neox-ckpt-pythia-70m-deduped-v0 / pythia-19Mnew.yml
hails's picture
Upload pythia-19Mnew.yml
bc31a64
raw
history blame
2.52 kB
{
"pipe-parallel-size": 1,
"model-parallel-size": 1,
# model settings
"num-layers": 6,
"hidden-size": 512,
"num-attention-heads": 8,
"seq-length": 2048,
"max-position-embeddings": 2048,
"pos-emb": "rotary",
"rotary-pct": 0.25,
"no-weight-tying": true,
"gpt-j-residual": true,
"output-layer-parallelism": "column",
"scaled-upper-triang-masked-softmax-fusion": true,
"bias-gelu-fusion": true,
# init methods
"init_method": "small_init",
"output_layer_init_method": "wang_init",
"optimizer": {
"type": "Adam",
"params": {
"lr": 0.001,
"betas": [0.9, 0.95],
"eps": 1.0e-8,
}
},
"min_lr": 0.0001,
"zero_optimization": {
"stage": 1,
"allgather_partitions": True,
"allgather_bucket_size": 500000000,
"overlap_comm": True,
"reduce_scatter": True,
"reduce_bucket_size": 500000000,
"contiguous_gradients": True,
"cpu_offload": False
},
"train_micro_batch_size_per_gpu": 32,
"gas": 1,
"data-impl": "mmap",
"num_workers": 1,
# activation checkpointing
"checkpoint-activations": true,
"checkpoint-num-layers": 1,
"partition-activations": true,
"synchronize-each-layer": true,
# regularization
"gradient_clipping": 1.0,
"weight-decay": 0.1,
"hidden-dropout": 0,
"attention-dropout": 0,
# precision settings
"fp16": {
"fp16": true,
"enabled": true,
"loss_scale": 0,
"loss_scale_window": 1000,
"initial_scale_power": 12,
"hysteresis": 2,
"min_loss_scale": 1,
},
"train-iters": 143000,
"lr-decay-iters": 143000,
"distributed-backend": "nccl",
"lr-decay-style": "cosine",
"warmup": 0.01,
"save-interval": 1000,
"eval-interval": 100000,
"eval-iters": 10,
"log-interval": 10,
"steps_per_print": 10,
"wall_clock_breakdown": true,
"save": "/fsx/hailey/pythia/ckpts/19M",
"load": "/fsx/hailey/pythia/ckpts/19M",
"train-data-paths": ["/fsx/pile/pile_20B_tokenizer_text_document"],
"valid-data-paths": ["/fsx/pile/pile_20B_tokenizer_text_document"],
"test-data-paths": ["/fsx/pile/pile_20B_tokenizer_text_document"],
"tokenizer-type": "HFTokenizer",
"vocab-file": "/fsx/pile/20B_tokenizer.json",
"tensorboard-dir": "/fsx/code-fim/FIMlogs/1.3B-AR-Pile-9-6-22-rotary-1MtokBS",
"log-dir": "/fsx/code-fim/FIMlogs/1.3B-AR-Pile-9-6-22-rotary-1MtokBS",
"use_wandb": true,
"wandb_group": "Pythia 19M new",
"wandb_team": "eleutherai",
"wandb_project": "pythia",
"launcher": "openmpi",
"deepspeed_mpi": true,
}