Model save

README.md

@@ -0,0 +1,69 @@
+---
+base_model: mehmetkeremturkcan/SmollerLM-48M-Instruct-ft-sft
+library_name: transformers
+model_name: SmollerLM-48M-Instruct-ft-dpo
+tags:
+- generated_from_trainer
+- trl
+- dpo
+licence: license
+---
+
+# Model Card for SmollerLM-48M-Instruct-ft-dpo
+
+This model is a fine-tuned version of [mehmetkeremturkcan/SmollerLM-48M-Instruct-ft-sft](https://huggingface.co/mehmetkeremturkcan/SmollerLM-48M-Instruct-ft-sft).
+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="mehmetkeremturkcan/SmollerLM-48M-Instruct-ft-dpo", 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/mkturkcan/huggingface/runs/c50b941a) 
+
+
+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
+- Transformers: 4.46.2
+- Pytorch: 2.5.1
+- Datasets: 3.2.0
+- Tokenizers: 0.20.0
+
+## 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 +1,15 @@
+{
+    "epoch": 1.9997425003218745,
+    "eval_logits/chosen": NaN,
+    "eval_logits/rejected": -5.614200592041016,
+    "eval_logps/chosen": -668.839111328125,
+    "eval_logps/rejected": -560.14111328125,
+    "eval_loss": 0.6387723684310913,
+    "eval_rewards/accuracies": 0.6010000109672546,
+    "eval_rewards/chosen": -0.07504798471927643,
+    "eval_rewards/margins": 0.16594481468200684,
+    "eval_rewards/rejected": -0.24099276959896088,
+    "eval_runtime": 47.0636,
+    "eval_samples_per_second": 21.248,
+    "eval_steps_per_second": 2.656
+}

eval_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 1.9997425003218745,
+    "eval_logits/chosen": NaN,
+    "eval_logits/rejected": -5.614200592041016,
+    "eval_logps/chosen": -668.839111328125,
+    "eval_logps/rejected": -560.14111328125,
+    "eval_loss": 0.6387723684310913,
+    "eval_rewards/accuracies": 0.6010000109672546,
+    "eval_rewards/chosen": -0.07504798471927643,
+    "eval_rewards/margins": 0.16594481468200684,
+    "eval_rewards/rejected": -0.24099276959896088,
+    "eval_runtime": 47.0636,
+    "eval_samples_per_second": 21.248,
+    "eval_steps_per_second": 2.656
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "transformers_version": "4.46.2"
+}

runs/Jan29_17-09-09_srv4-lg2.bed.cosmos-lab.org/events.out.tfevents.1738182851.srv4-lg2.bed.cosmos-lab.org.100278.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca0a3bda4dd3137e8e22bfc863c721671b385f33294a687c2a25a32fab8eef09
+size 828