x54-729
|
c4af9f21c6
|
paddle 和测试例跟进 set_dist_repro_dataloader 函数;修改test_trainer_wo_evaluator_torch.py的bug
|
2022-05-15 05:45:33 +00:00 |
|
x54-729
|
655e48de99
|
1.修改torch测试例中多卡的driver参数 2.修改测试例中的driver.save driver.load为driver.save_checkpoint driver.load_checkpoint 3.添加lstm
|
2022-05-13 11:19:31 +00:00 |
|
yh_cc
|
97b504c020
|
修改Trainer.save/Driver.save为Trainer.save_checkpoint/Driver.save_checkpoint
|
2022-05-13 12:32:44 +08:00 |
|
x54-729
|
34698f0f9e
|
删除 mix_module 和 torch_paddle_driver 的内容
|
2022-05-09 11:34:15 +00:00 |
|
x54-729
|
fe449bd543
|
删除 initialize_paddle_driver 对参数 driver的限制,使得它能够根据 device 初始化 driver
|
2022-05-09 08:59:03 +00:00 |
|
x54-729
|
281a570b09
|
1、调整单卡中 save_and_load_model 测试例,不再使用 pytest.fixture 2、添加 PaddleFleetDriver 中 broadcast 误删的设备转换
|
2022-05-03 15:34:17 +00:00 |
|
x54-729
|
45d08ee218
|
fix conflict
|
2022-05-03 14:41:06 +00:00 |
|
x54-729
|
80ef85cf7c
|
为 paddle 分布式的测试例添加paddledist标签
|
2022-05-03 14:38:35 +00:00 |
|
x54-729
|
007678b6d9
|
删除 paddle_driver/test_utils.py 中 get_device_from_visible 的测试例
|
2022-05-03 14:37:32 +00:00 |
|
yh_cc
|
5e24933521
|
设置init
|
2022-05-03 22:28:59 +08:00 |
|
x54-729
|
175ced3905
|
修正 initialize_torch_driver 的测试
|
2022-05-03 08:25:59 +00:00 |
|
x54-729
|
f79ee04956
|
为torch测试例添加_NEED_IMPORT_TORCH
|
2022-05-03 07:57:32 +00:00 |
|
x54-729
|
ebfd0e966c
|
为torch driver的测试例添加销毁通信进程的代码
|
2022-05-03 07:14:36 +00:00 |
|
yh_cc
|
7d5ce620f4
|
增加RandomBatchSampler
|
2022-05-02 23:08:50 +08:00 |
|
x54-729
|
f2fa05d136
|
测试例添加 _NEED_IMPORT_PADDLE
|
2022-05-02 07:16:09 +00:00 |
|
x54-729
|
3310a6cadf
|
部分测试例重命名
|
2022-05-02 07:03:46 +00:00 |
|
x54-729
|
4bfb509f12
|
调整测试例以适应pytest;为测试例添加标签
|
2022-05-02 05:46:47 +00:00 |
|
YWMditto
|
26397472aa
|
加入了 @pytest.mark.torch
|
2022-05-01 16:53:46 +08:00 |
|
x54-729
|
cf2ef2ecd7
|
调整测试例的backend设置
|
2022-04-30 13:04:55 +00:00 |
|
x54-729
|
f319b5bce1
|
torch ddp 的测试用例
|
2022-04-26 05:49:32 +00:00 |
|
x54-729
|
df109316e5
|
small
|
2022-04-26 05:33:37 +00:00 |
|
x54-729
|
705deeaea9
|
small
|
2022-04-26 03:35:25 +00:00 |
|
x54-729
|
cf65da1332
|
paddle 单卡测试例调整
|
2022-04-25 12:58:03 +00:00 |
|
x54-729
|
bb10410ccd
|
torch 单卡的测试例
|
2022-04-25 12:57:17 +00:00 |
|
x54-729
|
fcc45dbf4a
|
PaddleFleetDriver添加all_gather和broadcast_object函数
|
2022-04-20 10:17:19 +00:00 |
|
x54-729
|
1c0e331bad
|
完成fastnlp_paddle_all_gather和fastnlp_paddle_broadcast_object函数及测试例
|
2022-04-20 09:56:44 +00:00 |
|
yh_cc
|
368c17fe73
|
Merge branch 'dev0.8.0' of github.com:fastnlp/fastNLP into dev0.8.0
|
2022-04-19 22:38:55 +08:00 |
|
yh_cc
|
aa95513055
|
1.merge ModelCheckPointCallback和TrainerCheckpointCallback;2.新增MoreEvaluateCallback
|
2022-04-19 22:38:35 +08:00 |
|
x54-729
|
514415e9d4
|
完成了paddle fleet的save load函数测试
|
2022-04-16 15:47:18 +00:00 |
|
x54-729
|
9b13fd313a
|
small
|
2022-04-16 08:39:38 +00:00 |
|
x54-729
|
6bfdb39c2f
|
完善paddle fleet set_dist_repro_dataloader的测试例
|
2022-04-16 06:42:29 +00:00 |
|
x54-729
|
a25a73394b
|
Merge branch 'dev0.8.0' of github.com:fastnlp/fastNLP into dev0.8.0
|
2022-04-16 05:40:35 +00:00 |
|
x54-729
|
de544707d9
|
paddle fleet set_dist_repro_dataloader的测试例
|
2022-04-16 05:40:23 +00:00 |
|
yh_cc
|
048e409233
|
Merge branch 'dev0.8.0' of github.com:fastnlp/fastNLP into dev0.8.0
|
2022-04-16 00:33:32 +08:00 |
|
yh_cc
|
aaa4ccc3e0
|
1.Metric的aggregate_when_get_metric默认值修改为None;将根据Evaluator中Sampelr的状态最终决定;2.增加fastnlp_bo_syn_context关闭fastnlp中的多卡同步操作
|
2022-04-16 00:32:52 +08:00 |
|
x54-729
|
32d8e27472
|
small
|
2022-04-15 16:10:10 +00:00 |
|
x54-729
|
26c80d620c
|
paddle单卡加载fp16的测试
|
2022-04-15 16:01:21 +00:00 |
|
x54-729
|
9e97155312
|
PaddleSingleDriver的save load函数测试
|
2022-04-15 10:44:49 +00:00 |
|
x54-729
|
16cec4bd99
|
删除不必要的测试文件
|
2022-04-15 09:07:35 +00:00 |
|
x54-729
|
cf19062fb2
|
set_dist_repro_dataloader测试例的完善
|
2022-04-15 09:06:22 +00:00 |
|
x54-729
|
d0f26c7c34
|
将validate_step替换为evaluate_step
|
2022-04-15 08:10:01 +00:00 |
|
x54-729
|
f6f489dc90
|
多卡 set_dist_repro_dataloader 的测试例
|
2022-04-14 16:17:20 +00:00 |
|
x54-729
|
98644d2d0b
|
fix conflict
|
2022-04-14 16:05:53 +00:00 |
|
x54-729
|
5c29cd384a
|
调整num_consumed_batches在driver save中的逻辑
|
2022-04-14 16:04:12 +00:00 |
|
YWMditto
|
2924e2117f
|
删除了 driver 中的 **_step,使用 model_call 和 get_model_call_fn 来代替;删除了 driver 中的所有 dataloaders
|
2022-04-14 23:34:35 +08:00 |
|
x54-729
|
3ab93b2fae
|
paddle driver单卡和utils的pytest测试,添加了断点重训的测试
|
2022-04-13 07:33:27 +00:00 |
|
x54-729
|
fcd5125009
|
Merge branch 'dev0.8.0' of github.com:fastnlp/fastNLP into dev0.8.0
|
2022-04-12 07:34:44 +00:00 |
|
yh_cc
|
92b00d825f
|
修改fastnlp的dist功能
|
2022-04-12 02:19:28 +08:00 |
|
x54-729
|
00b5baf67a
|
整理PaddleSingleDriver的部分测试例
|
2022-04-11 17:39:19 +00:00 |
|
x54-729
|
3a3c38a44e
|
fix conflict
|
2022-04-11 14:16:39 +00:00 |
|