[Submit Model] <convnext_L>

{"date": "24/11/2022",
"extra_data": "yes imagenet_v2",
"model": "Adversarial Training",
"institution": "MIT",
"paper_link": "https://arxiv.org/abs/2201.03545",
"code_link": "",
"architecture": "convnext_L",
"training framework": "easyrobust (v1)",
"ImageNet-val": TODO,
"autoattack": TODO,
"files": "download",
"advrob_imgcls_leaderboard": true,
"oodrob_imgcls_leaderboard": false,
"advrob_objdet_leaderboard": false,
"oodrob_objdet_leaderboard": false}

Start by reviewing the submission fields in the issue body, the linked paper, and the downloadable ConvNeXt-L checkpoint. Determine the missing ImageNet-val and AutoAttack values and verify the architecture and training-framework details; done means the TODO fields and submission metadata are complete.

Written by the indexing model from the issue text.