File size: 1,786 Bytes
d04a061 f211cf7 d04a061 f211cf7 d04a061 f211cf7 d04a061 f211cf7 d04a061 f211cf7 d04a061 f211cf7 d04a061 f211cf7 d04a061 f211cf7 d04a061 f211cf7 d04a061 f211cf7 d04a061 f211cf7 d04a061 f211cf7 d04a061 f211cf7 d04a061 f211cf7 d04a061 f211cf7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 |
seed: 42
base_dir: /scratch/pranamlab/sgoel/MeMDLM_v2
lm:
pretrained_esm: facebook/esm2_t33_650M_UR50D
pretrained_evoflow: fredzzp/EvoFlow-650M-context-3070
pretrained_dplm: airkingbd/dplm_650m
ft_evoflow: ft_eflow-3070-650M_steps=5k_layers=3_lr=1e-5_lr-end=2e-6_wd=.01_polynom_pwr=1_betas=.9-.98_bsz=8_gclip=1.0_ml=1024
ft_dplm: ft_dplm-650M_steps=5k_layers=3_lr=0.00004_wd=.01_polynom_pwr=1_betas=.9-.98_bsz=32_gclip=1.0
model:
esm_dim: 1280
d_model: 128
num_heads: 2
dropout: 0.3
num_layers: 1
label_pad_value: -100
optim:
type: adamw
lr: 1e-4
lr_end: 1e-5
weight_decay: 0.02
beta1: 0.9
beta2: 0.98
power: 1
training:
mode: test # train / test
n_layers: 4
max_steps: 3000
warmup_steps: 200
log_every_n_steps: 10
num_sanity_val_steps: 2
val_check_interval: 100
enable_progress_bar: true
grad_clip_val: 1.0
devices: 2
guidance:
n_steps: 128
alpha: 3
gamma: 0.3
saliency_eps: 1e-4
saliency_t: 2.0
sampling_t: 0.7
boltzmann_t: 0.3
top_p: 0.2
steps: 128
prior: lm_probs # lm_probs / boltzmann
olig_guidance:
guide_steps: 12
diffusion_steps: 64
reg_strength: 1
step_size: 0.1
temperature: 1.0
eps: 1e-8
residue_thresh: 0.5
topk_frac: 0.2
data:
batch_size: 64
max_seq_len: 54
train: ${base_dir}/data/olig_clf/train.csv
test: ${base_dir}/data/olig_clf/test.csv
val: ${base_dir}/data/olig_clf/val.csv
wandb:
project: memdlm_oligo
group: programmablebio
name: oligo-clf_steps3k_lr1e-4_bsz64_drpt0.3_wd0.02_dmodel128_simple-mlp_mean-pool
id: ${.name}_${seed}
checkpointing:
save_every_n_steps: 250
save_dir: ${base_dir}/checkpoints/${wandb.name}
resume_ckpt_path: ${checkpointing.save_dir}/last.ckpt
best_ckpt_path: ${checkpointing.save_dir}/best_model.ckpt
|