configs/autotuning_configs/small_tune.json

{
   "pipe-parallel-size": 1,
   "model-parallel-size": 1,

   "num-layers": 12,
   "hidden-size": 768,
   "num-attention-heads": 12,
   "seq-length": 2048,
   "max-position-embeddings": 2048,
   "norm": "layernorm",
   "pos-emb": "rotary",
   "no-weight-tying": true,

   "scaled-upper-triang-masked-softmax-fusion": false,
   "bias-gelu-fusion": false,


   "optimizer": {
     "type": "Adam",
     "params": {
       "lr": 0.0006,
       "betas": [0.9, 0.999],
       "eps": 1.0e-8
     }
   },

   "train_micro_batch_size_per_gpu": 1,
   "data-impl": "mmap",
   "split": "949,50,1",

   "checkpoint-activations": true,
   "checkpoint-num-layers": 1,
   "partition-activations": true,
   "synchronize-each-layer": true,

   "gradient_clipping": 1.0,
   "weight-decay": 0.0,
   "hidden-dropout": 0.0,
   "attention-dropout": 0.0,

   "fp16": {
     "enabled": true,
     "loss_scale": 0,
     "loss_scale_window": 1000,
     "hysteresis": 2,
     "min_loss_scale": 1
   },

   "train-iters": 320000,
   "lr-decay-iters": 320000,
   "distributed-backend": "nccl",
   "lr-decay-style": "cosine",
   "warmup": 0.01,
   "save-interval": 10000,
   "eval-interval": 1000,
   "eval-iters": 10,

   "log-interval": 100,
   "steps_per_print": 10,
   "keep-last-n-checkpoints": 4,
   "wall_clock_breakdown": true,
   "launcher": "slurm",
   "deepspeed_slurm": true,
   "comment": "neox",
   "autotuning": {
       "enabled": true,
       "arg_mappings": {
       "train_micro_batch_size_per_gpu": "--train_micro_batch_size_per_gpu",
       "gradient_accumulation_steps ": "--gradient_accumulation_steps"
     }
   },
   "zero_optimization": {
      "stage": [0, 1, 2, 3]
   },
  "train-data-paths": ["/fsx/pile_deduped/pile_0.87_deduped_text_document"],
  "valid-data-paths": ["/fsx/pile_deduped/pile_0.87_deduped_text_document"],
  "test-data-paths": ["/fsx/pile_deduped/pile_0.87_deduped_text_document"]
}