Model save

README.md

@@ -0,0 +1,66 @@
+---
+base_model: meta-llama/Llama-3.2-3B
+library_name: transformers
+model_name: llama3.2-3b-orpo-finegrained
+tags:
+- generated_from_trainer
+- trl
+- orpo
+licence: license
+---
+
+# Model Card for llama3.2-3b-orpo-finegrained
+
+This model is a fine-tuned version of [meta-llama/Llama-3.2-3B](https://huggingface.co/meta-llama/Llama-3.2-3B).
+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="CriteriaPO/llama3.2-3b-orpo-finegrained", 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/bborges/CriteriaPreferences/runs/q3omw6ho)
+
+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: 0.12.2
+- Transformers: 4.46.3
+- Pytorch: 2.1.2+cu121
+- Datasets: 3.1.0
+- Tokenizers: 0.20.3
+
+## 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": 0.9999635926748461,
+    "total_flos": 0.0,
+    "train_loss": 0.824514170289517,
+    "train_runtime": 95775.3447,
+    "train_samples": 1757879,
+    "train_samples_per_second": 18.354,
+    "train_steps_per_second": 0.143
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.46.3"
+}

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ffb64ba8efcbca01071ced69d84a0b8f0adf6e95c42425e0de2654b4818125d
+oid sha256:4719f522b43d4e280c32ff5835d1e17987fa939843d99b56488a41b37565ae54
 size 4965799096

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e2d9c9b7bbceabfef615f52f6ef722fea1132a3dc248459fb365df425cbcc3a
+oid sha256:2efe6e17f0b24e1297fec3746df243df90a344092d15b36639a518c327730914
 size 1459729952

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9999635926748461,
+    "total_flos": 0.0,
+    "train_loss": 0.824514170289517,
+    "train_runtime": 95775.3447,
+    "train_samples": 1757879,
+    "train_samples_per_second": 18.354,
+    "train_steps_per_second": 0.143
+}