Model save

README.md

@@ -0,0 +1,67 @@
+---
+base_model: google/gemma-7b
+library_name: transformers
+model_name: gemma-7b-cpo-basic_long-5e-5-05-v120
+tags:
+- generated_from_trainer
+- trl
+- orpo
+licence: license
+---
+
+# Model Card for gemma-7b-cpo-basic_long-5e-5-05-v120
+
+This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b).
+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="silviasapora/gemma-7b-cpo-basic_long-5e-5-05-v120", 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/silvias/huggingface/runs/n8x4azrl) 
+
+
+This model was trained with ORPO, a method introduced in [ORPO: Monolithic Preference Optimization without Reference Model](https://huggingface.co/papers/2403.07691).
+
+### Framework versions
+
+- TRL: 0.15.2
+- Transformers: 4.49.0
+- Pytorch: 2.5.1
+- Datasets: 3.1.0
+- Tokenizers: 0.21.1
+
+## Citations
+
+Cite ORPO as:
+
+```bibtex
+@article{hong2024orpo,
+    title        = {{ORPO: Monolithic Preference Optimization without Reference Model}},
+    author       = {Jiwoo Hong and Noah Lee and James Thorne},
+    year         = 2024,
+    eprint       = {arXiv:2403.07691}
+}
+```
+
+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 +1,9 @@
+{
+    "epoch": 0.9990156096189003,
+    "total_flos": 0.0,
+    "train_loss": 29.51147762504784,
+    "train_runtime": 15990.0341,
+    "train_samples": 56888,
+    "train_samples_per_second": 3.558,
+    "train_steps_per_second": 0.056
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9990156096189003,
+    "total_flos": 0.0,
+    "train_loss": 29.51147762504784,
+    "train_runtime": 15990.0341,
+    "train_samples": 56888,
+    "train_samples_per_second": 3.558,
+    "train_steps_per_second": 0.056
+}