Model save

README.md

@@ -1,11 +1,9 @@
 ---
-base_model: Qwen/Qwen2.5-1.5B-Instruct
-datasets: open-r1/OpenR1-Math-220k
+base_model: llm-jp/llm-jp-3-3.7b-instruct
 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 [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-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/h3iwf5ur) 
+[<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) 
 
 
 This model was trained with SFT.
@@ -37,9 +35,9 @@ This model was trained with SFT.
 ### Framework versions
 
 - TRL: 0.16.0.dev0
-- Transformers: 4.49.0.dev0
+- Transformers: 4.49.0
 - Pytorch: 2.5.1
-- Datasets: 3.3.0
+- Datasets: 3.3.2
 - Tokenizers: 0.21.0
 
 ## Citations

all_results.json

@@ -1,8 +1,8 @@
 {
-    "total_flos": 488621249396736.0,
-    "train_loss": 0.5610741035484555,
-    "train_runtime": 6486.6391,
+    "total_flos": 588699087667200.0,
+    "train_loss": 0.7670444376984535,
+    "train_runtime": 29567.5701,
     "train_samples": 93733,
-    "train_samples_per_second": 5.288,
-    "train_steps_per_second": 0.083
+    "train_samples_per_second": 18.507,
+    "train_steps_per_second": 0.145
 }

generation_config.json

@@ -1,14 +1,6 @@
 {
-  "bos_token_id": 151643,
-  "do_sample": true,
-  "eos_token_id": [
-    151645,
-    151643
-  ],
-  "pad_token_id": 151643,
-  "repetition_penalty": 1.1,
-  "temperature": 0.7,
-  "top_k": 20,
-  "top_p": 0.8,
-  "transformers_version": "4.49.0.dev0"
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.49.0"
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "total_flos": 488621249396736.0,
-    "train_loss": 0.5610741035484555,
-    "train_runtime": 6486.6391,
+    "total_flos": 588699087667200.0,
+    "train_loss": 0.7670444376984535,
+    "train_runtime": 29567.5701,
     "train_samples": 93733,
-    "train_samples_per_second": 5.288,
-    "train_steps_per_second": 0.083
+    "train_samples_per_second": 18.507,
+    "train_steps_per_second": 0.145
 }