| { | |
| "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": true, | |
| "bias_gelu_fusion": true, | |
| "rope_fusion": false, | |
| "layernorm_fusion": false, | |
| "optimizer": { | |
| "type": "Adam", | |
| "params": { | |
| "lr": 0.0006, | |
| "betas": [0.9, 0.999], | |
| "eps": 1.0e-8 | |
| } | |
| }, | |
| "zero_optimization": { | |
| "stage": 0, | |
| "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, | |
| "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, | |
| "checkpoint_factor": 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" | |
| } | |