Model save

README.md

@@ -0,0 +1,58 @@
+---
+base_model: openai/gpt-oss-20b
+library_name: transformers
+model_name: gpt-oss-20b-math7k
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for gpt-oss-20b-math7k
+
+This model is a fine-tuned version of [openai/gpt-oss-20b](https://huggingface.co/openai/gpt-oss-20b).
+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="HectorHe/gpt-oss-20b-math7k", 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/hector_-carnegie-mellon-university/huggingface/runs/f38ip0il) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.18.0
+- Transformers: 4.55.2
+- Pytorch: 2.6.0
+- Datasets: 4.0.0
+- Tokenizers: 0.21.4
+
+## Citations
+
+
+
+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 Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

all_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 194968109678592.0,
+    "train_loss": 0.4934643579314845,
+    "train_runtime": 19223.4417,
+    "train_samples": 6851,
+    "train_samples_per_second": 1.069,
+    "train_steps_per_second": 0.034
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "bos_token_id": 199998,
+  "do_sample": true,
+  "eos_token_id": [
+    200002,
+    199999,
+    200012
+  ],
+  "pad_token_id": 199999,
+  "transformers_version": "4.55.2"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 194968109678592.0,
+    "train_loss": 0.4934643579314845,
+    "train_runtime": 19223.4417,
+    "train_samples": 6851,
+    "train_samples_per_second": 1.069,
+    "train_steps_per_second": 0.034
+}

training.log

@@ -1979,3 +1979,4 @@ weight_decay=0.0,
   )
   (lm_head): Linear(in_features=2880, out_features=201088, bias=False)
 )
+2025-08-14 06:14:57 - INFO - __main__ - *** Save model ***