Skip to main content

DeepRetrieval Training Report on PubMed Search

Created on March 1|Last edited on March 1
Base Model: Qwen/Qwen2.5-3B-Instruct
Start time: February 14th, 2025 9:34:49 AM
Duration: 5d 1h 30m 55s
OS: Linux-4.18.0-553.33.1.el8_10.x86_64-x86_64-with-glibc2.28
GPU count: 2
GPU type: NVIDIA A100 80GB PCIe
Python version: Python 3.9.21


5001k1.5k2k2.5kStep2345
5001k1.5k2k2.5kStep789
5001k1.5k2k2.5kStep78910
Run: literature_search_3b_continue
1



Run: literature_search_3b_continue
1



Run: literature_search_3b_continue
1



Run: literature_search_3b_continue
1



Run: literature_search_3b_continue
1



Run: literature_search_3b_continue
1



Run: literature_search_3b_continue
1



Run: literature_search_3b_continue
1



Run: literature_search_3b_continue
1



Run: literature_search_3b_continue
1