diff options
| -rw-r--r-- | configs/train/zbp_n64.yaml | 16 | ||||
| -rwxr-xr-x | scripts/run_ladder.sh | 2 |
2 files changed, 18 insertions, 0 deletions
diff --git a/configs/train/zbp_n64.yaml b/configs/train/zbp_n64.yaml new file mode 100644 index 0000000..b5f87f6 --- /dev/null +++ b/configs/train/zbp_n64.yaml @@ -0,0 +1,16 @@ +mode: cd +n_probes: 64 +probe: rademacher +eps: 0.1 +probe_chunk: 8 +measure_fp32: true +tokens: 2e9 +global_batch_tokens: 524288 +lr: 6e-4 +warmup: 2000 +optimizer: adamw +wd: 0.1 +betas: [0.9, 0.95] +grad_clip: 1.0 +eval_every: 500 +seed: 0 diff --git a/scripts/run_ladder.sh b/scripts/run_ladder.sh index 4d253f1..764632a 100755 --- a/scripts/run_ladder.sh +++ b/scripts/run_ladder.sh @@ -37,6 +37,8 @@ fi for size in $SIZES; do for arm in $ARMS; do + [ -f "configs/model/$size.yaml" ] || { echo "missing configs/model/$size.yaml"; exit 1; } + [ -f "configs/train/$arm.yaml" ] || { echo "missing configs/train/$arm.yaml"; exit 1; } name="${size}_${arm}" dir="$OUT/$name" if [ -f "$dir/DONE" ]; then echo "== skip $name (done)"; continue; fi |