Spaces:

HerrHruby
/

mr-v6-9b-rollout-compare

Running

App Files Files Community

mr-v6-9b-rollout-compare / data

23.4 MB

Ctrl+K

1 contributor

History: 1 commit

HerrHruby

v6 9B rollout comparison: SFT vs RL step 150 vs RL step 250 (10 problems, sample 0, depth 8 x width 6)

2a3f489 verified 1 day ago

index.json

21.8 kB
v6 9B rollout comparison: SFT vs RL step 150 vs RL step 250 (10 problems, sample 0, depth 8 x width 6) 1 day ago
p00__s150.json

555 kB
v6 9B rollout comparison: SFT vs RL step 150 vs RL step 250 (10 problems, sample 0, depth 8 x width 6) 1 day ago
p00__s250.json

414 kB
v6 9B rollout comparison: SFT vs RL step 150 vs RL step 250 (10 problems, sample 0, depth 8 x width 6) 1 day ago
p00__sft.json

1.48 MB
v6 9B rollout comparison: SFT vs RL step 150 vs RL step 250 (10 problems, sample 0, depth 8 x width 6) 1 day ago
p01__s150.json

507 kB
v6 9B rollout comparison: SFT vs RL step 150 vs RL step 250 (10 problems, sample 0, depth 8 x width 6) 1 day ago
p01__s250.json

425 kB
v6 9B rollout comparison: SFT vs RL step 150 vs RL step 250 (10 problems, sample 0, depth 8 x width 6) 1 day ago
p01__sft.json

1.69 MB
v6 9B rollout comparison: SFT vs RL step 150 vs RL step 250 (10 problems, sample 0, depth 8 x width 6) 1 day ago
p02__s150.json

1.37 MB
v6 9B rollout comparison: SFT vs RL step 150 vs RL step 250 (10 problems, sample 0, depth 8 x width 6) 1 day ago
p02__s250.json

179 kB
v6 9B rollout comparison: SFT vs RL step 150 vs RL step 250 (10 problems, sample 0, depth 8 x width 6) 1 day ago
p02__sft.json

1.43 MB
v6 9B rollout comparison: SFT vs RL step 150 vs RL step 250 (10 problems, sample 0, depth 8 x width 6) 1 day ago
p03__s150.json

750 kB
v6 9B rollout comparison: SFT vs RL step 150 vs RL step 250 (10 problems, sample 0, depth 8 x width 6) 1 day ago
p03__s250.json

389 kB
v6 9B rollout comparison: SFT vs RL step 150 vs RL step 250 (10 problems, sample 0, depth 8 x width 6) 1 day ago
p03__sft.json

1.47 MB
v6 9B rollout comparison: SFT vs RL step 150 vs RL step 250 (10 problems, sample 0, depth 8 x width 6) 1 day ago
p04__s150.json

259 kB
v6 9B rollout comparison: SFT vs RL step 150 vs RL step 250 (10 problems, sample 0, depth 8 x width 6) 1 day ago
p04__s250.json

456 kB
v6 9B rollout comparison: SFT vs RL step 150 vs RL step 250 (10 problems, sample 0, depth 8 x width 6) 1 day ago
p04__sft.json

1.57 MB
v6 9B rollout comparison: SFT vs RL step 150 vs RL step 250 (10 problems, sample 0, depth 8 x width 6) 1 day ago
p05__s150.json

1.02 MB
v6 9B rollout comparison: SFT vs RL step 150 vs RL step 250 (10 problems, sample 0, depth 8 x width 6) 1 day ago
p05__s250.json

362 kB
v6 9B rollout comparison: SFT vs RL step 150 vs RL step 250 (10 problems, sample 0, depth 8 x width 6) 1 day ago
p05__sft.json

1.12 MB
v6 9B rollout comparison: SFT vs RL step 150 vs RL step 250 (10 problems, sample 0, depth 8 x width 6) 1 day ago
p06__s150.json

953 kB
v6 9B rollout comparison: SFT vs RL step 150 vs RL step 250 (10 problems, sample 0, depth 8 x width 6) 1 day ago
p06__s250.json

316 kB
v6 9B rollout comparison: SFT vs RL step 150 vs RL step 250 (10 problems, sample 0, depth 8 x width 6) 1 day ago
p06__sft.json

1 MB
v6 9B rollout comparison: SFT vs RL step 150 vs RL step 250 (10 problems, sample 0, depth 8 x width 6) 1 day ago
p07__s150.json

1.01 MB
v6 9B rollout comparison: SFT vs RL step 150 vs RL step 250 (10 problems, sample 0, depth 8 x width 6) 1 day ago
p07__s250.json

417 kB
v6 9B rollout comparison: SFT vs RL step 150 vs RL step 250 (10 problems, sample 0, depth 8 x width 6) 1 day ago
p07__sft.json

1.23 MB
v6 9B rollout comparison: SFT vs RL step 150 vs RL step 250 (10 problems, sample 0, depth 8 x width 6) 1 day ago
p08__s150.json

436 kB
v6 9B rollout comparison: SFT vs RL step 150 vs RL step 250 (10 problems, sample 0, depth 8 x width 6) 1 day ago
p08__s250.json

131 kB
v6 9B rollout comparison: SFT vs RL step 150 vs RL step 250 (10 problems, sample 0, depth 8 x width 6) 1 day ago
p08__sft.json

280 kB
v6 9B rollout comparison: SFT vs RL step 150 vs RL step 250 (10 problems, sample 0, depth 8 x width 6) 1 day ago
p09__s150.json

521 kB
v6 9B rollout comparison: SFT vs RL step 150 vs RL step 250 (10 problems, sample 0, depth 8 x width 6) 1 day ago
p09__s250.json

376 kB
v6 9B rollout comparison: SFT vs RL step 150 vs RL step 250 (10 problems, sample 0, depth 8 x width 6) 1 day ago
p09__sft.json

1.22 MB
v6 9B rollout comparison: SFT vs RL step 150 vs RL step 250 (10 problems, sample 0, depth 8 x width 6) 1 day ago