{ "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", "no_weight_tying": true, "gpt_j_residual": false, "output_layer_parallelism": "column", "scaled_upper_triang_masked_softmax_fusion": false, "bias_gelu_fusion": false, "rope_fusion": false, "layernorm_fusion": false, # 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, # for all zero_optimization options, see https://www.deepspeed.ai/docs/config-json/#zero-optimizations-for-fp16-training "zero_optimization": { "stage": 1, "allgather_partitions": True, "allgather_bucket_size": 500000000, "overlap_comm": True, "reduce_scatter": True, "reduce_bucket_size": 500000000, "contiguous_gradients": True, }, "train_micro_batch_size_per_gpu": 4, #32, "gradient_accumulation_steps": 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, "checkpoint_factor": 1000, "eval_interval": 100000, "eval_iters": 10, "log_interval": 10, "steps_per_print": 10, "wall_clock_breakdown": true, # additional deepspeed args not specified above "deepspeed_extra_args": { "comms_logger": { "enabled": true, "verbose": true, "prof_all": true, "debug": false }, } }