Delta-Vector
/

distill-m-6a3lnzvb-code

Model card Files Files and versions

distill-m-6a3lnzvb-code / configs

24.4 kB

Ctrl+K

Ctrl+K

1 contributor

History: 8 commits

Delta-Vector's picture

add phase-2 ultra-conservative sweep (J,K,L,M) + waiter that auto-launches after phase 1 from the best ckpt

729546e verified about 2 months ago

sweep
add phase-2 ultra-conservative sweep (J,K,L,M) + waiter that auto-launches after phase 1 from the best ckpt about 2 months ago
accelerate.yaml

334 Bytes
initial scaffold: distill.py + base/zero_14_17 configs + accelerate yaml about 2 months ago
base.toml

1.23 kB
add 9-config hparam sweep + new_layer_lr_mul param-groups support about 2 months ago
grow40_simple.toml

1.3 kB
add 9-config hparam sweep + new_layer_lr_mul param-groups support about 2 months ago
grow40_winning.toml

1.42 kB
add 9-config hparam sweep + new_layer_lr_mul param-groups support about 2 months ago
grow40_winning_v2.toml

1.36 kB
add 9-config hparam sweep + new_layer_lr_mul param-groups support about 2 months ago
replicate_zero4.toml

1.28 kB
add 9-config hparam sweep + new_layer_lr_mul param-groups support about 2 months ago
zero_14_17.toml

1.29 kB
add 9-config hparam sweep + new_layer_lr_mul param-groups support about 2 months ago