-
Notifications
You must be signed in to change notification settings - Fork 1k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
50 changed files
with
3,751 additions
and
76 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,97 @@ | ||
| # GPT-2 pretraining setup | ||
| { | ||
| # parallelism settings ( you will want to change these based on your cluster setup, ideally scheduling pipeline stages | ||
| # across the node boundaries ) | ||
| "pipe_parallel_size": 1, | ||
| "model_parallel_size": 1, | ||
|
|
||
| # model settings | ||
| "num_layers": 24, | ||
| "hidden_size": 2048, | ||
| "num_attention_heads": 16, | ||
| "seq_length": 4096, | ||
| "max_position_embeddings": 4096, | ||
| "norm": "layernorm", | ||
| "pos_emb": "rotary", | ||
| "no_weight_tying": true, | ||
| "gpt_j_residual": false, | ||
| "output_layer_parallelism": "column", | ||
| #"profile": true, | ||
| #"profile_step_start": 1, | ||
| #"profile_step_stop": 5, | ||
|
|
||
| "attention_config": [[["flash"], 24]], | ||
| # these should provide some speedup but takes a while to build, set to true if desired | ||
| "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 settings | ||
| "optimizer": { | ||
| "type": "Adam", | ||
| "params": { | ||
| "lr": 0.0002, | ||
| "betas": [0.9, 0.95], | ||
| "eps": 1.0e-8, | ||
| } | ||
| }, | ||
| "min_lr": 0.00002, | ||
|
|
||
| # 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, | ||
| }, | ||
|
|
||
| # batch / data settings | ||
| "train_micro_batch_size_per_gpu": 1, | ||
| "data_impl": "mmap", | ||
|
|
||
| # 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, | ||
| "hysteresis": 2, | ||
| "min_loss_scale": 1 | ||
| }, | ||
|
|
||
| # misc. training settings | ||
| "train_iters": 100, | ||
| "lr_decay_iters": 100, | ||
| "distributed_backend": "nccl", | ||
| "lr_decay_style": "cosine", | ||
| "warmup": 0.01, | ||
| "checkpoint_factor": 10000, | ||
| "eval_interval": 1000, | ||
| "eval_iters": 10, | ||
|
|
||
| # logging | ||
| "log_interval": 5, | ||
| "steps_per_print": 5, | ||
| "keep_last_n_checkpoints": 4, | ||
| "wall_clock_breakdown": true, | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,97 @@ | ||
| # GPT-2 pretraining setup | ||
| { | ||
| # parallelism settings ( you will want to change these based on your cluster setup, ideally scheduling pipeline stages | ||
| # across the node boundaries ) | ||
| "pipe_parallel_size": 8, | ||
| "model_parallel_size": 1, | ||
|
|
||
| # model settings | ||
| "num_layers": 192, | ||
| "hidden_size": 2048, | ||
| "num_attention_heads": 16, | ||
| "seq_length": 4096, | ||
| "max_position_embeddings": 4096, | ||
| "norm": "layernorm", | ||
| "pos_emb": "rotary", | ||
| "no_weight_tying": true, | ||
| "gpt_j_residual": false, | ||
| "output_layer_parallelism": "column", | ||
| #"profile": true, | ||
| #"profile_step_start": 1, | ||
| #"profile_step_stop": 5, | ||
|
|
||
| "attention_config": [[["flash"], 192]], | ||
| # these should provide some speedup but takes a while to build, set to true if desired | ||
| "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 settings | ||
| "optimizer": { | ||
| "type": "Adam", | ||
| "params": { | ||
| "lr": 0.0002, | ||
| "betas": [0.9, 0.95], | ||
| "eps": 1.0e-8, | ||
| } | ||
| }, | ||
| "min_lr": 0.00002, | ||
|
|
||
| # 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, | ||
| }, | ||
|
|
||
| # batch / data settings | ||
| "train_micro_batch_size_per_gpu": 1, | ||
| "data_impl": "mmap", | ||
|
|
||
| # 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, | ||
| "hysteresis": 2, | ||
| "min_loss_scale": 1 | ||
| }, | ||
|
|
||
| # misc. training settings | ||
| "train_iters": 100, | ||
| "lr_decay_iters": 100, | ||
| "distributed_backend": "nccl", | ||
| "lr_decay_style": "cosine", | ||
| "warmup": 0.01, | ||
| "checkpoint_factor": 10000, | ||
| "eval_interval": 1000, | ||
| "eval_iters": 10, | ||
|
|
||
| # logging | ||
| "log_interval": 5, | ||
| "steps_per_print": 5, | ||
| "keep_last_n_checkpoints": 4, | ||
| "wall_clock_breakdown": true, | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.