-
Notifications
You must be signed in to change notification settings - Fork 975
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Lion Optimizer #1062
Merged
Merged
Lion Optimizer #1062
Conversation
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
Initial results: ConfigsLion: {
"pipe_parallel_size": 1,
"model_parallel_size": 1,
// model settings
"num_layers": 10,
"hidden_size": 512,
"num_attention_heads": 8,
"seq_length": 512,
"max_position_embeddings": 512,
"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,
// init methods
"init_method": "small_init",
"output_layer_init_method": "wang_init",
"optimizer": {
"type": "Lion",
"params": {
"lr": 0.00033,
"betas": [0.9, 0.95],
}
},
"min_lr": 0.000033,
// 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": 2, #32,
"gas": 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": 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": 5000,
"lr_decay_iters": 5000,
"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": {
"zero_allow_untested_optimizer": true,
"comms_logger": {
"enabled": true,
"verbose": true,
"prof_all": true,
"debug": false
},
}
} AdamW: {
"pipe_parallel_size": 1,
"model_parallel_size": 1,
// model settings
"num_layers": 10,
"hidden_size": 512,
"num_attention_heads": 8,
"seq_length": 512,
"max_position_embeddings": 512,
"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,
// 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": 2, #32
"gas": 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": 5000,
"lr_decay_iters": 5000,
"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
},
}
} |
Closed
I'll probably need some compute resources to run larger experiments (if needed). |
I think these results demonstrate correctness. Performance can be ironed out later on the target system if/when we use this to train a real model. |
Thank you @kamathis4 and @andylolu2! |
Quentin-Anthony
approved these changes
Oct 20, 2023
Thanks @andylolu2 for covering up!! |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Picking up from #1012