Model save

README.md

@@ -0,0 +1,69 @@
+---
+base_model: JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep
+library_name: transformers
+model_name: Qwen2.5-0.5B-SFT-2e-5-2ep-DPO_3e-6-3ep_0alp_0lam
+tags:
+- generated_from_trainer
+- trl
+- dpo
+licence: license
+---
+
+# Model Card for Qwen2.5-0.5B-SFT-2e-5-2ep-DPO_3e-6-3ep_0alp_0lam
+
+This model is a fine-tuned version of [JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep](https://huggingface.co/JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep).
+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="JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep-DPO_3e-6-3ep_0alp_0lam", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
+
+### Framework versions
+
+- TRL: 0.14.0.dev0
+- Transformers: 4.47.1
+- Pytorch: 2.5.1
+- Datasets: 3.2.0
+- Tokenizers: 0.21.0
+
+## Citations
+
+Cite DPO as:
+
+```bibtex
+@inproceedings{rafailov2023direct,
+    title        = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}},
+    author       = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn},
+    year         = 2023,
+    booktitle    = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},
+    url          = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html},
+    editor       = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},
+}
+```
+
+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 +1,22 @@
+{
+    "epoch": 2.999098751126561,
+    "eval_kl/chosen": 0.0006550672114826739,
+    "eval_kl/rejected": -6.322663102764636e-05,
+    "eval_logits/chosen": -1.2890625,
+    "eval_logits/rejected": -1.2578125,
+    "eval_logps/chosen": -324.0,
+    "eval_logps/rejected": -300.0,
+    "eval_loss": 0.8606816530227661,
+    "eval_nll_loss": 1.0625,
+    "eval_ref_probs/chosen": 0.0038271306548267603,
+    "eval_ref_probs/rejected": 0.0034569373819977045,
+    "eval_rejected_term/max": -6.322663102764636e-05,
+    "eval_rejected_term/min": -6.322663102764636e-05,
+    "eval_rewards/accuracies": 0.4399999976158142,
+    "eval_rewards/chosen": -0.314453125,
+    "eval_rewards/margins": -0.0654296875,
+    "eval_rewards/rejected": -0.248046875,
+    "eval_runtime": 25.5111,
+    "eval_samples_per_second": 39.199,
+    "eval_steps_per_second": 9.8
+}

eval_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 2.999098751126561,
+    "eval_kl/chosen": 0.0006550672114826739,
+    "eval_kl/rejected": -6.322663102764636e-05,
+    "eval_logits/chosen": -1.2890625,
+    "eval_logits/rejected": -1.2578125,
+    "eval_logps/chosen": -324.0,
+    "eval_logps/rejected": -300.0,
+    "eval_loss": 0.8606816530227661,
+    "eval_nll_loss": 1.0625,
+    "eval_ref_probs/chosen": 0.0038271306548267603,
+    "eval_ref_probs/rejected": 0.0034569373819977045,
+    "eval_rejected_term/max": -6.322663102764636e-05,
+    "eval_rejected_term/min": -6.322663102764636e-05,
+    "eval_rewards/accuracies": 0.4399999976158142,
+    "eval_rewards/chosen": -0.314453125,
+    "eval_rewards/margins": -0.0654296875,
+    "eval_rewards/rejected": -0.248046875,
+    "eval_runtime": 25.5111,
+    "eval_samples_per_second": 39.199,
+    "eval_steps_per_second": 9.8
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.47.1"
+}