2024-02-12 13:17:51 +00:00
|
|
|
[mock_model1]
|
2024-02-10 14:53:18 +00:00
|
|
|
requires_grad = true
|
2024-02-01 08:26:59 +00:00
|
|
|
learning_rate = 1e-5
|
|
|
|
|
|
2024-02-12 13:17:51 +00:00
|
|
|
[mock_model2]
|
2024-02-10 14:53:18 +00:00
|
|
|
requires_grad = true
|
2024-02-01 08:26:59 +00:00
|
|
|
|
2024-02-12 08:28:41 +00:00
|
|
|
[clock]
|
|
|
|
|
verbose = false
|
|
|
|
|
|
|
|
|
|
[gradient_clipping]
|
|
|
|
|
clip_grad_norm = 1.0
|
|
|
|
|
|
2024-02-01 08:26:59 +00:00
|
|
|
[training]
|
|
|
|
|
duration = "100:epoch"
|
|
|
|
|
seed = 0
|
|
|
|
|
batch_size = 4
|
|
|
|
|
gradient_accumulation = "4:step"
|
|
|
|
|
evaluation_interval = "5:epoch"
|
|
|
|
|
evaluation_seed = 1
|
|
|
|
|
|
|
|
|
|
[optimizer]
|
|
|
|
|
optimizer = "SGD"
|
|
|
|
|
learning_rate = 1
|
|
|
|
|
|
2024-02-15 09:48:12 +00:00
|
|
|
[lr_scheduler]
|
|
|
|
|
type = "ConstantLR"
|
2024-02-01 08:26:59 +00:00
|
|
|
update_interval = "1:step"
|
