chore: change yaml
This commit is contained in:
parent
fdae778fa7
commit
d4cea6f9ac
|
@ -29,7 +29,7 @@ learning_rate: 1.0e-4
|
||||||
num_train_epochs: 10.0
|
num_train_epochs: 10.0
|
||||||
lr_scheduler_type: cosine
|
lr_scheduler_type: cosine
|
||||||
warmup_ratio: 0.1
|
warmup_ratio: 0.1
|
||||||
fp16: true
|
bf16: true
|
||||||
ddp_timeout: 180000000
|
ddp_timeout: 180000000
|
||||||
max_steps: 1000
|
max_steps: 1000
|
||||||
include_num_input_tokens_seen: true
|
include_num_input_tokens_seen: true
|
||||||
|
|
|
@ -29,7 +29,7 @@ learning_rate: 1.0e-4
|
||||||
num_train_epochs: 10.0
|
num_train_epochs: 10.0
|
||||||
lr_scheduler_type: cosine
|
lr_scheduler_type: cosine
|
||||||
warmup_ratio: 0.1
|
warmup_ratio: 0.1
|
||||||
fp16: true
|
bf16: true
|
||||||
ddp_timeout: 180000000
|
ddp_timeout: 180000000
|
||||||
max_steps: 1000
|
max_steps: 1000
|
||||||
include_num_input_tokens_seen: true
|
include_num_input_tokens_seen: true
|
||||||
|
|
|
@ -29,7 +29,7 @@ learning_rate: 1.0e-4
|
||||||
num_train_epochs: 10.0
|
num_train_epochs: 10.0
|
||||||
lr_scheduler_type: cosine
|
lr_scheduler_type: cosine
|
||||||
warmup_ratio: 0.1
|
warmup_ratio: 0.1
|
||||||
fp16: true
|
bf16: true
|
||||||
ddp_timeout: 180000000
|
ddp_timeout: 180000000
|
||||||
max_steps: 1000
|
max_steps: 1000
|
||||||
include_num_input_tokens_seen: true
|
include_num_input_tokens_seen: true
|
||||||
|
|
|
@ -29,7 +29,7 @@ learning_rate: 1.0e-4
|
||||||
num_train_epochs: 10.0
|
num_train_epochs: 10.0
|
||||||
lr_scheduler_type: cosine
|
lr_scheduler_type: cosine
|
||||||
warmup_ratio: 0.1
|
warmup_ratio: 0.1
|
||||||
fp16: true
|
bf16: true
|
||||||
ddp_timeout: 180000000
|
ddp_timeout: 180000000
|
||||||
max_steps: 1000
|
max_steps: 1000
|
||||||
include_num_input_tokens_seen: true
|
include_num_input_tokens_seen: true
|
||||||
|
|
|
@ -29,7 +29,7 @@ learning_rate: 1.0e-4
|
||||||
num_train_epochs: 10.0
|
num_train_epochs: 10.0
|
||||||
lr_scheduler_type: cosine
|
lr_scheduler_type: cosine
|
||||||
warmup_ratio: 0.1
|
warmup_ratio: 0.1
|
||||||
fp16: true
|
bf16: true
|
||||||
ddp_timeout: 180000000
|
ddp_timeout: 180000000
|
||||||
max_steps: 1000
|
max_steps: 1000
|
||||||
include_num_input_tokens_seen: true
|
include_num_input_tokens_seen: true
|
||||||
|
|
|
@ -29,7 +29,7 @@ learning_rate: 1.0e-4
|
||||||
num_train_epochs: 10.0
|
num_train_epochs: 10.0
|
||||||
lr_scheduler_type: cosine
|
lr_scheduler_type: cosine
|
||||||
warmup_ratio: 0.1
|
warmup_ratio: 0.1
|
||||||
fp16: true
|
bf16: true
|
||||||
ddp_timeout: 180000000
|
ddp_timeout: 180000000
|
||||||
max_steps: 1000
|
max_steps: 1000
|
||||||
include_num_input_tokens_seen: true
|
include_num_input_tokens_seen: true
|
||||||
|
|
|
@ -29,7 +29,7 @@ learning_rate: 1.0e-4
|
||||||
num_train_epochs: 10.0
|
num_train_epochs: 10.0
|
||||||
lr_scheduler_type: cosine
|
lr_scheduler_type: cosine
|
||||||
warmup_ratio: 0.1
|
warmup_ratio: 0.1
|
||||||
fp16: true
|
bf16: true
|
||||||
ddp_timeout: 180000000
|
ddp_timeout: 180000000
|
||||||
max_steps: 1000
|
max_steps: 1000
|
||||||
include_num_input_tokens_seen: true
|
include_num_input_tokens_seen: true
|
||||||
|
|
Loading…
Reference in New Issue