Model save

README.md

@@ -0,0 +1,68 @@
+---
+base_model: Qwen/Qwen2.5-Math-7B
+library_name: transformers
+model_name: Qwen-2.5-7B-RL-LACPO-NoBaselineNoKLNoEntropy0.5NoSmooth
+tags:
+- generated_from_trainer
+- trl
+- grpo
+licence: license
+---
+
+# Model Card for Qwen-2.5-7B-RL-LACPO-NoBaselineNoKLNoEntropy0.5NoSmooth
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-Math-7B](https://huggingface.co/Qwen/Qwen2.5-Math-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="luckeciano/Qwen-2.5-7B-RL-LACPO-NoBaselineNoKLNoEntropy0.5NoSmooth", 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/max-ent-llms/MaxEntLLMs/runs/y4gzesyz) 
+
+
+This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
+
+### Framework versions
+
+- TRL: 0.16.0.dev0
+- Transformers: 4.49.0
+- Pytorch: 2.5.1
+- Datasets: 3.4.1
+- Tokenizers: 0.21.1
+
+## Citations
+
+Cite GRPO as:
+
+```bibtex
+@article{zhihong2024deepseekmath,
+    title        = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
+    author       = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
+    year         = 2024,
+    eprint       = {arXiv:2402.03300},
+}
+
+```
+
+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": 0.0,
+    "train_loss": -0.7872485533738748,
+    "train_runtime": 25817.0423,
+    "train_samples": 7500,
+    "train_samples_per_second": 0.291,
+    "train_steps_per_second": 0.002
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.49.0"
+}

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28f80a99de804f76d2829f567a47da2b4f7bd32e10a6fe151984ffbe0f358abe
+oid sha256:4bde858d8554b6aef5165e28358b8cec459b892c43eb013b9f9092581129421b
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cadda52e7dd36d947526901564c96aab652814d6f037e9e18f5e2c639b42bbc
+oid sha256:47cd71dd1c8af6c8f0009b364590c3cb34bdf9411aaf7062871f6cce93b9b3b5
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2371fe38a7a1e3c2de25029bb2a79ef2f9311341738586822662d3834fbdf156
+oid sha256:9954df8adcc1ff74e4c3b4cc6b0e9855e14a9e467ba7d673aef6c4dc224239ca
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:864204d2b2d7c6b6b5549a95338d0e93bd042fb9901ee04a765baad6993c1d44
+oid sha256:64e51fcd83b9bcfcb9f3fa3c246b06efdc5f695c99c6caa2b80266b9d30d82ce
 size 1089994880

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 0.0,
+    "train_loss": -0.7872485533738748,
+    "train_runtime": 25817.0423,
+    "train_samples": 7500,
+    "train_samples_per_second": 0.291,
+    "train_steps_per_second": 0.002
+}