MorningForest
|
39e199467a
|
accuracy修改
|
2022-04-30 00:22:29 +08:00 |
|
yh_cc
|
1ecbdc7446
|
修复TopkSaver在CheckpointCallbackk中的bug;修改Saver对象,使得其方便被直接使用
|
2022-04-23 00:41:12 +08:00 |
|
yh_cc
|
b117f6170c
|
Merge branch 'dev0.8.0' of github.com:fastnlp/fastNLP into dev0.8.0
|
2022-04-22 02:09:43 +08:00 |
|
yh_cc
|
ceb30937b8
|
更新Trainer的部分文档; 更新topk_saver文档
|
2022-04-22 02:09:30 +08:00 |
|
x54-729
|
c74da391c7
|
跟进paddle backend关于all_gather的改动
|
2022-04-20 10:27:09 +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
|
6c532829c5
|
Merge branch 'dev0.8.0' of github.com:fastnlp/fastNLP into dev0.8.0
|
2022-04-20 00:37:31 +08:00 |
|
yh_cc
|
6b4d4502db
|
修复no_sync的bug
|
2022-04-20 00:37:19 +08:00 |
|
YWMditto
|
3823fc557d
|
对 magic_argv_env_context 添加了 timeout 参数,测试函数超过一定时间后自动kill掉
|
2022-04-20 00:16:23 +08:00 |
|
yh_cc
|
bfa9920b16
|
bug fix
|
2022-04-19 23:08:31 +08:00 |
|
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
|
cb01a661f1
|
BucketedBatchSampler的batch_id_in_epoch实现
|
2022-04-16 15:46:57 +00:00 |
|
x54-729
|
77f6b63ba6
|
paddle save函数适应新的sampler
|
2022-04-16 08:40:16 +00:00 |
|
x54-729
|
9b13fd313a
|
small
|
2022-04-16 08:39:38 +00:00 |
|
x54-729
|
3dbb3677f0
|
微调 reproducible sampler 的初始化
|
2022-04-16 08:39:07 +00:00 |
|
x54-729
|
aa2f678507
|
Merge branch 'dev0.8.0' of github.com:fastnlp/fastNLP into dev0.8.0
|
2022-04-16 07:23:18 +00:00 |
|
yh_cc
|
d813f31f9a
|
1.删除sampler中num_consumed_samples_array,转为通过batch_size等进行换算。2.在Metric中新增all_gather_object接口,方便评测
|
2022-04-16 15:22:44 +08:00 |
|
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
|
fcd27cfc3f
|
添加FASTNLP_NO_SYNC相关的设置
|
2022-04-16 05:50:53 +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
|
d758a36d4a
|
update metric的实现
|
2022-04-16 12:40:29 +08:00 |
|
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
|
8cda30c426
|
small
|
2022-04-15 15:10:35 +00:00 |
|
x54-729
|
5d1ac72ec9
|
加载fp16时同时设置auto_cast和fp16属性
|
2022-04-15 14:38:29 +00:00 |
|
x54-729
|
262bc1a82e
|
small
|
2022-04-15 14:03:08 +00:00 |
|
x54-729
|
8e9a47cf00
|
Merge branch 'dev0.8.0' of github.com:fastnlp/fastNLP into dev0.8.0
|
2022-04-15 13:48:23 +00:00 |
|
MorningForest
|
a2956b697e
|
Merge branch 'dev0.8.0' of github.com:fastnlp/fastNLP into dev0.8.0
|
2022-04-15 20:04:53 +08:00 |
|
MorningForest
|
665d79a3ed
|
增加paddle单卡的accuracy测试用例
|
2022-04-15 20:03:44 +08:00 |
|
yh_cc
|
b0db3a5998
|
Merge branch 'dev0.8.0' of github.com:fastnlp/fastNLP into dev0.8.0
|
2022-04-15 19:31:58 +08:00 |
|
yh_cc
|
687db6d86a
|
1.torch在保存和load的时候会考虑GradScaler的保存问题; 2.新增Torch的GradientClip和Warmpup
|
2022-04-15 19:31:46 +08:00 |
|
x54-729
|
9e97155312
|
PaddleSingleDriver的save load函数测试
|
2022-04-15 10:44:49 +00:00 |
|
x54-729
|
be24572b11
|
修改paddle.distributed的import名
|
2022-04-15 10:44:25 +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
|
288eb36afb
|
断点重训 save时的逻辑修正
|
2022-04-15 09:05:44 +00:00 |
|
x54-729
|
cca265f99c
|
Merge branch 'dev0.8.0' of github.com:fastnlp/fastNLP into dev0.8.0
|
2022-04-15 08:10:19 +00:00 |
|
x54-729
|
d0f26c7c34
|
将validate_step替换为evaluate_step
|
2022-04-15 08:10:01 +00:00 |
|
x54-729
|
8fc4fd19ff
|
small
|
2022-04-15 08:05:39 +00:00 |
|
yh_cc
|
7c70874b4a
|
删除core.sampelrs.sampler.py;增加torch的clipgradient和warmupcallback
|
2022-04-15 16:04:43 +08:00 |
|
x54-729
|
9d50e99bfb
|
修改evaluate_dataloader的报错信息
|
2022-04-15 06:57:31 +00:00 |
|
MorningForest
|
3ea74b52d2
|
Merge remote-tracking branch 'refs/remotes/origin/dev0.8.0' into dev0.8.0
|
2022-04-15 14:00:39 +08:00 |
|
yh_cc
|
f27d53261c
|
修改部分测试用例中validate_dataloader为evaluate_dataloader
|
2022-04-15 12:30:20 +08:00 |
|
YWMditto
|
02e080d239
|
Merge branch 'dev0.8.0' of github.com:fastnlp/fastNLP into dev0.8.0
|
2022-04-15 00:18:27 +08:00 |
|