Model save

README.md

@@ -0,0 +1,58 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: transformers
+model_name: Q25-7B-IT-KoLIMO-5ep
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for Q25-7B-IT-KoLIMO-5ep
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+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="nlee-208/Q25-7B-IT-KoLIMO-5ep", 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/nlee28/reasoning/runs/8gtiz9vd) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.15.2
+- Transformers: 4.49.0
+- Pytorch: 2.5.1
+- Datasets: 3.3.2
+- Tokenizers: 0.21.0
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

all_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 1.182462262019883e+18,
+    "train_loss": 0.7659848809242249,
+    "train_runtime": 4906.2887,
+    "train_samples": 817,
+    "train_samples_per_second": 0.833,
+    "train_steps_per_second": 0.012
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.49.0"
+}

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:490b0030cfca7c08d8cf8804cbd47b86827ab43a4b9eb39bda23ce7601e85858
+oid sha256:bb45fc18887eae393822c2a306fd3ca001457d48ea05bd0534c04252afb4cdff
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87cb31fb5c7b43ae01f2fc3986bec8ef6a9d40aa01b1413fb50636bab8f2f08a
+oid sha256:6da069948cdf1bbbd573df38cd8dd40105e6ba87125be455bcf3e6ff7cc4613c
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1f40b281abf13f6f61b2cf6e8e1b825af8a5996f8a27e96e6f616b2300ca450
+oid sha256:2614d88abf9d599b47e7c37110e746667cd4f257a6e53fe6f4d13b24be70e621
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1100059206f491801c3c11d81d837e38044ed5781f51bde1a5f7e9211c428c03
+oid sha256:c024156a452187f567fd5fef2219bf6a24798cb642f9edb3cddf2765bf32320b
 size 1089994880

runs/Feb27_05-01-29_node0/events.out.tfevents.1740632561.node0.10371.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34cbcc7320fc4e7f04e46c96f6396fe5a403f187c19478b17a256d2b48947bf5
-size 12040
+oid sha256:11625d203d6cecfc9242d93593d28b8d8dfaebaf1a94951e84b119f1ed3505e9
+size 14008

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 1.182462262019883e+18,
+    "train_loss": 0.7659848809242249,
+    "train_runtime": 4906.2887,
+    "train_samples": 817,
+    "train_samples_per_second": 0.833,
+    "train_steps_per_second": 0.012
+}