Upload Rust v8 8GPU checkpoint ppo_v8_rust_8gpu/train_final.log 1b5b1e5 verified djmango commited on Jul 9
Upload Rust v8 8GPU checkpoint ppo_v8_rust_8gpu/metadata.json 7e4a079 verified djmango commited on Jul 9
Upload Rust v8 8GPU checkpoint ppo_v8_rust_8gpu/policy_latest.ot 316ca02 verified djmango commited on Jul 9
Upload Rust v8 8GPU checkpoint ppo_v8_rust_8gpu/policy_update200.ot 92a0510 verified djmango commited on Jul 9
v6_bc: fix - fold bc_v6/bc_best into v6-shape Policy (winner bucket) 592453a verified djmango commited on Jul 8
v6_bc: playable Policy folded from bc_v6/bc_best (winner bucket) 6a7736a verified djmango commited on Jul 8
bc_v6 freeze at step ~35600 (EDQUOT recovery; diminishing returns) b53f924 verified djmango commited on Jul 8