Model save

README.md

@@ -1,11 +1,9 @@
 ---
 base_model: llm-jp/llm-jp-3-3.7b-instruct
-datasets: open-r1/OpenR1-Math-220k
 library_name: transformers
 model_name: llm-jp-3-3.7b-Open-R1-Distill
 tags:
 - generated_from_trainer
-- open-r1
 - trl
 - sft
 licence: license
@@ -13,7 +11,7 @@ licence: license
 
 # Model Card for llm-jp-3-3.7b-Open-R1-Distill
 
-This model is a fine-tuned version of [llm-jp/llm-jp-3-3.7b-instruct](https://huggingface.co/llm-jp/llm-jp-3-3.7b-instruct) 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 [llm-jp/llm-jp-3-3.7b-instruct](https://huggingface.co/llm-jp/llm-jp-3-3.7b-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/kawamuramasaki/open-r1/runs/imxqbpbu) 
+[<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/kawamuramasaki/open-r1/runs/f74wyxlh) 
 
 
 This model was trained with SFT.

all_results.json

@@ -1,8 +1,8 @@
 {
-    "total_flos": 588699087667200.0,
-    "train_loss": 0.7670444376984535,
-    "train_runtime": 29567.5701,
+    "total_flos": 590489283723264.0,
+    "train_loss": 1.0968534403772496,
+    "train_runtime": 7318.0016,
     "train_samples": 93733,
-    "train_samples_per_second": 18.507,
-    "train_steps_per_second": 0.145
+    "train_samples_per_second": 4.68,
+    "train_steps_per_second": 0.037
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "total_flos": 588699087667200.0,
-    "train_loss": 0.7670444376984535,
-    "train_runtime": 29567.5701,
+    "total_flos": 590489283723264.0,
+    "train_loss": 1.0968534403772496,
+    "train_runtime": 7318.0016,
     "train_samples": 93733,
-    "train_samples_per_second": 18.507,
-    "train_steps_per_second": 0.145
+    "train_samples_per_second": 4.68,
+    "train_steps_per_second": 0.037
 }