djmango
/

openfront-rl

Reinforcement Learning

Model card Files Files and versions

openfront-rl / bc_v6

95.2 MB

Ctrl+K

Ctrl+K

1 contributor

History: 12 commits

djmango's picture

bc_v6 freeze at step ~35600 (EDQUOT recovery; diminishing returns)

b53f924 verified about 1 month ago

bc.pt
71.2 MB
xet

Upload bc_v6/bc.pt with huggingface_hub about 1 month ago
bc_best.pt
23.7 MB
xet

Upload bc_v6/bc_best.pt with huggingface_hub about 1 month ago
log.jsonl
229 kB
bc_v6 freeze at step ~35600 (EDQUOT recovery; diminishing returns) about 1 month ago