Model save

README.md

@@ -1,10 +1,8 @@
 ---
-datasets: RLHFlow/numia_prompt_dpo1
 library_name: transformers
 model_name: Llama-3.2-3B-Instruct-EMPO-numia_prompt_dpo1
 tags:
 - generated_from_trainer
-- open-r1
 - trl
 - grpo
 licence: license
@@ -12,7 +10,7 @@ licence: license
 
 # Model Card for Llama-3.2-3B-Instruct-EMPO-numia_prompt_dpo1
 
-This model is a fine-tuned version of [None](https://huggingface.co/None) on the [RLHFlow/numia_prompt_dpo1](https://huggingface.co/datasets/RLHFlow/numia_prompt_dpo1) 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/tjucsailab/huggingface/runs/fr5idqzr) 
+[<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/tjucsailab/huggingface/runs/2xifc66f) 
 
 
 This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).

all_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.0,
-    "train_runtime": 9.4816,
+    "train_loss": 5.786010212772085e-09,
+    "train_runtime": 7433.3342,
     "train_samples": 20000,
-    "train_samples_per_second": 2109.35,
-    "train_steps_per_second": 43.874
+    "train_samples_per_second": 2.691,
+    "train_steps_per_second": 0.024
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b31a06f6d89625f2567a1f724d50f68b28ca2fe67d5e40c532d46c8ec9ef9aed
+oid sha256:90d5f4c5c49db2a9e71c87b04e881a899ca4794d61231c8574892ad2d694ed74
 size 4965799096

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21cb2a01569769b11882daab4fc2fb511508e748fd741d2b92f0fdb8d13461d1
+oid sha256:fa0d27fd5d96dc7c6804eaac598601645a07c50bc0af51b8fad02fc64bedeb47
 size 1459729952

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.0,
-    "train_runtime": 9.4816,
+    "train_loss": 5.786010212772085e-09,
+    "train_runtime": 7433.3342,
     "train_samples": 20000,
-    "train_samples_per_second": 2109.35,
-    "train_steps_per_second": 43.874
+    "train_samples_per_second": 2.691,
+    "train_steps_per_second": 0.024
 }