    "train_samples_per_second": 0.607,
-    "train_steps_per_second": 0.04
+    "train_samples_per_second": 964.355,
+    "train_steps_per_second": 63.638
 }

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": 2.5375909456379904e+17,
-    "train_loss": 0.8519784138752864,
-    "train_runtime": 3243.3529,
+    "train_loss": 0.0,
+    "train_runtime": 2.0428,
     "train_samples": 3472,
-    "train_samples_per_second": 0.607,
-    "train_steps_per_second": 0.04
+    "train_samples_per_second": 964.355,
+    "train_steps_per_second": 63.638
 }

trainer_state.json

@@ -194,10 +194,10 @@
       "epoch": 10.0,
       "step": 130,
       "total_flos": 2.5375909456379904e+17,
-      "train_loss": 0.8519784138752864,
-      "train_runtime": 3243.3529,
-      "train_samples_per_second": 0.607,
-      "train_steps_per_second": 0.04
+      "train_loss": 0.0,
+      "train_runtime": 2.0428,
+      "train_samples_per_second": 964.355,
+      "train_steps_per_second": 63.638
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a17fee46534f3b0ec08271a60c4aa683765916504169cea34626699f7f792ee
+oid sha256:8059c50bedd31a2ed36ddf1aa09cc4ef20113c535f90c427a63405d23bc104e2
 size 6264