{
"vocab-file": "./tokenizer/20B_tokenizer.json",
"save": "./20B_checkpoints",
"load": "./20B_checkpoints",
"use_wandb": false,
"use_shared_fs": false,
"data-path": "./data/pile_20B_tokenizer/pile_20B_tokenizer_text_document",
"pipe-parallel-size": 2,
"model-parallel-size": 4,
"num-layers": 22,
"hidden-size": 6144,
"num-attention-heads": 64,
"seq-length": 2048,
"max-position-embeddings": 2048,
"norm": "layernorm",
"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": false,
"bias-gelu-fusion": false,
"init_method": "small_init",
"output_layer_init_method": "wang_init",
"optimizer": {
"type": "Adam",
"params": {
"lr": 0.97e-4,
"betas": [0.9, 0.95],
"eps": 1.0e-8,
}
},
"min_lr": 0.97e-5,
"zero_optimization": {
"stage": 1,
"allgather_partitions": True,
"allgather_bucket_size": 1260000000,
"overlap_comm": True,
"reduce_scatter": True,
"reduce_bucket_size": 1260000000,
"contiguous_gradients": True,
},
"train_micro_batch_size_per_gpu": 4,
"gradient_accumulation_steps": 64,
"data-impl": "mmap",
"split": "995,4,1",
"checkpoint-activations": false,
"checkpoint-selective": true,
"checkpoint-full-layers": 8,
"checkpoint-num-layers": 1,
"partition-activations": false,
"synchronize-each-layer": true,
"zero_allow_untested_optimizer": true,
"gradient_clipping": 1.0,
"weight-decay": 0.01,
"hidden-dropout": 0,
"attention-dropout": 0,
"fp16": {
"fp16": true,
"enabled": true,
"loss_scale": 0,
"loss_scale_window": 1000,
"initial_scale_power": 32,
"hysteresis": 2,
"min_loss_scale": 1
},
"train-iters": 150000,
"lr-decay-iters": 150000,
"distributed-backend": "nccl",
"lr-decay-style": "cosine",
"warmup": 0.02,
"checkpoint-factor": 500,
"eval-interval": 1000,
"eval-iters": 10,
"log-interval": 1,
"steps_per_print": 1,
"wall_clock_breakdown": false,
"tokenizer_type": "HFTokenizer", //slim:20B-tokenizer
"tensorboard-dir": "./tensorboard",
"log-dir": "./logs",
}