mirror of
https://github.com/hpcaitech/ColossalAI.git
synced 2025-09-16 14:41:53 +00:00
[Test/CI] remove test cases to reduce CI duration (#5753)
* [test] smaller gpt2 test case
* [test] reduce test cases: tests/test_zero/test_gemini/test_zeroddp_state_dict.py
* [test] reduce test cases: tests/test_zero/test_gemini/test_grad_accum.py
* [test] reduce test cases tests/test_zero/test_gemini/test_optim.py
* Revert "[test] smaller gpt2 test case"
Some tests might depend on the size of model (num of chunks)
This reverts commit df705a5210
.
* [test] reduce test cases: tests/test_checkpoint_io/test_gemini_checkpoint_io.py
* [CI] smaller test model for two mwo the two modifid cases
* [CI] hardcode gpt model for tests/test_zero/test_gemini/test_search.py since we need a fixed answer there
This commit is contained in:
@@ -15,9 +15,7 @@ from colossalai.zero.gemini.chunk import search_chunk_configuration
|
||||
from tests.kit.model_zoo import model_zoo, run_fwd
|
||||
|
||||
PLACEMENT_CONFIGS = [
|
||||
{"placement_policy": "static", "shard_param_frac": 0.0}, # zero2
|
||||
{"placement_policy": "static", "shard_param_frac": 1.0}, # zero3
|
||||
{"placement_policy": "static", "shard_param_frac": 0.5}, # zero3-half
|
||||
{"placement_policy": "static", "shard_param_frac": 0.75},
|
||||
{"placement_policy": "auto"},
|
||||
]
|
||||
|
||||
@@ -109,7 +107,7 @@ def exam_gemini_grad_acc(
|
||||
torch_model = DDP(torch_model, device_ids=[rank])
|
||||
|
||||
set_seed(rank)
|
||||
accum_iter = 4
|
||||
accum_iter = 2
|
||||
train_dataloader = DummyDataloader(data_gen_fn)
|
||||
for i, data in enumerate(train_dataloader):
|
||||
delay_unscale = False if (i + 1) % accum_iter == 0 else True
|
||||
|
Reference in New Issue
Block a user