dat commited on
Commit
3ac2ab9
β€’
1 Parent(s): 863f702

update readme

Browse files
README.md CHANGED
@@ -11,8 +11,6 @@ Created by [Dat Nguyen](https://www.linkedin.com/in/dat-nguyen-49a641138/) & Yeb
11
 
12
 
13
 
14
- Please do not hesitate to contact me via [LinkedIn](https://www.linkedin.com/in/henryk-borzymowski-0755a2167/=
15
-
16
 
17
 
18
  BigBird, is a sparse-attention based transformer which extends Transformer based models, such as BERT to much longer sequences. Moreover, BigBird comes along with a theoretical understanding of the capabilities of a complete transformer that the sparse model can handle.
 
11
 
12
 
13
 
 
 
14
 
15
 
16
  BigBird, is a sparse-attention based transformer which extends Transformer based models, such as BERT to much longer sequences. Moreover, BigBird comes along with a theoretical understanding of the capabilities of a complete transformer that the sparse model can handle.
events.out.tfevents.1626474829.t1v-n-f5c06ea1-w-0.798495.3.v2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2eba091f8fe3f0ead59825c7368f8ceef1e86032529a74117afab28db1b6b4d1
3
- size 2128342
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53a6478d810481447758fc0feda2c8c7d6617e6f078c40da3bb43572c4d199fb
3
+ size 2158492
wandb/run-20210716_223350-8eukt20m/files/output.log CHANGED
@@ -2151,3 +2151,30 @@ Training...: 14149it [1:40:45, 5.64it/s]β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ
2151
 
2152
 
2153
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2151
 
2152
 
2153
 
2154
+
2155
+
2156
+ Training...: 14200it [1:41:16, 3.23s/it]β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 500/500 [01:17<00:00, 7.90it/s]
2157
+
2158
+
2159
+
2160
+
2161
+
2162
+ Training...: 14249it [1:41:26, 5.51it/s]β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 500/500 [01:17<00:00, 7.90it/s]
2163
+
2164
+
2165
+
2166
+
2167
+
2168
+
2169
+ Training...: 14300it [1:41:56, 3.34s/it]β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 500/500 [01:17<00:00, 7.90it/s]
2170
+
2171
+
2172
+
2173
+
2174
+
2175
+ Training...: 14349it [1:42:06, 5.17it/s]β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 500/500 [01:17<00:00, 7.90it/s]
2176
+
2177
+
2178
+
2179
+
2180
+
wandb/run-20210716_223350-8eukt20m/files/wandb-summary.json CHANGED
@@ -1 +1 @@
1
- {"training_step": 344150, "learning_rate": 2.2845080820843577e-05, "train_loss": 1.9759552478790283, "_runtime": 6408, "_timestamp": 1626481238, "_step": 283, "eval_step": 340000, "eval_accuracy": 0.6408576965332031, "eval_loss": 1.8213207721710205}
 
1
+ {"training_step": 344350, "learning_rate": 2.2840797100798227e-05, "train_loss": 1.849149465560913, "_runtime": 6489, "_timestamp": 1626481319, "_step": 287, "eval_step": 340000, "eval_accuracy": 0.6408576965332031, "eval_loss": 1.8213207721710205}
wandb/run-20210716_223350-8eukt20m/logs/debug-internal.log CHANGED
@@ -4251,3 +4251,56 @@
4251
  2021-07-17 00:20:43,777 INFO Thread-8 :799749 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210716_223350-8eukt20m/files/output.log
4252
  2021-07-17 00:20:45,778 INFO Thread-8 :799749 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210716_223350-8eukt20m/files/output.log
4253
  2021-07-17 00:20:47,779 INFO Thread-8 :799749 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210716_223350-8eukt20m/files/output.log
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4251
  2021-07-17 00:20:43,777 INFO Thread-8 :799749 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210716_223350-8eukt20m/files/output.log
4252
  2021-07-17 00:20:45,778 INFO Thread-8 :799749 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210716_223350-8eukt20m/files/output.log
4253
  2021-07-17 00:20:47,779 INFO Thread-8 :799749 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210716_223350-8eukt20m/files/output.log
4254
+ 2021-07-17 00:20:49,780 INFO Thread-8 :799749 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210716_223350-8eukt20m/files/output.log
4255
+ 2021-07-17 00:20:56,648 DEBUG HandlerThread:799749 [handler.py:handle_request():124] handle_request: stop_status
4256
+ 2021-07-17 00:20:56,649 DEBUG SenderThread:799749 [sender.py:send_request():193] send_request: stop_status
4257
+ 2021-07-17 00:20:59,086 DEBUG SenderThread:799749 [sender.py:send():179] send: history
4258
+ 2021-07-17 00:20:59,086 DEBUG SenderThread:799749 [sender.py:send():179] send: summary
4259
+ 2021-07-17 00:20:59,087 INFO SenderThread:799749 [sender.py:_save_file():841] saving file wandb-summary.json with policy end
4260
+ 2021-07-17 00:20:59,784 INFO Thread-8 :799749 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210716_223350-8eukt20m/files/output.log
4261
+ 2021-07-17 00:20:59,784 INFO Thread-8 :799749 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210716_223350-8eukt20m/files/wandb-summary.json
4262
+ 2021-07-17 00:21:01,785 INFO Thread-8 :799749 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210716_223350-8eukt20m/files/output.log
4263
+ 2021-07-17 00:21:03,786 INFO Thread-8 :799749 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210716_223350-8eukt20m/files/output.log
4264
+ 2021-07-17 00:21:05,787 INFO Thread-8 :799749 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210716_223350-8eukt20m/files/output.log
4265
+ 2021-07-17 00:21:06,613 DEBUG SenderThread:799749 [sender.py:send():179] send: stats
4266
+ 2021-07-17 00:21:07,788 INFO Thread-8 :799749 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210716_223350-8eukt20m/files/output.log
4267
+ 2021-07-17 00:21:09,789 INFO Thread-8 :799749 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210716_223350-8eukt20m/files/output.log
4268
+ 2021-07-17 00:21:11,780 DEBUG HandlerThread:799749 [handler.py:handle_request():124] handle_request: stop_status
4269
+ 2021-07-17 00:21:11,780 DEBUG SenderThread:799749 [sender.py:send_request():193] send_request: stop_status
4270
+ 2021-07-17 00:21:19,229 DEBUG SenderThread:799749 [sender.py:send():179] send: history
4271
+ 2021-07-17 00:21:19,229 DEBUG SenderThread:799749 [sender.py:send():179] send: summary
4272
+ 2021-07-17 00:21:19,230 INFO SenderThread:799749 [sender.py:_save_file():841] saving file wandb-summary.json with policy end
4273
+ 2021-07-17 00:21:19,794 INFO Thread-8 :799749 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210716_223350-8eukt20m/files/wandb-summary.json
4274
+ 2021-07-17 00:21:21,795 INFO Thread-8 :799749 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210716_223350-8eukt20m/files/output.log
4275
+ 2021-07-17 00:21:23,795 INFO Thread-8 :799749 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210716_223350-8eukt20m/files/output.log
4276
+ 2021-07-17 00:21:25,796 INFO Thread-8 :799749 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210716_223350-8eukt20m/files/output.log
4277
+ 2021-07-17 00:21:26,978 DEBUG HandlerThread:799749 [handler.py:handle_request():124] handle_request: stop_status
4278
+ 2021-07-17 00:21:26,978 DEBUG SenderThread:799749 [sender.py:send_request():193] send_request: stop_status
4279
+ 2021-07-17 00:21:27,797 INFO Thread-8 :799749 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210716_223350-8eukt20m/files/output.log
4280
+ 2021-07-17 00:21:29,798 INFO Thread-8 :799749 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210716_223350-8eukt20m/files/output.log
4281
+ 2021-07-17 00:21:36,687 DEBUG SenderThread:799749 [sender.py:send():179] send: stats
4282
+ 2021-07-17 00:21:39,383 DEBUG SenderThread:799749 [sender.py:send():179] send: history
4283
+ 2021-07-17 00:21:39,384 DEBUG SenderThread:799749 [sender.py:send():179] send: summary
4284
+ 2021-07-17 00:21:39,384 INFO SenderThread:799749 [sender.py:_save_file():841] saving file wandb-summary.json with policy end
4285
+ 2021-07-17 00:21:39,803 INFO Thread-8 :799749 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210716_223350-8eukt20m/files/output.log
4286
+ 2021-07-17 00:21:39,803 INFO Thread-8 :799749 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210716_223350-8eukt20m/files/wandb-summary.json
4287
+ 2021-07-17 00:21:41,804 INFO Thread-8 :799749 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210716_223350-8eukt20m/files/output.log
4288
+ 2021-07-17 00:21:42,193 DEBUG HandlerThread:799749 [handler.py:handle_request():124] handle_request: stop_status
4289
+ 2021-07-17 00:21:42,194 DEBUG SenderThread:799749 [sender.py:send_request():193] send_request: stop_status
4290
+ 2021-07-17 00:21:43,805 INFO Thread-8 :799749 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210716_223350-8eukt20m/files/output.log
4291
+ 2021-07-17 00:21:45,806 INFO Thread-8 :799749 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210716_223350-8eukt20m/files/output.log
4292
+ 2021-07-17 00:21:48,807 INFO Thread-8 :799749 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210716_223350-8eukt20m/files/output.log
4293
+ 2021-07-17 00:21:50,808 INFO Thread-8 :799749 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210716_223350-8eukt20m/files/output.log
4294
+ 2021-07-17 00:21:57,364 DEBUG HandlerThread:799749 [handler.py:handle_request():124] handle_request: stop_status
4295
+ 2021-07-17 00:21:57,365 DEBUG SenderThread:799749 [sender.py:send_request():193] send_request: stop_status
4296
+ 2021-07-17 00:21:59,598 DEBUG SenderThread:799749 [sender.py:send():179] send: history
4297
+ 2021-07-17 00:21:59,598 DEBUG SenderThread:799749 [sender.py:send():179] send: summary
4298
+ 2021-07-17 00:21:59,599 INFO SenderThread:799749 [sender.py:_save_file():841] saving file wandb-summary.json with policy end
4299
+ 2021-07-17 00:21:59,812 INFO Thread-8 :799749 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210716_223350-8eukt20m/files/wandb-summary.json
4300
+ 2021-07-17 00:22:01,813 INFO Thread-8 :799749 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210716_223350-8eukt20m/files/output.log
4301
+ 2021-07-17 00:22:02,814 INFO Thread-8 :799749 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210716_223350-8eukt20m/files/output.log
4302
+ 2021-07-17 00:22:04,815 INFO Thread-8 :799749 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210716_223350-8eukt20m/files/output.log
4303
+ 2021-07-17 00:22:06,765 DEBUG SenderThread:799749 [sender.py:send():179] send: stats
4304
+ 2021-07-17 00:22:06,816 INFO Thread-8 :799749 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210716_223350-8eukt20m/files/output.log
4305
+ 2021-07-17 00:22:08,817 INFO Thread-8 :799749 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210716_223350-8eukt20m/files/output.log
4306
+ 2021-07-17 00:22:10,818 INFO Thread-8 :799749 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210716_223350-8eukt20m/files/output.log
wandb/run-20210716_223350-8eukt20m/run-8eukt20m.wandb CHANGED
Binary files a/wandb/run-20210716_223350-8eukt20m/run-8eukt20m.wandb and b/wandb/run-20210716_223350-8eukt20m/run-8eukt20m.wandb differ