@@ -10,6 +10,7 @@ badam_mode: layer
|
||||
badam_switch_mode: ascending
|
||||
badam_switch_interval: 50
|
||||
badam_verbose: 2
|
||||
# deepspeed: examples/deepspeed/ds_z3_config.json
|
||||
|
||||
### dataset
|
||||
dataset: identity,alpaca_en_demo
|
||||
@@ -29,7 +30,7 @@ overwrite_output_dir: true
|
||||
### train
|
||||
per_device_train_batch_size: 1
|
||||
gradient_accumulation_steps: 8
|
||||
learning_rate: 1.0e-4
|
||||
learning_rate: 1.0e-5
|
||||
num_train_epochs: 3.0
|
||||
lr_scheduler_type: cosine
|
||||
warmup_ratio: 0.1
|
||||
|
||||
Reference in New Issue
Block a user