Model save

README.md

@@ -1,15 +1,15 @@
 ---
 base_model: Qwen/Qwen2.5-1.5B-Instruct
 library_name: transformers
-model_name: Qwen2.5-1.5B-Instruct-decompose
+model_name: DeepSeek-R1-Distill-Qwen-1.5B-decompose
 tags:
 - generated_from_trainer
-- sft
 - trl
+- sft
 licence: license
 ---
 
-# Model Card for Qwen2.5-1.5B-Instruct-decompose
+# Model Card for DeepSeek-R1-Distill-Qwen-1.5B-decompose
 
 This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct).
 It has been trained using [TRL](https://github.com/huggingface/trl).
@@ -20,22 +20,22 @@ It has been trained using [TRL](https://github.com/huggingface/trl).
 from transformers import pipeline
 
 question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="Renee0v0/Qwen2.5-1.5B-Instruct-decompose", device="cuda")
+generator = pipeline("text-generation", model="Renee0v0/DeepSeek-R1-Distill-Qwen-1.5B-decompose", device="cuda")
 output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
 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/ryan0v0/huggingface/runs/001rst76) 
+[<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/ryan0v0/huggingface/runs/178lepgw) 
 
 
 This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.19.1
-- Transformers: 4.54.0
+- TRL: 0.18.0
+- Transformers: 4.52.3
 - Pytorch: 2.6.0
 - Datasets: 3.6.0
 - Tokenizers: 0.21.2

all_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 5.6569864867021824e+17,
+    "train_loss": 0.2920910031773893,
+    "train_runtime": 7360.5417,
+    "train_samples": 5290,
+    "train_samples_per_second": 7.187,
+    "train_steps_per_second": 0.45
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": 151645,
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.52.3"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 5.6569864867021824e+17,
+    "train_loss": 0.2920910031773893,
+    "train_runtime": 7360.5417,
+    "train_samples": 5290,
+    "train_samples_per_second": 7.187,
+    "train_steps_per_second": 0.45
+}