Model save

KETI_b1_s4_e3_training_log.log

@@ -228,3 +228,4 @@
 04/02/2025 01:26:12 - INFO  - >> GPU 5: 73.18 GB used
 04/02/2025 01:26:12 - INFO  - >> Total GPU Memory Used: 449.91 GB
 04/02/2025 01:26:12 - INFO  - >> Total GPU Power Consumption: 525.56 W
+04/02/2025 01:27:03 - INFO  - ✅ Training completed in 945.87 seconds (0.26 hours)

README.md

@@ -0,0 +1,58 @@
+---
+base_model: google/gemma-3-27b-pt
+library_name: transformers
+model_name: 20250402_010937_gemma-3-27b-pt_LoRA
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for 20250402_010937_gemma-3-27b-pt_LoRA
+
+This model is a fine-tuned version of [google/gemma-3-27b-pt](https://huggingface.co/google/gemma-3-27b-pt).
+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="minyong/20250402_010937_gemma-3-27b-pt_LoRA", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.16.0
+- Transformers: 4.50.0
+- Pytorch: 2.6.0
+- Datasets: 3.1.0
+- Tokenizers: 0.21.1
+
+## 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 Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```