Bagheera Bghira
v1: from ptx0/coco-xltest, 36000 + 21800 + 14200 steps of mixed LAION/MJ dataset and offset noise with input perturbation on a probability of 25%, 10% caption dropout, cosine LR 4e-7 to 8e-7 every 3200 steps
90816e1
| { | |
| "bos_token": { | |
| "content": "<|startoftext|>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "eos_token": { | |
| "content": "<|endoftext|>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "pad_token": "<|endoftext|>", | |
| "unk_token": { | |
| "content": "<|endoftext|>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| } | |
| } | |