/
base_cifar10_config.py
58 lines (46 loc) · 1.9 KB
/
base_cifar10_config.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
# Copyright 2021 Google LLC
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
# https://www.apache.org/licenses/LICENSE-2.0
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""Base Configuration."""
import ml_collections
NUM_EPOCHS = 200
TRAIN_EXAMPLES = 45000
VALID_EXAMPLES = 10000
def get_config():
"""Get the default hyperparameter configuration."""
config = ml_collections.ConfigDict()
config.batch_size = 256
config.eval_frequency = TRAIN_EXAMPLES // config.batch_size
config.num_train_steps = (TRAIN_EXAMPLES // config.batch_size) * NUM_EPOCHS
config.num_eval_steps = VALID_EXAMPLES // config.batch_size
config.weight_decay = 0.
config.grad_clip_norm = None
config.save_checkpoints = True
config.restore_checkpoints = True
config.checkpoint_freq = (TRAIN_EXAMPLES //
config.batch_size) * NUM_EPOCHS // 2
config.random_seed = 0
config.learning_rate = .0005
config.factors = 'constant * linear_warmup * cosine_decay'
config.warmup = (TRAIN_EXAMPLES // config.batch_size) * 1
config.steps_per_cycle = (TRAIN_EXAMPLES // config.batch_size) * NUM_EPOCHS
# model params
config.model = ml_collections.ConfigDict()
config.model.emb_dim = 32
config.model.num_heads = 1
config.model.num_layers = 1
config.model.qkv_dim = 32
config.model.mlp_dim = 64
config.model.dropout_rate = 0.3
config.model.attention_dropout_rate = 0.2
config.model.classifier_pool = 'CLS'
config.model.learn_pos_emb = True
config.trial = 0 # dummy for repeated runs.
return config