Files
Neo50M/training_configs/pretrain_fast.yaml

28 lines
536 B
YAML
Raw Permalink Normal View History

run:
name: neo50m_smoke
output_dir: outputs/smoke
model_config: configs/model_neo50m.yaml
data_config: configs/data_mix.yaml
seed: 1337
training:
stage: smoke
seq_len: 256
target_tokens: 1000000
micro_batch_size: 2
grad_accum: 1
learning_rate: 0.0006
min_lr_ratio: 0.1
warmup_steps: 20
weight_decay: 0.1
beta1: 0.9
beta2: 0.95
grad_clip: 1.0
eval_interval_steps: 0
eval_batches: 2
save_interval_steps: 100
keep_last_checkpoints: 2
log_interval_steps: 10
num_workers: 0
data_mode: random