AjayP13's picture
Super-squash branch 'main' using huggingface_hub
442540c verified
name: fineinstructions_ipt_synthetic_all_exp
dump_dir: /fsx/craffel/fineinstructions/pretraining/ipt_synthetic_all_exp/
seed: 777
grad_acc_steps: 8
gc_collect_freq: 1000
probe_freq: null
steps: 22000
data:
root_dir: /scratch/craffel/lingua/data/fineinstructions/
sources:
ipt_synthetic_all_exp: 1.0
batch_size: 4
seq_len: 4096
n_views: 2
seed: 42
add_bos: true
add_eos: true
load_async: true
prefetch_size: 1024
tokenizer:
name: tiktoken
path: /fsx/craffel/lingua/tokenizers/llama3.model
n_words: null
optim:
lr: 0.001
weight_decay: 0.1
epsilon: 1.0e-08
beta1: 0.9
beta2: 0.95
clip: 1.0
scheduler: cosine
warmup: 2000
lr_min_ratio: 1.0e-06
cycle_length: 1.0
cosine_theta: 1.0
annealing_step: 1000
decay_fraction: 0.1
exp_factor: 0.5
model:
dim: 2048
n_layers: 25
head_dim: null
n_heads: 16
n_kv_heads: null
ffn_dim_multiplier: null
multiple_of: 256
norm_eps: 1.0e-05
rope_theta: 10000.0
init_base_std: null
init_std_factor: disabled
max_seqlen: 4096
seed: 42
vocab_size: 128256
weight_tying: false
sliding_window: null
distributed:
dp_shard: 1
dp_replicate: 8
tp_size: 1
selective_activation_checkpointing: false
compile: true
fsdp_type: full_shard
model_dtype: bf16
float8_recipe: null
float8_filter: layers\.[0-9]+\.
matmul_allow_tf32: false
detect_anomaly: false
compile_cache_size_limit: 8
spawn_method: forkserver
env:
MKL_SERVICE_FORCE_INTEL: GNU
OMP_NUM_THREADS: '1'
MKL_NUM_THREADS: '1'
ENABLE_INTRA_NODE_COMM: '1'
TORCH_NCCL_AVOID_RECORD_STREAMS: '1'
NCCL_IB_TIMEOUT: '22'
NCCL_DEBUG: INFO
TORCH_NCCL_ASYNC_ERROR_HANDLING: '1'
checkpoint:
dump:
every: 2000
keep: -1
eval:
every: 2000
keep: -1
path: /fsx/craffel/fineinstructions/pretraining/ipt_synthetic_all_exp/checkpoints
init_ckpt_path: null
load_init_optimizer_state: false
save_init_ckpt: false
profiling:
run: true
trace_folder: profiling
mem_warmup: 0
mem_steps: 4
profile_warmup: 100
profile_steps: 4
logging:
freq: 1
acc_freq: null
wandb: null
async_eval_gpus: 8
eval:
harness:
tasks:
- hellaswag
- mmlu
- commonsense_qa
- sciq
confirm_run_unsafe_code: true
generator:
max_tokens: 8192
dtype: bf16