Skip to content
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.

Sign up for GitHub

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

Signed-off-by: dimapihtar <[email protected]> #148

Merged
merged 1 commit into from
Oct 20, 2023
Merged

Signed-off-by: dimapihtar <[email protected]> #148

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions launcher_scripts/conf/training/gpt3/1b_improved.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -70,7 +70,7 @@ model:
ffn_dropout: 0.0
kv_channels: null
apply_query_key_layer_scaling: true
normalization: LayerNorm
normalization: layernorm1p
layernorm_zero_centered_gamma: True
layernorm_epsilon: 1.0e-05
do_layer_norm_weight_decay: false
Expand Down Expand Up @@ -142,7 +142,7 @@ model:
ub_tp_comm_overlap: False

optim:
name: fused_adam
name: distributed_fused_adam
lr: 2e-4
weight_decay: 0.1
betas:
Expand Down
4 changes: 2 additions & 2 deletions launcher_scripts/conf/training/gpt3/400m_improved.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -70,7 +70,7 @@ model:
ffn_dropout: 0.0
kv_channels: null
apply_query_key_layer_scaling: true
normalization: LayerNorm
normalization: layernorm1p
layernorm_zero_centered_gamma: True
layernorm_epsilon: 1.0e-05
do_layer_norm_weight_decay: false
Expand Down Expand Up @@ -142,7 +142,7 @@ model:
ub_tp_comm_overlap: False

optim:
name: fused_adam
name: distributed_fused_adam
lr: 2.5e-4
weight_decay: 0.1
betas:
Expand Down
4 changes: 2 additions & 2 deletions launcher_scripts/conf/training/gpt3/40b_improved.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -70,7 +70,7 @@ model:
ffn_dropout: 0.0
kv_channels: null
apply_query_key_layer_scaling: true
normalization: LayerNorm
normalization: layernorm1p
layernorm_zero_centered_gamma: True
layernorm_epsilon: 1.0e-05
do_layer_norm_weight_decay: false
Expand Down Expand Up @@ -142,7 +142,7 @@ model:
ub_tp_comm_overlap: False

optim:
name: fused_adam
name: distributed_fused_adam
lr: 9e-5
weight_decay: 0.1
betas:
Expand Down
6 changes: 3 additions & 3 deletions launcher_scripts/conf/training/gpt3/7b_improved.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,7 +54,7 @@ model:
micro_batch_size: 1
global_batch_size: 512
rampup_batch_size: null
tensor_model_parallel_size: 2
tensor_model_parallel_size: 4
pipeline_model_parallel_size: 1
virtual_pipeline_model_parallel_size: null
encoder_seq_length: 2048
Expand All @@ -70,7 +70,7 @@ model:
ffn_dropout: 0.0
kv_channels: null
apply_query_key_layer_scaling: true
normalization: LayerNorm
normalization: layernorm1p
layernorm_zero_centered_gamma: True
layernorm_epsilon: 1.0e-05
do_layer_norm_weight_decay: false
Expand Down Expand Up @@ -142,7 +142,7 @@ model:
ub_tp_comm_overlap: False

optim:
name: fused_adam
name: distributed_fused_adam
lr: 1e-4
weight_decay: 0.1
betas:
Expand Down