nipunsadvilkar commited on
Commit
77beea9
1 Parent(s): faa64e8

Saving weights and logs of step 500

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. events.out.tfevents.1625836684.t1v-n-112df4a9-w-0.38631.3.v2 +3 -0
  2. flax_model.msgpack +1 -1
  3. run.log +166 -310
  4. run.sh +1 -1
  5. run_mlm_flax.py +11 -3
  6. test_mr_tokenizer.py +8 -0
  7. wandb/debug-internal.log +1 -1
  8. wandb/debug.log +1 -1
  9. wandb/latest-run +1 -1
  10. wandb/run-20210709_111555-275xd40l/files/config.yaml +305 -0
  11. wandb/run-20210709_111555-275xd40l/files/output.log +33 -0
  12. wandb/run-20210709_111555-275xd40l/files/requirements.txt +96 -0
  13. wandb/run-20210709_111555-275xd40l/files/wandb-metadata.json +36 -0
  14. wandb/run-20210709_111555-275xd40l/files/wandb-summary.json +1 -0
  15. wandb/run-20210709_111555-275xd40l/logs/debug-internal.log +175 -0
  16. wandb/run-20210709_111555-275xd40l/logs/debug.log +88 -0
  17. wandb/run-20210709_111555-275xd40l/run-275xd40l.wandb +0 -0
  18. wandb/run-20210709_115016-mgpt342u/files/config.yaml +305 -0
  19. wandb/run-20210709_115016-mgpt342u/files/output.log +34 -0
  20. wandb/run-20210709_115016-mgpt342u/files/requirements.txt +96 -0
  21. wandb/run-20210709_115016-mgpt342u/files/wandb-metadata.json +36 -0
  22. wandb/run-20210709_115016-mgpt342u/files/wandb-summary.json +1 -0
  23. wandb/run-20210709_115016-mgpt342u/logs/debug-internal.log +177 -0
  24. wandb/run-20210709_115016-mgpt342u/logs/debug.log +96 -0
  25. wandb/run-20210709_115016-mgpt342u/run-mgpt342u.wandb +0 -0
  26. wandb/run-20210709_122021-2porvgvv/files/config.yaml +305 -0
  27. wandb/run-20210709_122021-2porvgvv/files/output.log +18 -0
  28. wandb/run-20210709_122021-2porvgvv/files/requirements.txt +96 -0
  29. wandb/run-20210709_122021-2porvgvv/files/wandb-metadata.json +36 -0
  30. wandb/run-20210709_122021-2porvgvv/files/wandb-summary.json +1 -0
  31. wandb/run-20210709_122021-2porvgvv/logs/debug-internal.log +156 -0
  32. wandb/run-20210709_122021-2porvgvv/logs/debug.log +88 -0
  33. wandb/run-20210709_122021-2porvgvv/run-2porvgvv.wandb +0 -0
  34. wandb/run-20210709_122709-2pc90wcd/files/config.yaml +303 -0
  35. wandb/run-20210709_122709-2pc90wcd/files/output.log +18 -0
  36. wandb/run-20210709_122709-2pc90wcd/files/requirements.txt +96 -0
  37. wandb/run-20210709_122709-2pc90wcd/files/wandb-metadata.json +36 -0
  38. wandb/run-20210709_122709-2pc90wcd/files/wandb-summary.json +1 -0
  39. wandb/run-20210709_122709-2pc90wcd/logs/debug-internal.log +0 -0
  40. wandb/run-20210709_122709-2pc90wcd/logs/debug.log +53 -0
  41. wandb/run-20210709_122709-2pc90wcd/run-2pc90wcd.wandb +0 -0
  42. wandb/run-20210709_124353-3pjvcule/files/config.yaml +19 -0
  43. wandb/run-20210709_124353-3pjvcule/files/output.log +5 -0
  44. wandb/run-20210709_124353-3pjvcule/files/requirements.txt +96 -0
  45. wandb/run-20210709_124353-3pjvcule/files/wandb-metadata.json +36 -0
  46. wandb/run-20210709_124353-3pjvcule/files/wandb-summary.json +1 -0
  47. wandb/run-20210709_124353-3pjvcule/logs/debug-internal.log +55 -0
  48. wandb/run-20210709_124353-3pjvcule/logs/debug.log +28 -0
  49. wandb/run-20210709_124353-3pjvcule/run-3pjvcule.wandb +0 -0
  50. wandb/run-20210709_124449-choidyfc/files/config.yaml +305 -0
events.out.tfevents.1625836684.t1v-n-112df4a9-w-0.38631.3.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1198c8afc6504eecba539da0dee931919669a28655dbd66157e980a6606dbd50
3
+ size 11274
flax_model.msgpack CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76d55c57630984430801c3b6d5cc75703bd2a61ef6bb8f9d20f7c6150f2dfbd3
3
  size 498796983
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1f30bd95331d281308f6cb94e74bec0d82ebc06684501d536c8d38952e09abb
3
  size 498796983
run.log CHANGED
@@ -1,4 +1,5 @@
1
- [10:39:50] - INFO - __main__ - Training/evaluation parameters TrainingArguments(
 
2
  _n_gpu=-1,
3
  adafactor=False,
4
  adam_beta1=0.9,
@@ -34,7 +35,7 @@ local_rank=-1,
34
  log_level=-1,
35
  log_level_replica=-1,
36
  log_on_each_node=True,
37
- logging_dir=./runs/Jul09_10-39-50_t1v-n-112df4a9-w-0,
38
  logging_first_step=False,
39
  logging_steps=500,
40
  logging_strategy=IntervalStrategy.STEPS,
@@ -73,326 +74,181 @@ warmup_ratio=0.0,
73
  warmup_steps=1000,
74
  weight_decay=0.0,
75
  )
76
- [10:39:50] - DEBUG - urllib3.connectionpool - Starting new HTTPS connection (1): s3.amazonaws.com:443
77
- [10:39:50] - DEBUG - urllib3.connectionpool - https://s3.amazonaws.com:443 "HEAD /datasets.huggingface.co/datasets/datasets/oscar/oscar.py HTTP/1.1" 404 0
78
- [10:39:50] - DEBUG - urllib3.connectionpool - Starting new HTTPS connection (1): raw.githubusercontent.com:443
79
- [10:39:50] - DEBUG - urllib3.connectionpool - https://raw.githubusercontent.com:443 "HEAD /huggingface/datasets/master/datasets/oscar/oscar.py HTTP/1.1" 200 0
80
- [10:39:50] - DEBUG - urllib3.connectionpool - Starting new HTTPS connection (1): raw.githubusercontent.com:443
81
- [10:39:50] - DEBUG - urllib3.connectionpool - https://raw.githubusercontent.com:443 "HEAD /huggingface/datasets/master/datasets/oscar/dataset_infos.json HTTP/1.1" 200 0
82
- [10:39:50] - WARNING - datasets.builder - Reusing dataset oscar (/home/nipunsadvilkar/.cache/huggingface/datasets/oscar/unshuffled_deduplicated_als/1.0.0/84838bd49d2295f62008383b05620571535451d84545037bb94d6f3501651df2)
83
- [10:39:50] - DEBUG - urllib3.connectionpool - Starting new HTTPS connection (1): s3.amazonaws.com:443
84
- [10:39:51] - DEBUG - urllib3.connectionpool - https://s3.amazonaws.com:443 "HEAD /datasets.huggingface.co/datasets/datasets/oscar/oscar.py HTTP/1.1" 404 0
85
- [10:39:51] - DEBUG - urllib3.connectionpool - Starting new HTTPS connection (1): raw.githubusercontent.com:443
86
- [10:39:51] - DEBUG - urllib3.connectionpool - https://raw.githubusercontent.com:443 "HEAD /huggingface/datasets/master/datasets/oscar/oscar.py HTTP/1.1" 200 0
87
- [10:39:51] - DEBUG - urllib3.connectionpool - Starting new HTTPS connection (1): raw.githubusercontent.com:443
88
- [10:39:51] - DEBUG - urllib3.connectionpool - https://raw.githubusercontent.com:443 "HEAD /huggingface/datasets/master/datasets/oscar/dataset_infos.json HTTP/1.1" 200 0
89
- [10:39:51] - WARNING - datasets.builder - Reusing dataset oscar (/home/nipunsadvilkar/.cache/huggingface/datasets/oscar/unshuffled_deduplicated_als/1.0.0/84838bd49d2295f62008383b05620571535451d84545037bb94d6f3501651df2)
90
- [10:39:51] - DEBUG - urllib3.connectionpool - Starting new HTTPS connection (1): s3.amazonaws.com:443
91
- [10:39:51] - DEBUG - urllib3.connectionpool - https://s3.amazonaws.com:443 "HEAD /datasets.huggingface.co/datasets/datasets/oscar/oscar.py HTTP/1.1" 404 0
92
- [10:39:51] - DEBUG - urllib3.connectionpool - Starting new HTTPS connection (1): raw.githubusercontent.com:443
93
- [10:39:51] - DEBUG - urllib3.connectionpool - https://raw.githubusercontent.com:443 "HEAD /huggingface/datasets/master/datasets/oscar/oscar.py HTTP/1.1" 200 0
94
- [10:39:51] - DEBUG - urllib3.connectionpool - Starting new HTTPS connection (1): raw.githubusercontent.com:443
95
- [10:39:51] - DEBUG - urllib3.connectionpool - https://raw.githubusercontent.com:443 "HEAD /huggingface/datasets/master/datasets/oscar/dataset_infos.json HTTP/1.1" 200 0
96
- [10:39:51] - WARNING - datasets.builder - Reusing dataset oscar (/home/nipunsadvilkar/.cache/huggingface/datasets/oscar/unshuffled_deduplicated_als/1.0.0/84838bd49d2295f62008383b05620571535451d84545037bb94d6f3501651df2)
97
- [10:39:51] - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/nipunsadvilkar/.cache/huggingface/datasets/oscar/unshuffled_deduplicated_als/1.0.0/84838bd49d2295f62008383b05620571535451d84545037bb94d6f3501651df2/cache-0f52086e7b10d7e8.arrow
98
- [10:39:51] - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/nipunsadvilkar/.cache/huggingface/datasets/oscar/unshuffled_deduplicated_als/1.0.0/84838bd49d2295f62008383b05620571535451d84545037bb94d6f3501651df2/cache-a39e5f5a5c6c69fc.arrow
99
- [10:39:51] - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/nipunsadvilkar/.cache/huggingface/datasets/oscar/unshuffled_deduplicated_als/1.0.0/84838bd49d2295f62008383b05620571535451d84545037bb94d6f3501651df2/cache-e4d3282a2dd50fa0.arrow
100
- [10:39:51] - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/nipunsadvilkar/.cache/huggingface/datasets/oscar/unshuffled_deduplicated_als/1.0.0/84838bd49d2295f62008383b05620571535451d84545037bb94d6f3501651df2/cache-b9a3aa9913be3b34.arrow
101
- [10:39:51] - INFO - absl - Starting the local TPU driver.
102
- [10:39:51] - INFO - absl - Unable to initialize backend 'tpu_driver': Not found: Unable to find driver in registry given worker: local://
103
- [10:39:51] - INFO - absl - Unable to initialize backend 'gpu': Not found: Could not find registered platform with name: "cuda". Available platform names are: Interpreter Host TPU
104
- [10:39:55] - WARNING - __main__ - Unable to display metrics through TensorBoard because some package are not installed: No module named 'tensorflow'
105
  0%| | 0/5 [00:00<?, ?ba/s]
106
  20%|██ | 1/5 [00:00<00:03, 1.33ba/s]
107
  40%|████ | 2/5 [00:01<00:02, 1.25ba/s]
108
  60%|██████ | 3/5 [00:02<00:01, 1.22ba/s]
109
  80%|████████ | 4/5 [00:03<00:00, 1.14ba/s]
 
110
  0%| | 0/1 [00:00<?, ?ba/s]
 
 
 
 
 
111
  /home/nipunsadvilkar/roberta_mr_env/lib/python3.8/site-packages/jax/lib/xla_bridge.py:382: UserWarning: jax.host_count has been renamed to jax.process_count. This alias will eventually be removed; please update your code.
112
  warnings.warn(
113
  /home/nipunsadvilkar/roberta_mr_env/lib/python3.8/site-packages/jax/lib/xla_bridge.py:369: UserWarning: jax.host_id has been renamed to jax.process_index. This alias will eventually be removed; please update your code.
114
  warnings.warn(
115
 
116
 
117
-
118
-
119
-
120
-
121
-
122
-
123
-
124
-
125
-
126
-
127
-
128
-
129
-
130
-
131
-
132
-
133
-
134
-
135
-
136
-
137
-
138
-
139
-
140
-
141
-
142
-
143
-
144
-
145
-
146
-
147
-
148
-
149
-
150
-
151
-
152
-
153
-
154
 
155
-
156
-
157
-
158
-
159
-
160
-
161
-
162
-
163
-
164
-
165
-
166
-
167
-
168
-
169
-
170
-
171
-
172
-
173
-
174
-
175
-
176
-
177
-
178
-
179
-
180
-
181
-
182
-
183
-
184
-
185
-
186
-
187
-
188
-
189
-
190
-
191
-
192
-
193
-
194
-
195
-
196
-
197
-
198
-
199
-
200
-
201
-
202
-
203
-
204
-
205
-
206
-
207
-
208
-
209
-
210
-
211
-
212
-
213
-
214
-
215
-
216
-
217
-
218
-
219
-
220
-
221
-
222
-
223
-
224
-
225
-
226
-
227
-
228
-
229
-
230
-
231
-
232
-
233
-
234
-
235
-
236
-
237
-
238
-
239
-
240
-
241
-
242
-
243
-
244
-
245
-
246
-
247
-
248
 
249
-
250
 
251
-
252
-
253
-
254
-
255
-
256
-
257
-
258
-
259
- [10:41:35] - INFO - huggingface_hub.repository - git version 2.25.1
260
- git-lfs/2.9.2 (GitHub; linux amd64; go 1.13.5)
261
- [10:41:35] - DEBUG - huggingface_hub.repository - [Repository] is a valid git repo
262
-
263
-
264
-
265
-
266
-
267
-
268
-
269
-
270
-
271
-
272
-
273
-
274
-
275
-
276
-
277
-
278
-
279
-
280
-
281
-
282
-
283
-
 
 
 
284
 
285
-
286
-
287
-
288
-
289
-
290
-
291
-
292
-
293
-
294
-
295
-
296
-
297
-
298
-
299
-
300
-
301
-
302
-
303
-
304
-
305
-
306
-
307
-
308
-
309
-
310
-
311
-
312
-
313
-
314
-
315
-
316
-
317
-
318
-
319
-
320
-
321
-
322
-
323
-
324
-
325
-
326
-
327
-
328
-
329
-
330
-
331
-
332
-
333
-
334
-
335
-
336
-
337
-
338
-
339
-
340
-
341
-
342
-
343
-
344
-
345
-
346
-
347
-
348
-
349
-
350
-
351
-
352
-
353
-
354
-
355
-
356
-
357
-
358
-
359
-
360
-
361
-
362
-
363
-
364
-
365
-
366
-
367
-
368
-
369
-
370
-
371
-
372
-
373
-
374
-
375
-
376
-
377
-
378
-
379
-
380
-
381
-
382
-
383
-
384
-
385
-
386
-
387
-
388
-
389
 
390
-
391
-
392
-
393
-
394
-
395
 
396
-
397
 
398
-
399
 
400
-
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
401
 
 
402
 
 
403
 
404
 
405
 
406
 
407
-
408
- [10:42:04] - INFO - huggingface_hub.repository - git version 2.25.1
 
 
409
  git-lfs/2.9.2 (GitHub; linux amd64; go 1.13.5)
410
- [10:42:04] - DEBUG - huggingface_hub.repository - [Repository] is a valid git repo
 
1
+ 2021-07-09 13:17:54.997560: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory
2
+ [13:17:56] - INFO - __main__ - Training/evaluation parameters TrainingArguments(
3
  _n_gpu=-1,
4
  adafactor=False,
5
  adam_beta1=0.9,
 
35
  log_level=-1,
36
  log_level_replica=-1,
37
  log_on_each_node=True,
38
+ logging_dir=./runs/Jul09_13-17-56_t1v-n-112df4a9-w-0,
39
  logging_first_step=False,
40
  logging_steps=500,
41
  logging_strategy=IntervalStrategy.STEPS,
 
74
  warmup_steps=1000,
75
  weight_decay=0.0,
76
  )
77
+ [13:17:56] - DEBUG - urllib3.connectionpool - Starting new HTTPS connection (1): s3.amazonaws.com:443
78
+ [13:17:56] - DEBUG - urllib3.connectionpool - https://s3.amazonaws.com:443 "HEAD /datasets.huggingface.co/datasets/datasets/oscar/oscar.py HTTP/1.1" 404 0
79
+ [13:17:56] - DEBUG - urllib3.connectionpool - Starting new HTTPS connection (1): raw.githubusercontent.com:443
80
+ [13:17:56] - DEBUG - urllib3.connectionpool - https://raw.githubusercontent.com:443 "HEAD /huggingface/datasets/master/datasets/oscar/oscar.py HTTP/1.1" 200 0
81
+ [13:17:56] - DEBUG - urllib3.connectionpool - Starting new HTTPS connection (1): raw.githubusercontent.com:443
82
+ [13:17:56] - DEBUG - urllib3.connectionpool - https://raw.githubusercontent.com:443 "HEAD /huggingface/datasets/master/datasets/oscar/dataset_infos.json HTTP/1.1" 200 0
83
+ [13:17:56] - WARNING - datasets.builder - Reusing dataset oscar (/home/nipunsadvilkar/.cache/huggingface/datasets/oscar/unshuffled_deduplicated_als/1.0.0/84838bd49d2295f62008383b05620571535451d84545037bb94d6f3501651df2)
84
+ [13:17:56] - DEBUG - urllib3.connectionpool - Starting new HTTPS connection (1): s3.amazonaws.com:443
85
+ [13:17:57] - DEBUG - urllib3.connectionpool - https://s3.amazonaws.com:443 "HEAD /datasets.huggingface.co/datasets/datasets/oscar/oscar.py HTTP/1.1" 404 0
86
+ [13:17:57] - DEBUG - urllib3.connectionpool - Starting new HTTPS connection (1): raw.githubusercontent.com:443
87
+ [13:17:57] - DEBUG - urllib3.connectionpool - https://raw.githubusercontent.com:443 "HEAD /huggingface/datasets/master/datasets/oscar/oscar.py HTTP/1.1" 200 0
88
+ [13:17:57] - DEBUG - urllib3.connectionpool - Starting new HTTPS connection (1): raw.githubusercontent.com:443
89
+ [13:17:57] - DEBUG - urllib3.connectionpool - https://raw.githubusercontent.com:443 "HEAD /huggingface/datasets/master/datasets/oscar/dataset_infos.json HTTP/1.1" 200 0
90
+ [13:17:57] - WARNING - datasets.builder - Reusing dataset oscar (/home/nipunsadvilkar/.cache/huggingface/datasets/oscar/unshuffled_deduplicated_als/1.0.0/84838bd49d2295f62008383b05620571535451d84545037bb94d6f3501651df2)
91
+ [13:17:57] - DEBUG - urllib3.connectionpool - Starting new HTTPS connection (1): s3.amazonaws.com:443
92
+ [13:17:57] - DEBUG - urllib3.connectionpool - https://s3.amazonaws.com:443 "HEAD /datasets.huggingface.co/datasets/datasets/oscar/oscar.py HTTP/1.1" 404 0
93
+ [13:17:57] - DEBUG - urllib3.connectionpool - Starting new HTTPS connection (1): raw.githubusercontent.com:443
94
+ [13:17:57] - DEBUG - urllib3.connectionpool - https://raw.githubusercontent.com:443 "HEAD /huggingface/datasets/master/datasets/oscar/oscar.py HTTP/1.1" 200 0
95
+ [13:17:57] - DEBUG - urllib3.connectionpool - Starting new HTTPS connection (1): raw.githubusercontent.com:443
96
+ [13:17:57] - DEBUG - urllib3.connectionpool - https://raw.githubusercontent.com:443 "HEAD /huggingface/datasets/master/datasets/oscar/dataset_infos.json HTTP/1.1" 200 0
97
+ [13:17:57] - WARNING - datasets.builder - Reusing dataset oscar (/home/nipunsadvilkar/.cache/huggingface/datasets/oscar/unshuffled_deduplicated_als/1.0.0/84838bd49d2295f62008383b05620571535451d84545037bb94d6f3501651df2)
98
+ [13:17:57] - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/nipunsadvilkar/.cache/huggingface/datasets/oscar/unshuffled_deduplicated_als/1.0.0/84838bd49d2295f62008383b05620571535451d84545037bb94d6f3501651df2/cache-0f52086e7b10d7e8.arrow
99
+ [13:17:57] - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/nipunsadvilkar/.cache/huggingface/datasets/oscar/unshuffled_deduplicated_als/1.0.0/84838bd49d2295f62008383b05620571535451d84545037bb94d6f3501651df2/cache-a39e5f5a5c6c69fc.arrow
100
+
 
 
 
 
 
101
  0%| | 0/5 [00:00<?, ?ba/s]
102
  20%|██ | 1/5 [00:00<00:03, 1.33ba/s]
103
  40%|████ | 2/5 [00:01<00:02, 1.25ba/s]
104
  60%|██████ | 3/5 [00:02<00:01, 1.22ba/s]
105
  80%|████████ | 4/5 [00:03<00:00, 1.14ba/s]
106
+
107
  0%| | 0/1 [00:00<?, ?ba/s]
108
+ [13:18:01] - INFO - absl - Starting the local TPU driver.
109
+ [13:18:01] - INFO - absl - Unable to initialize backend 'tpu_driver': Not found: Unable to find driver in registry given worker: local://
110
+ [13:18:01] - INFO - absl - Unable to initialize backend 'gpu': Not found: Could not find registered platform with name: "cuda". Available platform names are: Interpreter Host TPU
111
+ 2021-07-09 13:18:04.352179: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcuda.so.1'; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory
112
+ 2021-07-09 13:18:04.352213: W tensorflow/stream_executor/cuda/cuda_driver.cc:326] failed call to cuInit: UNKNOWN ERROR (303)
113
  /home/nipunsadvilkar/roberta_mr_env/lib/python3.8/site-packages/jax/lib/xla_bridge.py:382: UserWarning: jax.host_count has been renamed to jax.process_count. This alias will eventually be removed; please update your code.
114
  warnings.warn(
115
  /home/nipunsadvilkar/roberta_mr_env/lib/python3.8/site-packages/jax/lib/xla_bridge.py:369: UserWarning: jax.host_id has been renamed to jax.process_index. This alias will eventually be removed; please update your code.
116
  warnings.warn(
117
 
118
 
119
+
120
+
121
+
122
+
123
+
124
+
125
+
126
+
127
+
128
+
129
+
130
+
131
+
132
+
133
+
134
+
135
+
136
+
137
+
138
+
139
+
140
+
141
+
142
+
143
+
144
+
145
+
146
+
147
+
148
+
149
+
150
+
151
+
152
+
153
+
154
+
155
+
156
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
157
 
 
158
 
159
+
160
+
161
+
162
+
163
+
164
+
165
+
166
+
167
+
168
+
169
+
170
+
171
+
172
+
173
+
174
+
175
+
176
+
177
+
178
+
179
+
180
+
181
+
182
+
183
+
184
+
185
+
186
+
187
+
188
+
189
+
190
+
191
+
192
+
193
+
194
+
195
 
196
+
197
+
198
+
199
+
200
+
201
+
202
+
203
+
204
+
205
+
206
+
207
+
208
+
209
+
210
+
211
+
212
+
213
+
214
+
215
+
216
+
217
+
218
+
219
+
220
+
221
+
222
+
223
+
224
+
225
+
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
226
 
227
+
228
+
229
+
230
+
231
+
232
 
 
233
 
 
234
 
235
+
236
+
237
+
238
+
239
+
240
+
241
+
242
+
243
+
244
+
245
+
246
+
247
+
248
+
249
+
250
+
251
+
252
+
253
 
254
+
255
 
256
+
257
 
258
 
259
 
260
 
261
+
262
+
263
+
264
+ [13:19:46] - INFO - huggingface_hub.repository - git version 2.25.1
265
  git-lfs/2.9.2 (GitHub; linux amd64; go 1.13.5)
266
+ [13:19:47] - DEBUG - huggingface_hub.repository - [Repository] is a valid git repo
run.sh CHANGED
@@ -17,4 +17,4 @@ python run_mlm_flax.py \
17
  --run_name hf-flax-robert-base-mr \
18
  --push_to_hub_model_id="flax-community/roberta-base-mr" \
19
  --push_to_hub_token=$HUB_TOKEN \
20
- --push_to_hub 2>&1 | tee run.log
 
17
  --run_name hf-flax-robert-base-mr \
18
  --push_to_hub_model_id="flax-community/roberta-base-mr" \
19
  --push_to_hub_token=$HUB_TOKEN \
20
+ --push_to_hub 2>&1 | tee run.log
run_mlm_flax.py CHANGED
@@ -431,7 +431,8 @@ if __name__ == "__main__":
431
  total_length = len(concatenated_examples[list(examples.keys())[0]])
432
  # We drop the small remainder, we could add padding if the model supported it instead of this drop, you can
433
  # customize this part to your needs.
434
- total_length = (total_length // max_seq_length) * max_seq_length
 
435
  # Split by chunks of max_len.
436
  result = {
437
  k: [t[i : i + max_seq_length] for i in range(0, total_length, max_seq_length)]
@@ -457,6 +458,7 @@ if __name__ == "__main__":
457
  if has_tensorboard and jax.process_index() == 0:
458
  try:
459
  from flax.metrics.tensorboard import SummaryWriter
 
460
  summary_writer = SummaryWriter(log_dir=Path(training_args.output_dir))
461
  except ImportError as ie:
462
  has_tensorboard = False
@@ -477,7 +479,14 @@ if __name__ == "__main__":
477
  rng = jax.random.PRNGKey(training_args.seed)
478
  dropout_rngs = jax.random.split(rng, jax.local_device_count())
479
 
480
- model = FlaxAutoModelForMaskedLM.from_config(config, seed=training_args.seed, dtype=getattr(jnp, model_args.dtype))
 
 
 
 
 
 
 
481
 
482
  # Store some constant
483
  num_epochs = int(training_args.num_train_epochs)
@@ -654,7 +663,6 @@ if __name__ == "__main__":
654
 
655
  # Save metrics
656
  if has_tensorboard and jax.process_index() == 0:
657
- cur_step = epoch * (len(tokenized_datasets["train"]) // train_batch_size)
658
  write_eval_metric(summary_writer, eval_metrics, cur_step)
659
 
660
  if cur_step % training_args.save_steps == 0 and cur_step > 0:
 
431
  total_length = len(concatenated_examples[list(examples.keys())[0]])
432
  # We drop the small remainder, we could add padding if the model supported it instead of this drop, you can
433
  # customize this part to your needs.
434
+ if total_length >= max_seq_length:
435
+ total_length = (total_length // max_seq_length) * max_seq_length
436
  # Split by chunks of max_len.
437
  result = {
438
  k: [t[i : i + max_seq_length] for i in range(0, total_length, max_seq_length)]
 
458
  if has_tensorboard and jax.process_index() == 0:
459
  try:
460
  from flax.metrics.tensorboard import SummaryWriter
461
+
462
  summary_writer = SummaryWriter(log_dir=Path(training_args.output_dir))
463
  except ImportError as ie:
464
  has_tensorboard = False
 
479
  rng = jax.random.PRNGKey(training_args.seed)
480
  dropout_rngs = jax.random.split(rng, jax.local_device_count())
481
 
482
+ if model_args.model_name_or_path:
483
+ model = FlaxAutoModelForMaskedLM.from_pretrained(
484
+ model_args.model_name_or_path, config=config, seed=training_args.seed, dtype=getattr(jnp, model_args.dtype)
485
+ )
486
+ else:
487
+ model = FlaxAutoModelForMaskedLM.from_config(
488
+ config, seed=training_args.seed, dtype=getattr(jnp, model_args.dtype)
489
+ )
490
 
491
  # Store some constant
492
  num_epochs = int(training_args.num_train_epochs)
 
663
 
664
  # Save metrics
665
  if has_tensorboard and jax.process_index() == 0:
 
666
  write_eval_metric(summary_writer, eval_metrics, cur_step)
667
 
668
  if cur_step % training_args.save_steps == 0 and cur_step > 0:
test_mr_tokenizer.py ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ from tokenizers import Tokenizer
2
+
3
+ tokenizer = Tokenizer.from_file("tokenizer.json")
4
+
5
+ text = "गेल्या अनेक दिवसांपासून केंद्र सरकरा विरुद्ध ट्विटर इंडिया यांच्यामध्ये सरकारच्या नव्या मार्गदर्शक सूचना किंवा नियमावलीवरून वाद सुरू आहे."
6
+
7
+ output = tokenizer.encode(text)
8
+ print(tokenizer.decode(output.ids))
wandb/debug-internal.log CHANGED
@@ -1 +1 @@
1
- run-20210709_103433-d7n9baaw/logs/debug-internal.log
 
1
+ run-20210709_125049-89spqu1d/logs/debug-internal.log
wandb/debug.log CHANGED
@@ -1 +1 @@
1
- run-20210709_103433-d7n9baaw/logs/debug.log
 
1
+ run-20210709_125049-89spqu1d/logs/debug.log
wandb/latest-run CHANGED
@@ -1 +1 @@
1
- run-20210709_103433-d7n9baaw
 
1
+ run-20210709_125049-89spqu1d
wandb/run-20210709_111555-275xd40l/files/config.yaml ADDED
@@ -0,0 +1,305 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ wandb_version: 1
2
+
3
+ _wandb:
4
+ desc: null
5
+ value:
6
+ cli_version: 0.10.33
7
+ framework: huggingface
8
+ huggingface_version: 4.9.0.dev0
9
+ is_jupyter_run: false
10
+ is_kaggle_kernel: false
11
+ python_version: 3.8.10
12
+ t:
13
+ 1:
14
+ - 11
15
+ 2:
16
+ - 11
17
+ 4: 3.8.10
18
+ 5: 0.10.33
19
+ 6: 4.9.0.dev0
20
+ 8:
21
+ - 5
22
+ adafactor:
23
+ desc: null
24
+ value: false
25
+ adam_beta1:
26
+ desc: null
27
+ value: 0.9
28
+ adam_beta2:
29
+ desc: null
30
+ value: 0.999
31
+ adam_epsilon:
32
+ desc: null
33
+ value: 1.0e-08
34
+ cache_dir:
35
+ desc: null
36
+ value: null
37
+ config_name:
38
+ desc: null
39
+ value: ./
40
+ dataloader_drop_last:
41
+ desc: null
42
+ value: false
43
+ dataloader_num_workers:
44
+ desc: null
45
+ value: 0
46
+ dataloader_pin_memory:
47
+ desc: null
48
+ value: true
49
+ dataset_config_name:
50
+ desc: null
51
+ value: unshuffled_deduplicated_als
52
+ dataset_name:
53
+ desc: null
54
+ value: oscar
55
+ ddp_find_unused_parameters:
56
+ desc: null
57
+ value: null
58
+ debug:
59
+ desc: null
60
+ value: []
61
+ deepspeed:
62
+ desc: null
63
+ value: null
64
+ disable_tqdm:
65
+ desc: null
66
+ value: false
67
+ do_eval:
68
+ desc: null
69
+ value: false
70
+ do_predict:
71
+ desc: null
72
+ value: false
73
+ do_train:
74
+ desc: null
75
+ value: false
76
+ dtype:
77
+ desc: null
78
+ value: float32
79
+ eval_accumulation_steps:
80
+ desc: null
81
+ value: null
82
+ eval_steps:
83
+ desc: null
84
+ value: 500
85
+ evaluation_strategy:
86
+ desc: null
87
+ value: IntervalStrategy.NO
88
+ fp16:
89
+ desc: null
90
+ value: false
91
+ fp16_backend:
92
+ desc: null
93
+ value: auto
94
+ fp16_full_eval:
95
+ desc: null
96
+ value: false
97
+ fp16_opt_level:
98
+ desc: null
99
+ value: O1
100
+ gradient_accumulation_steps:
101
+ desc: null
102
+ value: 1
103
+ greater_is_better:
104
+ desc: null
105
+ value: null
106
+ group_by_length:
107
+ desc: null
108
+ value: false
109
+ ignore_data_skip:
110
+ desc: null
111
+ value: false
112
+ label_names:
113
+ desc: null
114
+ value: null
115
+ label_smoothing_factor:
116
+ desc: null
117
+ value: 0.0
118
+ learning_rate:
119
+ desc: null
120
+ value: 0.0003
121
+ length_column_name:
122
+ desc: null
123
+ value: length
124
+ line_by_line:
125
+ desc: null
126
+ value: false
127
+ load_best_model_at_end:
128
+ desc: null
129
+ value: false
130
+ local_rank:
131
+ desc: null
132
+ value: -1
133
+ log_level:
134
+ desc: null
135
+ value: -1
136
+ log_level_replica:
137
+ desc: null
138
+ value: -1
139
+ log_on_each_node:
140
+ desc: null
141
+ value: true
142
+ logging_dir:
143
+ desc: null
144
+ value: ./runs/Jul09_11-15-50_t1v-n-112df4a9-w-0
145
+ logging_first_step:
146
+ desc: null
147
+ value: false
148
+ logging_steps:
149
+ desc: null
150
+ value: 500
151
+ logging_strategy:
152
+ desc: null
153
+ value: IntervalStrategy.STEPS
154
+ lr_scheduler_type:
155
+ desc: null
156
+ value: SchedulerType.LINEAR
157
+ max_grad_norm:
158
+ desc: null
159
+ value: 1.0
160
+ max_seq_length:
161
+ desc: null
162
+ value: 128
163
+ max_steps:
164
+ desc: null
165
+ value: -1
166
+ metric_for_best_model:
167
+ desc: null
168
+ value: null
169
+ mlm_probability:
170
+ desc: null
171
+ value: 0.15
172
+ model_name_or_path:
173
+ desc: null
174
+ value: null
175
+ model_type:
176
+ desc: null
177
+ value: roberta
178
+ mp_parameters:
179
+ desc: null
180
+ value: ''
181
+ no_cuda:
182
+ desc: null
183
+ value: false
184
+ num_train_epochs:
185
+ desc: null
186
+ value: 8.0
187
+ output_dir:
188
+ desc: null
189
+ value: ./
190
+ overwrite_cache:
191
+ desc: null
192
+ value: false
193
+ overwrite_output_dir:
194
+ desc: null
195
+ value: true
196
+ pad_to_max_length:
197
+ desc: null
198
+ value: false
199
+ past_index:
200
+ desc: null
201
+ value: -1
202
+ per_device_eval_batch_size:
203
+ desc: null
204
+ value: 4
205
+ per_device_train_batch_size:
206
+ desc: null
207
+ value: 4
208
+ per_gpu_eval_batch_size:
209
+ desc: null
210
+ value: null
211
+ per_gpu_train_batch_size:
212
+ desc: null
213
+ value: null
214
+ prediction_loss_only:
215
+ desc: null
216
+ value: false
217
+ preprocessing_num_workers:
218
+ desc: null
219
+ value: null
220
+ push_to_hub:
221
+ desc: null
222
+ value: false
223
+ push_to_hub_model_id:
224
+ desc: null
225
+ value: ''
226
+ push_to_hub_organization:
227
+ desc: null
228
+ value: null
229
+ push_to_hub_token:
230
+ desc: null
231
+ value: null
232
+ remove_unused_columns:
233
+ desc: null
234
+ value: true
235
+ report_to:
236
+ desc: null
237
+ value:
238
+ - tensorboard
239
+ - wandb
240
+ resume_from_checkpoint:
241
+ desc: null
242
+ value: null
243
+ run_name:
244
+ desc: null
245
+ value: ./
246
+ save_on_each_node:
247
+ desc: null
248
+ value: false
249
+ save_steps:
250
+ desc: null
251
+ value: 500
252
+ save_strategy:
253
+ desc: null
254
+ value: IntervalStrategy.STEPS
255
+ save_total_limit:
256
+ desc: null
257
+ value: null
258
+ seed:
259
+ desc: null
260
+ value: 42
261
+ sharded_ddp:
262
+ desc: null
263
+ value: []
264
+ skip_memory_metrics:
265
+ desc: null
266
+ value: true
267
+ tokenizer_name:
268
+ desc: null
269
+ value: ./
270
+ tpu_metrics_debug:
271
+ desc: null
272
+ value: false
273
+ tpu_num_cores:
274
+ desc: null
275
+ value: null
276
+ train_file:
277
+ desc: null
278
+ value: null
279
+ train_ref_file:
280
+ desc: null
281
+ value: null
282
+ use_fast_tokenizer:
283
+ desc: null
284
+ value: true
285
+ use_legacy_prediction_loop:
286
+ desc: null
287
+ value: false
288
+ validation_file:
289
+ desc: null
290
+ value: null
291
+ validation_ref_file:
292
+ desc: null
293
+ value: null
294
+ validation_split_percentage:
295
+ desc: null
296
+ value: 5
297
+ warmup_ratio:
298
+ desc: null
299
+ value: 0.0
300
+ warmup_steps:
301
+ desc: null
302
+ value: 1000
303
+ weight_decay:
304
+ desc: null
305
+ value: 0.0
wandb/run-20210709_111555-275xd40l/files/output.log ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ [11:15:56] - WARNING - __main__ - Unable to display metrics through TensorBoard because some package are not installed: No module named 'tensorflow'
3
+ /home/nipunsadvilkar/roberta_mr_env/lib/python3.8/site-packages/jax/lib/xla_bridge.py:382: UserWarning: jax.host_count has been renamed to jax.process_count. This alias will eventually be removed; please update your code.
4
+ warnings.warn(
5
+ /home/nipunsadvilkar/roberta_mr_env/lib/python3.8/site-packages/jax/lib/xla_bridge.py:369: UserWarning: jax.host_id has been renamed to jax.process_index. This alias will eventually be removed; please update your code.
6
+ warnings.warn(
7
+ Epoch ... (1/8): 0%| | 0/8 [00:00<?, ?it/s]
8
+
9
+
10
+ Epoch ... (1/8): 12%|███████████████████ | 1/8 [01:13<08:36, 73.75s/it]
11
+
12
+ Epoch ... (1/8): 25%|██████████████████████████████████████ | 2/8 [01:18<03:19, 33.23s/it]
13
+
14
+
15
+ Epoch ... (1/8): 38%|█████████████████████████████████████████████████████████ | 3/8 [01:23<01:41, 20.39s/it]
16
+ Training...: 20%|██████████████████████████████▏ | 28/142 [00:00<00:03, 37.68it/s]
17
+ Training...: 51%|█████████████████████████████████████████████████████████████████████████████▌ | 72/142 [00:02<00:01, 36.09it/s]
18
+
19
+
20
+ Step... (500 | Loss: 8.205772399902344, Acc: 0.0773010179400444): 50%|███████████████████████████████████████████████████▌ | 4/8 [01:39<01:14, 18.65s/it]
21
+
22
+ Step... (500 | Loss: 8.205772399902344, Acc: 0.0773010179400444): 62%|████████████████████████████████████████████████████████████████▍ | 5/8 [01:44<00:40, 13.57s/it]
23
+
24
+
25
+ Step... (500 | Loss: 8.205772399902344, Acc: 0.0773010179400444): 75%|█████████████████████████████████████████████████████████████████████████████▎ | 6/8 [01:49<00:21, 10.68s/it]
26
+
27
+ Evaluating ...: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 10/10 [00:00<00:00, 77.04it/s]
28
+ Training...: 3%|████▎ | 4/142 [00:00<00:03, 35.08it/s]
29
+ Evaluating ...: 80%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▌ | 8/10 [00:00<00:00, 76.37it/s]
30
+
31
+
32
+
33
+ Step... (1000 | Loss: 7.925442218780518, Acc: 0.09575153142213821): 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████| 8/8 [02:05<00:00, 15.69s/it]
wandb/run-20210709_111555-275xd40l/files/requirements.txt ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ absl-py==0.13.0
2
+ aiohttp==3.7.4.post0
3
+ async-timeout==3.0.1
4
+ attrs==21.2.0
5
+ backcall==0.2.0
6
+ cachetools==4.2.2
7
+ certifi==2021.5.30
8
+ chardet==4.0.0
9
+ chex==0.0.8
10
+ click==8.0.1
11
+ configparser==5.0.2
12
+ cycler==0.10.0
13
+ datasets==1.9.1.dev0
14
+ decorator==5.0.9
15
+ dill==0.3.4
16
+ dm-tree==0.1.6
17
+ docker-pycreds==0.4.0
18
+ filelock==3.0.12
19
+ flatbuffers==2.0
20
+ flax==0.3.4
21
+ fsspec==2021.6.1
22
+ gitdb==4.0.7
23
+ gitpython==3.1.18
24
+ google-auth-oauthlib==0.4.4
25
+ google-auth==1.32.1
26
+ grpcio==1.38.1
27
+ huggingface-hub==0.0.12
28
+ idna==2.10
29
+ ipython-genutils==0.2.0
30
+ ipython==7.25.0
31
+ jax==0.2.16
32
+ jaxlib==0.1.68
33
+ jedi==0.18.0
34
+ joblib==1.0.1
35
+ kiwisolver==1.3.1
36
+ libtpu-nightly==0.1.dev20210615
37
+ markdown==3.3.4
38
+ matplotlib-inline==0.1.2
39
+ matplotlib==3.4.2
40
+ msgpack==1.0.2
41
+ multidict==5.1.0
42
+ multiprocess==0.70.12.2
43
+ numpy==1.21.0
44
+ oauthlib==3.1.1
45
+ opt-einsum==3.3.0
46
+ optax==0.0.9
47
+ packaging==21.0
48
+ pandas==1.3.0
49
+ parso==0.8.2
50
+ pathtools==0.1.2
51
+ pexpect==4.8.0
52
+ pickleshare==0.7.5
53
+ pillow==8.3.1
54
+ pip==20.0.2
55
+ pkg-resources==0.0.0
56
+ promise==2.3
57
+ prompt-toolkit==3.0.19
58
+ protobuf==3.17.3
59
+ psutil==5.8.0
60
+ ptyprocess==0.7.0
61
+ pyarrow==4.0.1
62
+ pyasn1-modules==0.2.8
63
+ pyasn1==0.4.8
64
+ pygments==2.9.0
65
+ pyparsing==2.4.7
66
+ python-dateutil==2.8.1
67
+ pytz==2021.1
68
+ pyyaml==5.4.1
69
+ regex==2021.7.6
70
+ requests-oauthlib==1.3.0
71
+ requests==2.25.1
72
+ rsa==4.7.2
73
+ sacremoses==0.0.45
74
+ scipy==1.7.0
75
+ sentry-sdk==1.3.0
76
+ setuptools==44.0.0
77
+ shortuuid==1.0.1
78
+ six==1.16.0
79
+ smmap==4.0.0
80
+ subprocess32==3.5.4
81
+ tensorboard-data-server==0.6.1
82
+ tensorboard-plugin-wit==1.8.0
83
+ tensorboard==2.5.0
84
+ tokenizers==0.10.3
85
+ toolz==0.11.1
86
+ tqdm==4.61.2
87
+ traitlets==5.0.5
88
+ transformers==4.9.0.dev0
89
+ typing-extensions==3.10.0.0
90
+ urllib3==1.26.6
91
+ wandb==0.10.33
92
+ wcwidth==0.2.5
93
+ werkzeug==2.0.1
94
+ wheel==0.36.2
95
+ xxhash==2.0.2
96
+ yarl==1.6.3
wandb/run-20210709_111555-275xd40l/files/wandb-metadata.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "os": "Linux-5.4.0-1043-gcp-x86_64-with-glibc2.29",
3
+ "python": "3.8.10",
4
+ "heartbeatAt": "2021-07-09T11:15:56.409747",
5
+ "startedAt": "2021-07-09T11:15:55.658458",
6
+ "docker": null,
7
+ "cpu_count": 96,
8
+ "cuda": null,
9
+ "args": [
10
+ "--output_dir=./",
11
+ "--model_type=roberta",
12
+ "--config_name=./",
13
+ "--tokenizer_name=./",
14
+ "--dataset_name=oscar",
15
+ "--dataset_config_name=unshuffled_deduplicated_als",
16
+ "--max_seq_length=128",
17
+ "--per_device_train_batch_size=4",
18
+ "--per_device_eval_batch_size=4",
19
+ "--learning_rate=3e-4",
20
+ "--warmup_steps=1000",
21
+ "--overwrite_output_dir",
22
+ "--num_train_epochs=8"
23
+ ],
24
+ "state": "running",
25
+ "program": "run_mlm_flax.py",
26
+ "codePath": "run_mlm_flax.py",
27
+ "git": {
28
+ "remote": "https://huggingface.co/flax-community/roberta-base-mr",
29
+ "commit": "faa64e8a79301832a56c78b2b293675039070bb0"
30
+ },
31
+ "email": "nipunsadvilkar@gmail.com",
32
+ "root": "/home/nipunsadvilkar/sample/roberta-base-mr",
33
+ "host": "t1v-n-112df4a9-w-0",
34
+ "username": "nipunsadvilkar",
35
+ "executable": "/home/nipunsadvilkar/roberta_mr_env/bin/python"
36
+ }
wandb/run-20210709_111555-275xd40l/files/wandb-summary.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {}
wandb/run-20210709_111555-275xd40l/logs/debug-internal.log ADDED
@@ -0,0 +1,175 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2021-07-09 11:15:56,246 INFO MainThread:29289 [internal.py:wandb_internal():88] W&B internal server running at pid: 29289, started at: 2021-07-09 11:15:56.246443
2
+ 2021-07-09 11:15:56,248 DEBUG HandlerThread:29289 [handler.py:handle_request():124] handle_request: check_version
3
+ 2021-07-09 11:15:56,248 INFO WriterThread:29289 [datastore.py:open_for_write():80] open: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/run-275xd40l.wandb
4
+ 2021-07-09 11:15:56,249 DEBUG SenderThread:29289 [sender.py:send():179] send: header
5
+ 2021-07-09 11:15:56,249 DEBUG SenderThread:29289 [sender.py:send_request():193] send_request: check_version
6
+ 2021-07-09 11:15:56,311 DEBUG SenderThread:29289 [sender.py:send():179] send: run
7
+ 2021-07-09 11:15:56,407 DEBUG HandlerThread:29289 [handler.py:handle_request():124] handle_request: run_start
8
+ 2021-07-09 11:15:56,408 INFO SenderThread:29289 [dir_watcher.py:__init__():168] watching files in: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files
9
+ 2021-07-09 11:15:56,408 INFO SenderThread:29289 [sender.py:_start_run_threads():716] run started: 275xd40l with start time 1625829355
10
+ 2021-07-09 11:15:56,408 DEBUG SenderThread:29289 [sender.py:send():179] send: summary
11
+ 2021-07-09 11:15:56,409 INFO SenderThread:29289 [sender.py:_save_file():841] saving file wandb-summary.json with policy end
12
+ 2021-07-09 11:15:56,409 DEBUG HandlerThread:29289 [meta.py:__init__():39] meta init
13
+ 2021-07-09 11:15:56,409 DEBUG HandlerThread:29289 [meta.py:__init__():53] meta init done
14
+ 2021-07-09 11:15:56,409 DEBUG HandlerThread:29289 [meta.py:probe():210] probe
15
+ 2021-07-09 11:15:56,410 DEBUG HandlerThread:29289 [meta.py:_setup_git():200] setup git
16
+ 2021-07-09 11:15:56,426 DEBUG HandlerThread:29289 [meta.py:_setup_git():207] setup git done
17
+ 2021-07-09 11:15:56,426 DEBUG HandlerThread:29289 [meta.py:_save_pip():57] save pip
18
+ 2021-07-09 11:15:56,426 DEBUG HandlerThread:29289 [meta.py:_save_pip():71] save pip done
19
+ 2021-07-09 11:15:56,426 DEBUG HandlerThread:29289 [meta.py:probe():252] probe done
20
+ 2021-07-09 11:15:56,454 DEBUG SenderThread:29289 [sender.py:send():179] send: files
21
+ 2021-07-09 11:15:56,455 INFO SenderThread:29289 [sender.py:_save_file():841] saving file wandb-metadata.json with policy now
22
+ 2021-07-09 11:15:56,459 DEBUG HandlerThread:29289 [handler.py:handle_request():124] handle_request: stop_status
23
+ 2021-07-09 11:15:56,460 DEBUG SenderThread:29289 [sender.py:send_request():193] send_request: stop_status
24
+ 2021-07-09 11:15:56,485 DEBUG SenderThread:29289 [sender.py:send():179] send: config
25
+ 2021-07-09 11:15:56,485 DEBUG SenderThread:29289 [sender.py:send():179] send: config
26
+ 2021-07-09 11:15:56,485 DEBUG SenderThread:29289 [sender.py:send():179] send: config
27
+ 2021-07-09 11:15:56,689 INFO Thread-11 :29289 [upload_job.py:push():137] Uploaded file /tmp/tmp260my7l0wandb/rfatvpgl-wandb-metadata.json
28
+ 2021-07-09 11:15:57,409 INFO Thread-8 :29289 [dir_watcher.py:_on_file_created():216] file/dir created: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/wandb-summary.json
29
+ 2021-07-09 11:15:57,409 INFO Thread-8 :29289 [dir_watcher.py:_on_file_created():216] file/dir created: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/wandb-metadata.json
30
+ 2021-07-09 11:15:57,409 INFO Thread-8 :29289 [dir_watcher.py:_on_file_created():216] file/dir created: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/output.log
31
+ 2021-07-09 11:15:57,409 INFO Thread-8 :29289 [dir_watcher.py:_on_file_created():216] file/dir created: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/requirements.txt
32
+ 2021-07-09 11:15:59,409 INFO Thread-8 :29289 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/output.log
33
+ 2021-07-09 11:16:03,410 INFO Thread-8 :29289 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/output.log
34
+ 2021-07-09 11:16:05,412 INFO Thread-8 :29289 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/output.log
35
+ 2021-07-09 11:16:11,521 DEBUG HandlerThread:29289 [handler.py:handle_request():124] handle_request: stop_status
36
+ 2021-07-09 11:16:11,521 DEBUG SenderThread:29289 [sender.py:send_request():193] send_request: stop_status
37
+ 2021-07-09 11:16:24,485 DEBUG SenderThread:29289 [sender.py:send():179] send: stats
38
+ 2021-07-09 11:16:26,562 DEBUG HandlerThread:29289 [handler.py:handle_request():124] handle_request: stop_status
39
+ 2021-07-09 11:16:26,562 DEBUG SenderThread:29289 [sender.py:send_request():193] send_request: stop_status
40
+ 2021-07-09 11:16:27,421 INFO Thread-8 :29289 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/config.yaml
41
+ 2021-07-09 11:16:41,590 DEBUG HandlerThread:29289 [handler.py:handle_request():124] handle_request: stop_status
42
+ 2021-07-09 11:16:41,590 DEBUG SenderThread:29289 [sender.py:send_request():193] send_request: stop_status
43
+ 2021-07-09 11:16:54,566 DEBUG SenderThread:29289 [sender.py:send():179] send: stats
44
+ 2021-07-09 11:16:56,619 DEBUG HandlerThread:29289 [handler.py:handle_request():124] handle_request: stop_status
45
+ 2021-07-09 11:16:56,619 DEBUG SenderThread:29289 [sender.py:send_request():193] send_request: stop_status
46
+ 2021-07-09 11:17:11,651 DEBUG HandlerThread:29289 [handler.py:handle_request():124] handle_request: stop_status
47
+ 2021-07-09 11:17:11,652 DEBUG SenderThread:29289 [sender.py:send_request():193] send_request: stop_status
48
+ 2021-07-09 11:17:13,440 INFO Thread-8 :29289 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/output.log
49
+ 2021-07-09 11:17:15,441 INFO Thread-8 :29289 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/output.log
50
+ 2021-07-09 11:17:17,442 INFO Thread-8 :29289 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/output.log
51
+ 2021-07-09 11:17:19,443 INFO Thread-8 :29289 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/output.log
52
+ 2021-07-09 11:17:21,444 INFO Thread-8 :29289 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/output.log
53
+ 2021-07-09 11:17:23,444 INFO Thread-8 :29289 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/output.log
54
+ 2021-07-09 11:17:24,641 DEBUG SenderThread:29289 [sender.py:send():179] send: stats
55
+ 2021-07-09 11:17:25,445 INFO Thread-8 :29289 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/output.log
56
+ 2021-07-09 11:17:26,687 DEBUG HandlerThread:29289 [handler.py:handle_request():124] handle_request: stop_status
57
+ 2021-07-09 11:17:26,688 DEBUG SenderThread:29289 [sender.py:send_request():193] send_request: stop_status
58
+ 2021-07-09 11:17:27,446 INFO Thread-8 :29289 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/output.log
59
+ 2021-07-09 11:17:29,447 INFO Thread-8 :29289 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/output.log
60
+ 2021-07-09 11:17:33,449 INFO Thread-8 :29289 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/output.log
61
+ 2021-07-09 11:17:41,453 INFO Thread-8 :29289 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/output.log
62
+ 2021-07-09 11:17:41,727 DEBUG HandlerThread:29289 [handler.py:handle_request():124] handle_request: stop_status
63
+ 2021-07-09 11:17:41,727 DEBUG SenderThread:29289 [sender.py:send_request():193] send_request: stop_status
64
+ 2021-07-09 11:17:43,454 INFO Thread-8 :29289 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/output.log
65
+ 2021-07-09 11:17:45,455 INFO Thread-8 :29289 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/output.log
66
+ 2021-07-09 11:17:47,456 INFO Thread-8 :29289 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/output.log
67
+ 2021-07-09 11:17:49,457 INFO Thread-8 :29289 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/output.log
68
+ 2021-07-09 11:17:51,458 INFO Thread-8 :29289 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/output.log
69
+ 2021-07-09 11:17:53,459 INFO Thread-8 :29289 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/output.log
70
+ 2021-07-09 11:17:54,712 DEBUG SenderThread:29289 [sender.py:send():179] send: stats
71
+ 2021-07-09 11:17:55,459 INFO Thread-8 :29289 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/output.log
72
+ 2021-07-09 11:17:56,763 DEBUG HandlerThread:29289 [handler.py:handle_request():124] handle_request: stop_status
73
+ 2021-07-09 11:17:56,763 DEBUG SenderThread:29289 [sender.py:send_request():193] send_request: stop_status
74
+ 2021-07-09 11:17:58,461 INFO Thread-8 :29289 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/output.log
75
+ 2021-07-09 11:17:59,461 INFO Thread-8 :29289 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/output.log
76
+ 2021-07-09 11:18:04,463 INFO Thread-8 :29289 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/output.log
77
+ 2021-07-09 11:18:06,464 INFO Thread-8 :29289 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/output.log
78
+ 2021-07-09 11:18:08,465 INFO Thread-8 :29289 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/output.log
79
+ 2021-07-09 11:18:08,711 DEBUG SenderThread:29289 [sender.py:send():179] send: telemetry
80
+ 2021-07-09 11:18:08,711 DEBUG SenderThread:29289 [sender.py:send():179] send: exit
81
+ 2021-07-09 11:18:08,711 INFO SenderThread:29289 [sender.py:send_exit():287] handling exit code: 0
82
+ 2021-07-09 11:18:08,711 INFO SenderThread:29289 [sender.py:send_exit():295] send defer
83
+ 2021-07-09 11:18:08,712 DEBUG HandlerThread:29289 [handler.py:handle_request():124] handle_request: poll_exit
84
+ 2021-07-09 11:18:08,712 DEBUG HandlerThread:29289 [handler.py:handle_request():124] handle_request: defer
85
+ 2021-07-09 11:18:08,712 INFO HandlerThread:29289 [handler.py:handle_request_defer():141] handle defer: 0
86
+ 2021-07-09 11:18:08,712 DEBUG SenderThread:29289 [sender.py:send_request():193] send_request: poll_exit
87
+ 2021-07-09 11:18:08,712 DEBUG SenderThread:29289 [sender.py:send_request():193] send_request: defer
88
+ 2021-07-09 11:18:08,712 INFO SenderThread:29289 [sender.py:send_request_defer():304] handle sender defer: 0
89
+ 2021-07-09 11:18:08,712 INFO SenderThread:29289 [sender.py:transition_state():308] send defer: 1
90
+ 2021-07-09 11:18:08,712 DEBUG HandlerThread:29289 [handler.py:handle_request():124] handle_request: defer
91
+ 2021-07-09 11:18:08,712 INFO HandlerThread:29289 [handler.py:handle_request_defer():141] handle defer: 1
92
+ 2021-07-09 11:18:08,745 DEBUG SenderThread:29289 [sender.py:send_request():193] send_request: defer
93
+ 2021-07-09 11:18:08,745 INFO SenderThread:29289 [sender.py:send_request_defer():304] handle sender defer: 1
94
+ 2021-07-09 11:18:08,745 INFO SenderThread:29289 [sender.py:transition_state():308] send defer: 2
95
+ 2021-07-09 11:18:08,746 DEBUG SenderThread:29289 [sender.py:send():179] send: stats
96
+ 2021-07-09 11:18:08,746 DEBUG HandlerThread:29289 [handler.py:handle_request():124] handle_request: defer
97
+ 2021-07-09 11:18:08,746 INFO HandlerThread:29289 [handler.py:handle_request_defer():141] handle defer: 2
98
+ 2021-07-09 11:18:08,746 DEBUG SenderThread:29289 [sender.py:send_request():193] send_request: defer
99
+ 2021-07-09 11:18:08,746 INFO SenderThread:29289 [sender.py:send_request_defer():304] handle sender defer: 2
100
+ 2021-07-09 11:18:08,746 INFO SenderThread:29289 [sender.py:transition_state():308] send defer: 3
101
+ 2021-07-09 11:18:08,746 DEBUG HandlerThread:29289 [handler.py:handle_request():124] handle_request: defer
102
+ 2021-07-09 11:18:08,746 INFO HandlerThread:29289 [handler.py:handle_request_defer():141] handle defer: 3
103
+ 2021-07-09 11:18:08,747 DEBUG SenderThread:29289 [sender.py:send():179] send: summary
104
+ 2021-07-09 11:18:08,747 INFO SenderThread:29289 [sender.py:_save_file():841] saving file wandb-summary.json with policy end
105
+ 2021-07-09 11:18:08,747 DEBUG SenderThread:29289 [sender.py:send_request():193] send_request: defer
106
+ 2021-07-09 11:18:08,747 INFO SenderThread:29289 [sender.py:send_request_defer():304] handle sender defer: 3
107
+ 2021-07-09 11:18:08,747 INFO SenderThread:29289 [sender.py:transition_state():308] send defer: 4
108
+ 2021-07-09 11:18:08,747 DEBUG HandlerThread:29289 [handler.py:handle_request():124] handle_request: defer
109
+ 2021-07-09 11:18:08,747 INFO HandlerThread:29289 [handler.py:handle_request_defer():141] handle defer: 4
110
+ 2021-07-09 11:18:08,748 DEBUG SenderThread:29289 [sender.py:send_request():193] send_request: defer
111
+ 2021-07-09 11:18:08,748 INFO SenderThread:29289 [sender.py:send_request_defer():304] handle sender defer: 4
112
+ 2021-07-09 11:18:08,811 INFO SenderThread:29289 [sender.py:transition_state():308] send defer: 5
113
+ 2021-07-09 11:18:08,812 DEBUG HandlerThread:29289 [handler.py:handle_request():124] handle_request: defer
114
+ 2021-07-09 11:18:08,812 INFO HandlerThread:29289 [handler.py:handle_request_defer():141] handle defer: 5
115
+ 2021-07-09 11:18:08,812 DEBUG SenderThread:29289 [sender.py:send_request():193] send_request: defer
116
+ 2021-07-09 11:18:08,812 INFO SenderThread:29289 [sender.py:send_request_defer():304] handle sender defer: 5
117
+ 2021-07-09 11:18:08,812 INFO SenderThread:29289 [dir_watcher.py:finish():282] shutting down directory watcher
118
+ 2021-07-09 11:18:08,814 DEBUG HandlerThread:29289 [handler.py:handle_request():124] handle_request: poll_exit
119
+ 2021-07-09 11:18:09,466 INFO Thread-8 :29289 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/wandb-summary.json
120
+ 2021-07-09 11:18:09,466 INFO SenderThread:29289 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/config.yaml
121
+ 2021-07-09 11:18:09,466 INFO SenderThread:29289 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/output.log
122
+ 2021-07-09 11:18:09,467 INFO SenderThread:29289 [dir_watcher.py:finish():312] scan: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files
123
+ 2021-07-09 11:18:09,467 INFO SenderThread:29289 [dir_watcher.py:finish():318] scan save: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/requirements.txt requirements.txt
124
+ 2021-07-09 11:18:09,467 INFO SenderThread:29289 [dir_watcher.py:finish():318] scan save: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/output.log output.log
125
+ 2021-07-09 11:18:09,467 INFO SenderThread:29289 [dir_watcher.py:finish():318] scan save: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/wandb-metadata.json wandb-metadata.json
126
+ 2021-07-09 11:18:09,467 INFO SenderThread:29289 [dir_watcher.py:finish():318] scan save: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/config.yaml config.yaml
127
+ 2021-07-09 11:18:09,467 INFO SenderThread:29289 [dir_watcher.py:finish():318] scan save: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/wandb-summary.json wandb-summary.json
128
+ 2021-07-09 11:18:09,468 INFO SenderThread:29289 [sender.py:transition_state():308] send defer: 6
129
+ 2021-07-09 11:18:09,468 DEBUG SenderThread:29289 [sender.py:send_request():193] send_request: poll_exit
130
+ 2021-07-09 11:18:09,471 DEBUG HandlerThread:29289 [handler.py:handle_request():124] handle_request: defer
131
+ 2021-07-09 11:18:09,471 INFO HandlerThread:29289 [handler.py:handle_request_defer():141] handle defer: 6
132
+ 2021-07-09 11:18:09,473 DEBUG SenderThread:29289 [sender.py:send_request():193] send_request: defer
133
+ 2021-07-09 11:18:09,473 INFO SenderThread:29289 [sender.py:send_request_defer():304] handle sender defer: 6
134
+ 2021-07-09 11:18:09,474 INFO SenderThread:29289 [file_pusher.py:finish():177] shutting down file pusher
135
+ 2021-07-09 11:18:09,570 DEBUG HandlerThread:29289 [handler.py:handle_request():124] handle_request: poll_exit
136
+ 2021-07-09 11:18:09,570 DEBUG SenderThread:29289 [sender.py:send_request():193] send_request: poll_exit
137
+ 2021-07-09 11:18:09,672 DEBUG HandlerThread:29289 [handler.py:handle_request():124] handle_request: poll_exit
138
+ 2021-07-09 11:18:09,672 DEBUG SenderThread:29289 [sender.py:send_request():193] send_request: poll_exit
139
+ 2021-07-09 11:18:09,676 INFO Thread-12 :29289 [upload_job.py:push():137] Uploaded file /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/requirements.txt
140
+ 2021-07-09 11:18:09,678 INFO Thread-14 :29289 [upload_job.py:push():137] Uploaded file /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/config.yaml
141
+ 2021-07-09 11:18:09,688 INFO Thread-15 :29289 [upload_job.py:push():137] Uploaded file /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/wandb-summary.json
142
+ 2021-07-09 11:18:09,700 INFO Thread-13 :29289 [upload_job.py:push():137] Uploaded file /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/files/output.log
143
+ 2021-07-09 11:18:09,773 DEBUG HandlerThread:29289 [handler.py:handle_request():124] handle_request: poll_exit
144
+ 2021-07-09 11:18:09,773 DEBUG SenderThread:29289 [sender.py:send_request():193] send_request: poll_exit
145
+ 2021-07-09 11:18:09,875 DEBUG HandlerThread:29289 [handler.py:handle_request():124] handle_request: poll_exit
146
+ 2021-07-09 11:18:09,875 DEBUG SenderThread:29289 [sender.py:send_request():193] send_request: poll_exit
147
+ 2021-07-09 11:18:09,900 INFO Thread-7 :29289 [sender.py:transition_state():308] send defer: 7
148
+ 2021-07-09 11:18:09,901 DEBUG HandlerThread:29289 [handler.py:handle_request():124] handle_request: defer
149
+ 2021-07-09 11:18:09,901 INFO HandlerThread:29289 [handler.py:handle_request_defer():141] handle defer: 7
150
+ 2021-07-09 11:18:09,901 DEBUG SenderThread:29289 [sender.py:send_request():193] send_request: defer
151
+ 2021-07-09 11:18:09,901 INFO SenderThread:29289 [sender.py:send_request_defer():304] handle sender defer: 7
152
+ 2021-07-09 11:18:09,972 INFO SenderThread:29289 [sender.py:transition_state():308] send defer: 8
153
+ 2021-07-09 11:18:09,973 DEBUG HandlerThread:29289 [handler.py:handle_request():124] handle_request: defer
154
+ 2021-07-09 11:18:09,973 INFO HandlerThread:29289 [handler.py:handle_request_defer():141] handle defer: 8
155
+ 2021-07-09 11:18:09,973 DEBUG SenderThread:29289 [sender.py:send_request():193] send_request: defer
156
+ 2021-07-09 11:18:09,973 INFO SenderThread:29289 [sender.py:send_request_defer():304] handle sender defer: 8
157
+ 2021-07-09 11:18:09,973 INFO SenderThread:29289 [sender.py:transition_state():308] send defer: 9
158
+ 2021-07-09 11:18:09,974 DEBUG HandlerThread:29289 [handler.py:handle_request():124] handle_request: defer
159
+ 2021-07-09 11:18:09,974 INFO HandlerThread:29289 [handler.py:handle_request_defer():141] handle defer: 9
160
+ 2021-07-09 11:18:09,974 DEBUG SenderThread:29289 [sender.py:send():179] send: final
161
+ 2021-07-09 11:18:09,974 DEBUG SenderThread:29289 [sender.py:send():179] send: footer
162
+ 2021-07-09 11:18:09,974 DEBUG SenderThread:29289 [sender.py:send_request():193] send_request: defer
163
+ 2021-07-09 11:18:09,974 INFO SenderThread:29289 [sender.py:send_request_defer():304] handle sender defer: 9
164
+ 2021-07-09 11:18:09,977 DEBUG HandlerThread:29289 [handler.py:handle_request():124] handle_request: poll_exit
165
+ 2021-07-09 11:18:09,977 DEBUG SenderThread:29289 [sender.py:send_request():193] send_request: poll_exit
166
+ 2021-07-09 11:18:09,977 INFO SenderThread:29289 [file_pusher.py:join():182] waiting for file pusher
167
+ 2021-07-09 11:18:09,978 DEBUG HandlerThread:29289 [handler.py:handle_request():124] handle_request: get_summary
168
+ 2021-07-09 11:18:09,978 DEBUG HandlerThread:29289 [handler.py:handle_request():124] handle_request: sampled_history
169
+ 2021-07-09 11:18:09,979 DEBUG HandlerThread:29289 [handler.py:handle_request():124] handle_request: shutdown
170
+ 2021-07-09 11:18:09,979 INFO HandlerThread:29289 [handler.py:finish():638] shutting down handler
171
+ 2021-07-09 11:18:10,974 INFO WriterThread:29289 [datastore.py:close():288] close: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/run-275xd40l.wandb
172
+ 2021-07-09 11:18:10,977 INFO SenderThread:29289 [sender.py:finish():945] shutting down sender
173
+ 2021-07-09 11:18:10,977 INFO SenderThread:29289 [file_pusher.py:finish():177] shutting down file pusher
174
+ 2021-07-09 11:18:10,977 INFO SenderThread:29289 [file_pusher.py:join():182] waiting for file pusher
175
+ 2021-07-09 11:18:10,980 INFO MainThread:29289 [internal.py:handle_exit():78] Internal process exited
wandb/run-20210709_111555-275xd40l/logs/debug.log ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2021-07-09 11:15:55,659 INFO MainThread:28231 [wandb_setup.py:_flush():69] Unhandled environment var: WANDB_WATCH
2
+ 2021-07-09 11:15:55,660 INFO MainThread:28231 [wandb_setup.py:_flush():69] setting env: {'project': 'hf-flax-robert-base-mr', 'entity': 'nipunsadvilkar'}
3
+ 2021-07-09 11:15:55,660 INFO MainThread:28231 [wandb_setup.py:_flush():69] setting login settings: {}
4
+ 2021-07-09 11:15:55,660 INFO MainThread:28231 [wandb_init.py:_log_setup():337] Logging user logs to /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/logs/debug.log
5
+ 2021-07-09 11:15:55,660 INFO MainThread:28231 [wandb_init.py:_log_setup():338] Logging internal logs to /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_111555-275xd40l/logs/debug-internal.log
6
+ 2021-07-09 11:15:55,660 INFO MainThread:28231 [wandb_init.py:init():370] calling init triggers
7
+ 2021-07-09 11:15:55,660 INFO MainThread:28231 [wandb_init.py:init():375] wandb.init called with sweep_config: {}
8
+ config: {}
9
+ 2021-07-09 11:15:55,660 INFO MainThread:28231 [wandb_init.py:init():419] starting backend
10
+ 2021-07-09 11:15:55,660 INFO MainThread:28231 [backend.py:_multiprocessing_setup():70] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
11
+ 2021-07-09 11:15:55,687 INFO MainThread:28231 [backend.py:ensure_launched():135] starting backend process...
12
+ 2021-07-09 11:15:55,713 INFO MainThread:28231 [backend.py:ensure_launched():139] started backend process with pid: 29289
13
+ 2021-07-09 11:15:55,714 INFO MainThread:28231 [wandb_init.py:init():424] backend started and connected
14
+ 2021-07-09 11:15:55,716 INFO MainThread:28231 [wandb_init.py:init():472] updated telemetry
15
+ 2021-07-09 11:15:55,717 INFO MainThread:28231 [wandb_init.py:init():491] communicating current version
16
+ 2021-07-09 11:15:56,309 INFO MainThread:28231 [wandb_init.py:init():496] got version response
17
+ 2021-07-09 11:15:56,310 INFO MainThread:28231 [wandb_init.py:init():504] communicating run to backend with 30 second timeout
18
+ 2021-07-09 11:15:56,406 INFO MainThread:28231 [wandb_init.py:init():529] starting run threads in backend
19
+ 2021-07-09 11:15:56,456 INFO MainThread:28231 [wandb_run.py:_console_start():1623] atexit reg
20
+ 2021-07-09 11:15:56,457 INFO MainThread:28231 [wandb_run.py:_redirect():1497] redirect: SettingsConsole.REDIRECT
21
+ 2021-07-09 11:15:56,457 INFO MainThread:28231 [wandb_run.py:_redirect():1502] Redirecting console.
22
+ 2021-07-09 11:15:56,459 INFO MainThread:28231 [wandb_run.py:_redirect():1558] Redirects installed.
23
+ 2021-07-09 11:15:56,459 INFO MainThread:28231 [wandb_init.py:init():554] run started, returning control to user process
24
+ 2021-07-09 11:15:56,460 INFO MainThread:28231 [wandb_run.py:_config_callback():872] config_cb None None {'output_dir': './', 'overwrite_output_dir': True, 'do_train': False, 'do_eval': False, 'do_predict': False, 'evaluation_strategy': 'IntervalStrategy.NO', 'prediction_loss_only': False, 'per_device_train_batch_size': 4, 'per_device_eval_batch_size': 4, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'learning_rate': 0.0003, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 8.0, 'max_steps': -1, 'lr_scheduler_type': 'SchedulerType.LINEAR', 'warmup_ratio': 0.0, 'warmup_steps': 1000, 'log_level': -1, 'log_level_replica': -1, 'log_on_each_node': True, 'logging_dir': './runs/Jul09_11-15-50_t1v-n-112df4a9-w-0', 'logging_strategy': 'IntervalStrategy.STEPS', 'logging_first_step': False, 'logging_steps': 500, 'save_strategy': 'IntervalStrategy.STEPS', 'save_steps': 500, 'save_total_limit': None, 'save_on_each_node': False, 'no_cuda': False, 'seed': 42, 'fp16': False, 'fp16_opt_level': 'O1', 'fp16_backend': 'auto', 'fp16_full_eval': False, 'local_rank': -1, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': 500, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': './', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'sharded_ddp': [], 'deepspeed': None, 'label_smoothing_factor': 0.0, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'dataloader_pin_memory': True, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': False, 'resume_from_checkpoint': None, 'push_to_hub_model_id': '', 'push_to_hub_organization': None, 'push_to_hub_token': None, 'mp_parameters': ''}
25
+ 2021-07-09 11:15:56,460 INFO MainThread:28231 [wandb_run.py:_config_callback():872] config_cb None None {'model_name_or_path': None, 'model_type': 'roberta', 'config_name': './', 'tokenizer_name': './', 'cache_dir': None, 'use_fast_tokenizer': True, 'dtype': 'float32'}
26
+ 2021-07-09 11:15:56,461 INFO MainThread:28231 [wandb_run.py:_config_callback():872] config_cb None None {'dataset_name': 'oscar', 'dataset_config_name': 'unshuffled_deduplicated_als', 'train_file': None, 'validation_file': None, 'train_ref_file': None, 'validation_ref_file': None, 'overwrite_cache': False, 'validation_split_percentage': 5, 'max_seq_length': 128, 'preprocessing_num_workers': None, 'mlm_probability': 0.15, 'pad_to_max_length': False, 'line_by_line': False}
27
+ 2021-07-09 11:18:06,643 INFO MainThread:28231 [wandb_run.py:_atexit_cleanup():1593] got exitcode: 0
28
+ 2021-07-09 11:18:06,644 INFO MainThread:28231 [wandb_run.py:_restore():1565] restore
29
+ 2021-07-09 11:18:08,713 INFO MainThread:28231 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
30
+ wandb_count: 1
31
+ }
32
+ pusher_stats {
33
+ uploaded_bytes: 1200
34
+ total_bytes: 1200
35
+ }
36
+
37
+ 2021-07-09 11:18:09,469 INFO MainThread:28231 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
38
+ wandb_count: 4
39
+ }
40
+ pusher_stats {
41
+ uploaded_bytes: 1200
42
+ total_bytes: 12360
43
+ }
44
+
45
+ 2021-07-09 11:18:09,571 INFO MainThread:28231 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
46
+ wandb_count: 5
47
+ }
48
+ pusher_stats {
49
+ uploaded_bytes: 12362
50
+ total_bytes: 12362
51
+ }
52
+
53
+ 2021-07-09 11:18:09,673 INFO MainThread:28231 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
54
+ wandb_count: 5
55
+ }
56
+ pusher_stats {
57
+ uploaded_bytes: 12362
58
+ total_bytes: 12362
59
+ }
60
+
61
+ 2021-07-09 11:18:09,774 INFO MainThread:28231 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
62
+ wandb_count: 5
63
+ }
64
+ pusher_stats {
65
+ uploaded_bytes: 12362
66
+ total_bytes: 12362
67
+ }
68
+
69
+ 2021-07-09 11:18:09,876 INFO MainThread:28231 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
70
+ wandb_count: 5
71
+ }
72
+ pusher_stats {
73
+ uploaded_bytes: 12362
74
+ total_bytes: 12362
75
+ }
76
+
77
+ 2021-07-09 11:18:09,977 INFO MainThread:28231 [wandb_run.py:_wait_for_finish():1715] got exit ret: done: true
78
+ exit_result {
79
+ }
80
+ file_counts {
81
+ wandb_count: 5
82
+ }
83
+ pusher_stats {
84
+ uploaded_bytes: 12362
85
+ total_bytes: 12362
86
+ }
87
+
88
+ 2021-07-09 11:18:11,050 INFO MainThread:28231 [wandb_run.py:_show_files():1937] logging synced files
wandb/run-20210709_111555-275xd40l/run-275xd40l.wandb ADDED
Binary file (16.2 kB). View file
 
wandb/run-20210709_115016-mgpt342u/files/config.yaml ADDED
@@ -0,0 +1,305 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ wandb_version: 1
2
+
3
+ _wandb:
4
+ desc: null
5
+ value:
6
+ cli_version: 0.10.33
7
+ framework: huggingface
8
+ huggingface_version: 4.9.0.dev0
9
+ is_jupyter_run: false
10
+ is_kaggle_kernel: false
11
+ python_version: 3.8.10
12
+ t:
13
+ 1:
14
+ - 11
15
+ 2:
16
+ - 11
17
+ 4: 3.8.10
18
+ 5: 0.10.33
19
+ 6: 4.9.0.dev0
20
+ 8:
21
+ - 5
22
+ adafactor:
23
+ desc: null
24
+ value: false
25
+ adam_beta1:
26
+ desc: null
27
+ value: 0.9
28
+ adam_beta2:
29
+ desc: null
30
+ value: 0.999
31
+ adam_epsilon:
32
+ desc: null
33
+ value: 1.0e-08
34
+ cache_dir:
35
+ desc: null
36
+ value: null
37
+ config_name:
38
+ desc: null
39
+ value: ./
40
+ dataloader_drop_last:
41
+ desc: null
42
+ value: false
43
+ dataloader_num_workers:
44
+ desc: null
45
+ value: 0
46
+ dataloader_pin_memory:
47
+ desc: null
48
+ value: true
49
+ dataset_config_name:
50
+ desc: null
51
+ value: unshuffled_deduplicated_als
52
+ dataset_name:
53
+ desc: null
54
+ value: oscar
55
+ ddp_find_unused_parameters:
56
+ desc: null
57
+ value: null
58
+ debug:
59
+ desc: null
60
+ value: []
61
+ deepspeed:
62
+ desc: null
63
+ value: null
64
+ disable_tqdm:
65
+ desc: null
66
+ value: false
67
+ do_eval:
68
+ desc: null
69
+ value: false
70
+ do_predict:
71
+ desc: null
72
+ value: false
73
+ do_train:
74
+ desc: null
75
+ value: false
76
+ dtype:
77
+ desc: null
78
+ value: float32
79
+ eval_accumulation_steps:
80
+ desc: null
81
+ value: null
82
+ eval_steps:
83
+ desc: null
84
+ value: 500
85
+ evaluation_strategy:
86
+ desc: null
87
+ value: IntervalStrategy.NO
88
+ fp16:
89
+ desc: null
90
+ value: false
91
+ fp16_backend:
92
+ desc: null
93
+ value: auto
94
+ fp16_full_eval:
95
+ desc: null
96
+ value: false
97
+ fp16_opt_level:
98
+ desc: null
99
+ value: O1
100
+ gradient_accumulation_steps:
101
+ desc: null
102
+ value: 1
103
+ greater_is_better:
104
+ desc: null
105
+ value: null
106
+ group_by_length:
107
+ desc: null
108
+ value: false
109
+ ignore_data_skip:
110
+ desc: null
111
+ value: false
112
+ label_names:
113
+ desc: null
114
+ value: null
115
+ label_smoothing_factor:
116
+ desc: null
117
+ value: 0.0
118
+ learning_rate:
119
+ desc: null
120
+ value: 0.0003
121
+ length_column_name:
122
+ desc: null
123
+ value: length
124
+ line_by_line:
125
+ desc: null
126
+ value: false
127
+ load_best_model_at_end:
128
+ desc: null
129
+ value: false
130
+ local_rank:
131
+ desc: null
132
+ value: -1
133
+ log_level:
134
+ desc: null
135
+ value: -1
136
+ log_level_replica:
137
+ desc: null
138
+ value: -1
139
+ log_on_each_node:
140
+ desc: null
141
+ value: true
142
+ logging_dir:
143
+ desc: null
144
+ value: ./runs/Jul09_11-50-10_t1v-n-112df4a9-w-0
145
+ logging_first_step:
146
+ desc: null
147
+ value: false
148
+ logging_steps:
149
+ desc: null
150
+ value: 500
151
+ logging_strategy:
152
+ desc: null
153
+ value: IntervalStrategy.STEPS
154
+ lr_scheduler_type:
155
+ desc: null
156
+ value: SchedulerType.LINEAR
157
+ max_grad_norm:
158
+ desc: null
159
+ value: 1.0
160
+ max_seq_length:
161
+ desc: null
162
+ value: 128
163
+ max_steps:
164
+ desc: null
165
+ value: -1
166
+ metric_for_best_model:
167
+ desc: null
168
+ value: null
169
+ mlm_probability:
170
+ desc: null
171
+ value: 0.15
172
+ model_name_or_path:
173
+ desc: null
174
+ value: null
175
+ model_type:
176
+ desc: null
177
+ value: roberta
178
+ mp_parameters:
179
+ desc: null
180
+ value: ''
181
+ no_cuda:
182
+ desc: null
183
+ value: false
184
+ num_train_epochs:
185
+ desc: null
186
+ value: 8.0
187
+ output_dir:
188
+ desc: null
189
+ value: ./
190
+ overwrite_cache:
191
+ desc: null
192
+ value: false
193
+ overwrite_output_dir:
194
+ desc: null
195
+ value: true
196
+ pad_to_max_length:
197
+ desc: null
198
+ value: false
199
+ past_index:
200
+ desc: null
201
+ value: -1
202
+ per_device_eval_batch_size:
203
+ desc: null
204
+ value: 4
205
+ per_device_train_batch_size:
206
+ desc: null
207
+ value: 4
208
+ per_gpu_eval_batch_size:
209
+ desc: null
210
+ value: null
211
+ per_gpu_train_batch_size:
212
+ desc: null
213
+ value: null
214
+ prediction_loss_only:
215
+ desc: null
216
+ value: false
217
+ preprocessing_num_workers:
218
+ desc: null
219
+ value: null
220
+ push_to_hub:
221
+ desc: null
222
+ value: false
223
+ push_to_hub_model_id:
224
+ desc: null
225
+ value: ''
226
+ push_to_hub_organization:
227
+ desc: null
228
+ value: null
229
+ push_to_hub_token:
230
+ desc: null
231
+ value: null
232
+ remove_unused_columns:
233
+ desc: null
234
+ value: true
235
+ report_to:
236
+ desc: null
237
+ value:
238
+ - tensorboard
239
+ - wandb
240
+ resume_from_checkpoint:
241
+ desc: null
242
+ value: null
243
+ run_name:
244
+ desc: null
245
+ value: ./
246
+ save_on_each_node:
247
+ desc: null
248
+ value: false
249
+ save_steps:
250
+ desc: null
251
+ value: 500
252
+ save_strategy:
253
+ desc: null
254
+ value: IntervalStrategy.STEPS
255
+ save_total_limit:
256
+ desc: null
257
+ value: null
258
+ seed:
259
+ desc: null
260
+ value: 42
261
+ sharded_ddp:
262
+ desc: null
263
+ value: []
264
+ skip_memory_metrics:
265
+ desc: null
266
+ value: true
267
+ tokenizer_name:
268
+ desc: null
269
+ value: ./
270
+ tpu_metrics_debug:
271
+ desc: null
272
+ value: false
273
+ tpu_num_cores:
274
+ desc: null
275
+ value: null
276
+ train_file:
277
+ desc: null
278
+ value: null
279
+ train_ref_file:
280
+ desc: null
281
+ value: null
282
+ use_fast_tokenizer:
283
+ desc: null
284
+ value: true
285
+ use_legacy_prediction_loop:
286
+ desc: null
287
+ value: false
288
+ validation_file:
289
+ desc: null
290
+ value: null
291
+ validation_ref_file:
292
+ desc: null
293
+ value: null
294
+ validation_split_percentage:
295
+ desc: null
296
+ value: 5
297
+ warmup_ratio:
298
+ desc: null
299
+ value: 0.0
300
+ warmup_steps:
301
+ desc: null
302
+ value: 1000
303
+ weight_decay:
304
+ desc: null
305
+ value: 0.0
wandb/run-20210709_115016-mgpt342u/files/output.log ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ [11:50:17] - WARNING - __main__ - Unable to display metrics through TensorBoard because some package are not installed: No module named 'tensorflow'
3
+ /home/nipunsadvilkar/roberta_mr_env/lib/python3.8/site-packages/jax/lib/xla_bridge.py:382: UserWarning: jax.host_count has been renamed to jax.process_count. This alias will eventually be removed; please update your code.
4
+ warnings.warn(
5
+ /home/nipunsadvilkar/roberta_mr_env/lib/python3.8/site-packages/jax/lib/xla_bridge.py:369: UserWarning: jax.host_id has been renamed to jax.process_index. This alias will eventually be removed; please update your code.
6
+ warnings.warn(
7
+ Epoch ... (1/8): 0%| | 0/8 [00:00<?, ?it/s]
8
+
9
+
10
+ Epoch ... (1/8): 12%|███████████████████ | 1/8 [01:17<09:01, 77.32s/it]
11
+
12
+
13
+ Epoch ... (1/8): 25%|██████████████████████████████████████ | 2/8 [01:22<03:28, 34.83s/it]
14
+
15
+ Epoch ... (1/8): 38%|█████████████████████████████████████████████████████████ | 3/8 [01:27<01:46, 21.26s/it]
16
+ Training...: 8%|████████████▉ | 12/142 [00:00<00:03, 37.10it/s]
17
+
18
+ Training...: 51%|█████████████████████████████████████████████████████████████████████████████▌ | 72/142 [00:02<00:02, 34.45it/s]
19
+
20
+
21
+ Step... (500 | Loss: 8.205772399902344, Acc: 0.0773010179400444): 50%|███████████████████████████████████████████████████▌ | 4/8 [01:43<01:17, 19.34s/it]
22
+
23
+
24
+ Step... (500 | Loss: 8.205772399902344, Acc: 0.0773010179400444): 62%|████████████████████████████████████████████████████████████████▍ | 5/8 [01:48<00:42, 14.01s/it]
25
+
26
+ Step... (500 | Loss: 8.205772399902344, Acc: 0.0773010179400444): 75%|█████████████████████████████████████████████████████████████████████████████▎ | 6/8 [01:53<00:21, 10.96s/it]
27
+
28
+
29
+ Step... (500 | Loss: 8.205772399902344, Acc: 0.0773010179400444): 88%|██████████████████████████████████████████████████████████████████████████████████████████▏ | 7/8 [01:58<00:09, 9.03s/it]
30
+ Evaluating ...: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 10/10 [00:00<00:00, 77.42it/s]
31
+ Training...: 3%|████▎ | 4/142 [00:00<00:03, 35.26it/s]
32
+
33
+
34
+ Step... (1000 | Loss: 7.925442218780518, Acc: 0.09575153142213821): 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████| 8/8 [02:09<00:00, 16.16s/it]
wandb/run-20210709_115016-mgpt342u/files/requirements.txt ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ absl-py==0.13.0
2
+ aiohttp==3.7.4.post0
3
+ async-timeout==3.0.1
4
+ attrs==21.2.0
5
+ backcall==0.2.0
6
+ cachetools==4.2.2
7
+ certifi==2021.5.30
8
+ chardet==4.0.0
9
+ chex==0.0.8
10
+ click==8.0.1
11
+ configparser==5.0.2
12
+ cycler==0.10.0
13
+ datasets==1.9.1.dev0
14
+ decorator==5.0.9
15
+ dill==0.3.4
16
+ dm-tree==0.1.6
17
+ docker-pycreds==0.4.0
18
+ filelock==3.0.12
19
+ flatbuffers==2.0
20
+ flax==0.3.4
21
+ fsspec==2021.6.1
22
+ gitdb==4.0.7
23
+ gitpython==3.1.18
24
+ google-auth-oauthlib==0.4.4
25
+ google-auth==1.32.1
26
+ grpcio==1.38.1
27
+ huggingface-hub==0.0.12
28
+ idna==2.10
29
+ ipython-genutils==0.2.0
30
+ ipython==7.25.0
31
+ jax==0.2.16
32
+ jaxlib==0.1.68
33
+ jedi==0.18.0
34
+ joblib==1.0.1
35
+ kiwisolver==1.3.1
36
+ libtpu-nightly==0.1.dev20210615
37
+ markdown==3.3.4
38
+ matplotlib-inline==0.1.2
39
+ matplotlib==3.4.2
40
+ msgpack==1.0.2
41
+ multidict==5.1.0
42
+ multiprocess==0.70.12.2
43
+ numpy==1.21.0
44
+ oauthlib==3.1.1
45
+ opt-einsum==3.3.0
46
+ optax==0.0.9
47
+ packaging==21.0
48
+ pandas==1.3.0
49
+ parso==0.8.2
50
+ pathtools==0.1.2
51
+ pexpect==4.8.0
52
+ pickleshare==0.7.5
53
+ pillow==8.3.1
54
+ pip==20.0.2
55
+ pkg-resources==0.0.0
56
+ promise==2.3
57
+ prompt-toolkit==3.0.19
58
+ protobuf==3.17.3
59
+ psutil==5.8.0
60
+ ptyprocess==0.7.0
61
+ pyarrow==4.0.1
62
+ pyasn1-modules==0.2.8
63
+ pyasn1==0.4.8
64
+ pygments==2.9.0
65
+ pyparsing==2.4.7
66
+ python-dateutil==2.8.1
67
+ pytz==2021.1
68
+ pyyaml==5.4.1
69
+ regex==2021.7.6
70
+ requests-oauthlib==1.3.0
71
+ requests==2.25.1
72
+ rsa==4.7.2
73
+ sacremoses==0.0.45
74
+ scipy==1.7.0
75
+ sentry-sdk==1.3.0
76
+ setuptools==44.0.0
77
+ shortuuid==1.0.1
78
+ six==1.16.0
79
+ smmap==4.0.0
80
+ subprocess32==3.5.4
81
+ tensorboard-data-server==0.6.1
82
+ tensorboard-plugin-wit==1.8.0
83
+ tensorboard==2.5.0
84
+ tokenizers==0.10.3
85
+ toolz==0.11.1
86
+ tqdm==4.61.2
87
+ traitlets==5.0.5
88
+ transformers==4.9.0.dev0
89
+ typing-extensions==3.10.0.0
90
+ urllib3==1.26.6
91
+ wandb==0.10.33
92
+ wcwidth==0.2.5
93
+ werkzeug==2.0.1
94
+ wheel==0.36.2
95
+ xxhash==2.0.2
96
+ yarl==1.6.3
wandb/run-20210709_115016-mgpt342u/files/wandb-metadata.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "os": "Linux-5.4.0-1043-gcp-x86_64-with-glibc2.29",
3
+ "python": "3.8.10",
4
+ "heartbeatAt": "2021-07-09T11:50:17.221650",
5
+ "startedAt": "2021-07-09T11:50:16.489745",
6
+ "docker": null,
7
+ "cpu_count": 96,
8
+ "cuda": null,
9
+ "args": [
10
+ "--output_dir=./",
11
+ "--model_type=roberta",
12
+ "--config_name=./",
13
+ "--tokenizer_name=./",
14
+ "--dataset_name=oscar",
15
+ "--dataset_config_name=unshuffled_deduplicated_als",
16
+ "--max_seq_length=128",
17
+ "--per_device_train_batch_size=4",
18
+ "--per_device_eval_batch_size=4",
19
+ "--learning_rate=3e-4",
20
+ "--warmup_steps=1000",
21
+ "--overwrite_output_dir",
22
+ "--num_train_epochs=8"
23
+ ],
24
+ "state": "running",
25
+ "program": "run_mlm_flax.py",
26
+ "codePath": "run_mlm_flax.py",
27
+ "git": {
28
+ "remote": "https://huggingface.co/flax-community/roberta-base-mr",
29
+ "commit": "faa64e8a79301832a56c78b2b293675039070bb0"
30
+ },
31
+ "email": "nipunsadvilkar@gmail.com",
32
+ "root": "/home/nipunsadvilkar/sample/roberta-base-mr",
33
+ "host": "t1v-n-112df4a9-w-0",
34
+ "username": "nipunsadvilkar",
35
+ "executable": "/home/nipunsadvilkar/roberta_mr_env/bin/python"
36
+ }
wandb/run-20210709_115016-mgpt342u/files/wandb-summary.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {}
wandb/run-20210709_115016-mgpt342u/logs/debug-internal.log ADDED
@@ -0,0 +1,177 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2021-07-09 11:50:17,074 INFO MainThread:30716 [internal.py:wandb_internal():88] W&B internal server running at pid: 30716, started at: 2021-07-09 11:50:17.074054
2
+ 2021-07-09 11:50:17,076 DEBUG HandlerThread:30716 [handler.py:handle_request():124] handle_request: check_version
3
+ 2021-07-09 11:50:17,076 INFO WriterThread:30716 [datastore.py:open_for_write():80] open: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/run-mgpt342u.wandb
4
+ 2021-07-09 11:50:17,077 DEBUG SenderThread:30716 [sender.py:send():179] send: header
5
+ 2021-07-09 11:50:17,077 DEBUG SenderThread:30716 [sender.py:send_request():193] send_request: check_version
6
+ 2021-07-09 11:50:17,138 DEBUG SenderThread:30716 [sender.py:send():179] send: run
7
+ 2021-07-09 11:50:17,219 INFO SenderThread:30716 [dir_watcher.py:__init__():168] watching files in: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files
8
+ 2021-07-09 11:50:17,219 INFO SenderThread:30716 [sender.py:_start_run_threads():716] run started: mgpt342u with start time 1625831416
9
+ 2021-07-09 11:50:17,219 DEBUG SenderThread:30716 [sender.py:send():179] send: summary
10
+ 2021-07-09 11:50:17,219 DEBUG HandlerThread:30716 [handler.py:handle_request():124] handle_request: run_start
11
+ 2021-07-09 11:50:17,221 INFO SenderThread:30716 [sender.py:_save_file():841] saving file wandb-summary.json with policy end
12
+ 2021-07-09 11:50:17,221 DEBUG HandlerThread:30716 [meta.py:__init__():39] meta init
13
+ 2021-07-09 11:50:17,221 DEBUG HandlerThread:30716 [meta.py:__init__():53] meta init done
14
+ 2021-07-09 11:50:17,221 DEBUG HandlerThread:30716 [meta.py:probe():210] probe
15
+ 2021-07-09 11:50:17,222 DEBUG HandlerThread:30716 [meta.py:_setup_git():200] setup git
16
+ 2021-07-09 11:50:17,238 DEBUG HandlerThread:30716 [meta.py:_setup_git():207] setup git done
17
+ 2021-07-09 11:50:17,238 DEBUG HandlerThread:30716 [meta.py:_save_pip():57] save pip
18
+ 2021-07-09 11:50:17,239 DEBUG HandlerThread:30716 [meta.py:_save_pip():71] save pip done
19
+ 2021-07-09 11:50:17,239 DEBUG HandlerThread:30716 [meta.py:probe():252] probe done
20
+ 2021-07-09 11:50:17,267 DEBUG SenderThread:30716 [sender.py:send():179] send: files
21
+ 2021-07-09 11:50:17,267 INFO SenderThread:30716 [sender.py:_save_file():841] saving file wandb-metadata.json with policy now
22
+ 2021-07-09 11:50:17,271 DEBUG HandlerThread:30716 [handler.py:handle_request():124] handle_request: stop_status
23
+ 2021-07-09 11:50:17,271 DEBUG SenderThread:30716 [sender.py:send_request():193] send_request: stop_status
24
+ 2021-07-09 11:50:17,297 DEBUG SenderThread:30716 [sender.py:send():179] send: config
25
+ 2021-07-09 11:50:17,297 DEBUG SenderThread:30716 [sender.py:send():179] send: config
26
+ 2021-07-09 11:50:17,297 DEBUG SenderThread:30716 [sender.py:send():179] send: config
27
+ 2021-07-09 11:50:17,553 INFO Thread-11 :30716 [upload_job.py:push():137] Uploaded file /tmp/tmpt1i58m5_wandb/1ivr8ckt-wandb-metadata.json
28
+ 2021-07-09 11:50:18,220 INFO Thread-8 :30716 [dir_watcher.py:_on_file_created():216] file/dir created: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/output.log
29
+ 2021-07-09 11:50:18,221 INFO Thread-8 :30716 [dir_watcher.py:_on_file_created():216] file/dir created: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/wandb-metadata.json
30
+ 2021-07-09 11:50:18,221 INFO Thread-8 :30716 [dir_watcher.py:_on_file_created():216] file/dir created: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/requirements.txt
31
+ 2021-07-09 11:50:18,221 INFO Thread-8 :30716 [dir_watcher.py:_on_file_created():216] file/dir created: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/wandb-summary.json
32
+ 2021-07-09 11:50:20,221 INFO Thread-8 :30716 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/output.log
33
+ 2021-07-09 11:50:24,223 INFO Thread-8 :30716 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/output.log
34
+ 2021-07-09 11:50:26,224 INFO Thread-8 :30716 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/output.log
35
+ 2021-07-09 11:50:32,314 DEBUG HandlerThread:30716 [handler.py:handle_request():124] handle_request: stop_status
36
+ 2021-07-09 11:50:32,315 DEBUG SenderThread:30716 [sender.py:send_request():193] send_request: stop_status
37
+ 2021-07-09 11:50:45,291 DEBUG SenderThread:30716 [sender.py:send():179] send: stats
38
+ 2021-07-09 11:50:47,357 DEBUG HandlerThread:30716 [handler.py:handle_request():124] handle_request: stop_status
39
+ 2021-07-09 11:50:47,358 DEBUG SenderThread:30716 [sender.py:send_request():193] send_request: stop_status
40
+ 2021-07-09 11:50:48,234 INFO Thread-8 :30716 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/config.yaml
41
+ 2021-07-09 11:51:02,431 DEBUG HandlerThread:30716 [handler.py:handle_request():124] handle_request: stop_status
42
+ 2021-07-09 11:51:02,431 DEBUG SenderThread:30716 [sender.py:send_request():193] send_request: stop_status
43
+ 2021-07-09 11:51:15,372 DEBUG SenderThread:30716 [sender.py:send():179] send: stats
44
+ 2021-07-09 11:51:17,464 DEBUG HandlerThread:30716 [handler.py:handle_request():124] handle_request: stop_status
45
+ 2021-07-09 11:51:17,464 DEBUG SenderThread:30716 [sender.py:send_request():193] send_request: stop_status
46
+ 2021-07-09 11:51:32,530 DEBUG HandlerThread:30716 [handler.py:handle_request():124] handle_request: stop_status
47
+ 2021-07-09 11:51:32,530 DEBUG SenderThread:30716 [sender.py:send_request():193] send_request: stop_status
48
+ 2021-07-09 11:51:38,258 INFO Thread-8 :30716 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/output.log
49
+ 2021-07-09 11:51:40,259 INFO Thread-8 :30716 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/output.log
50
+ 2021-07-09 11:51:42,260 INFO Thread-8 :30716 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/output.log
51
+ 2021-07-09 11:51:44,261 INFO Thread-8 :30716 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/output.log
52
+ 2021-07-09 11:51:45,445 DEBUG SenderThread:30716 [sender.py:send():179] send: stats
53
+ 2021-07-09 11:51:46,262 INFO Thread-8 :30716 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/output.log
54
+ 2021-07-09 11:51:47,561 DEBUG HandlerThread:30716 [handler.py:handle_request():124] handle_request: stop_status
55
+ 2021-07-09 11:51:47,561 DEBUG SenderThread:30716 [sender.py:send_request():193] send_request: stop_status
56
+ 2021-07-09 11:51:48,263 INFO Thread-8 :30716 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/output.log
57
+ 2021-07-09 11:51:50,264 INFO Thread-8 :30716 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/output.log
58
+ 2021-07-09 11:51:52,264 INFO Thread-8 :30716 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/output.log
59
+ 2021-07-09 11:51:54,266 INFO Thread-8 :30716 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/output.log
60
+ 2021-07-09 11:51:56,267 INFO Thread-8 :30716 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/output.log
61
+ 2021-07-09 11:52:00,269 INFO Thread-8 :30716 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/output.log
62
+ 2021-07-09 11:52:02,619 DEBUG HandlerThread:30716 [handler.py:handle_request():124] handle_request: stop_status
63
+ 2021-07-09 11:52:02,620 DEBUG SenderThread:30716 [sender.py:send_request():193] send_request: stop_status
64
+ 2021-07-09 11:52:06,272 INFO Thread-8 :30716 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/output.log
65
+ 2021-07-09 11:52:08,273 INFO Thread-8 :30716 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/output.log
66
+ 2021-07-09 11:52:10,274 INFO Thread-8 :30716 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/output.log
67
+ 2021-07-09 11:52:12,275 INFO Thread-8 :30716 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/output.log
68
+ 2021-07-09 11:52:14,276 INFO Thread-8 :30716 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/output.log
69
+ 2021-07-09 11:52:15,519 DEBUG SenderThread:30716 [sender.py:send():179] send: stats
70
+ 2021-07-09 11:52:16,277 INFO Thread-8 :30716 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/output.log
71
+ 2021-07-09 11:52:17,653 DEBUG HandlerThread:30716 [handler.py:handle_request():124] handle_request: stop_status
72
+ 2021-07-09 11:52:17,653 DEBUG SenderThread:30716 [sender.py:send_request():193] send_request: stop_status
73
+ 2021-07-09 11:52:18,278 INFO Thread-8 :30716 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/output.log
74
+ 2021-07-09 11:52:20,279 INFO Thread-8 :30716 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/output.log
75
+ 2021-07-09 11:52:22,280 INFO Thread-8 :30716 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/output.log
76
+ 2021-07-09 11:52:24,281 INFO Thread-8 :30716 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/output.log
77
+ 2021-07-09 11:52:30,284 INFO Thread-8 :30716 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/output.log
78
+ 2021-07-09 11:52:32,285 INFO Thread-8 :30716 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/output.log
79
+ 2021-07-09 11:52:33,545 DEBUG HandlerThread:30716 [handler.py:handle_request():124] handle_request: poll_exit
80
+ 2021-07-09 11:52:33,546 DEBUG SenderThread:30716 [sender.py:send():179] send: telemetry
81
+ 2021-07-09 11:52:33,546 DEBUG SenderThread:30716 [sender.py:send():179] send: exit
82
+ 2021-07-09 11:52:33,546 INFO SenderThread:30716 [sender.py:send_exit():287] handling exit code: 0
83
+ 2021-07-09 11:52:33,546 INFO SenderThread:30716 [sender.py:send_exit():295] send defer
84
+ 2021-07-09 11:52:33,546 DEBUG SenderThread:30716 [sender.py:send_request():193] send_request: poll_exit
85
+ 2021-07-09 11:52:33,547 DEBUG HandlerThread:30716 [handler.py:handle_request():124] handle_request: defer
86
+ 2021-07-09 11:52:33,547 INFO HandlerThread:30716 [handler.py:handle_request_defer():141] handle defer: 0
87
+ 2021-07-09 11:52:33,547 DEBUG SenderThread:30716 [sender.py:send_request():193] send_request: defer
88
+ 2021-07-09 11:52:33,547 INFO SenderThread:30716 [sender.py:send_request_defer():304] handle sender defer: 0
89
+ 2021-07-09 11:52:33,547 INFO SenderThread:30716 [sender.py:transition_state():308] send defer: 1
90
+ 2021-07-09 11:52:33,547 DEBUG HandlerThread:30716 [handler.py:handle_request():124] handle_request: defer
91
+ 2021-07-09 11:52:33,547 INFO HandlerThread:30716 [handler.py:handle_request_defer():141] handle defer: 1
92
+ 2021-07-09 11:52:33,560 DEBUG SenderThread:30716 [sender.py:send_request():193] send_request: defer
93
+ 2021-07-09 11:52:33,561 INFO SenderThread:30716 [sender.py:send_request_defer():304] handle sender defer: 1
94
+ 2021-07-09 11:52:33,561 INFO SenderThread:30716 [sender.py:transition_state():308] send defer: 2
95
+ 2021-07-09 11:52:33,561 DEBUG SenderThread:30716 [sender.py:send():179] send: stats
96
+ 2021-07-09 11:52:33,561 DEBUG HandlerThread:30716 [handler.py:handle_request():124] handle_request: defer
97
+ 2021-07-09 11:52:33,561 INFO HandlerThread:30716 [handler.py:handle_request_defer():141] handle defer: 2
98
+ 2021-07-09 11:52:33,562 DEBUG SenderThread:30716 [sender.py:send_request():193] send_request: defer
99
+ 2021-07-09 11:52:33,562 INFO SenderThread:30716 [sender.py:send_request_defer():304] handle sender defer: 2
100
+ 2021-07-09 11:52:33,562 INFO SenderThread:30716 [sender.py:transition_state():308] send defer: 3
101
+ 2021-07-09 11:52:33,562 DEBUG HandlerThread:30716 [handler.py:handle_request():124] handle_request: defer
102
+ 2021-07-09 11:52:33,562 INFO HandlerThread:30716 [handler.py:handle_request_defer():141] handle defer: 3
103
+ 2021-07-09 11:52:33,562 DEBUG SenderThread:30716 [sender.py:send():179] send: summary
104
+ 2021-07-09 11:52:33,563 INFO SenderThread:30716 [sender.py:_save_file():841] saving file wandb-summary.json with policy end
105
+ 2021-07-09 11:52:33,563 DEBUG SenderThread:30716 [sender.py:send_request():193] send_request: defer
106
+ 2021-07-09 11:52:33,563 INFO SenderThread:30716 [sender.py:send_request_defer():304] handle sender defer: 3
107
+ 2021-07-09 11:52:33,563 INFO SenderThread:30716 [sender.py:transition_state():308] send defer: 4
108
+ 2021-07-09 11:52:33,563 DEBUG HandlerThread:30716 [handler.py:handle_request():124] handle_request: defer
109
+ 2021-07-09 11:52:33,563 INFO HandlerThread:30716 [handler.py:handle_request_defer():141] handle defer: 4
110
+ 2021-07-09 11:52:33,563 DEBUG SenderThread:30716 [sender.py:send_request():193] send_request: defer
111
+ 2021-07-09 11:52:33,563 INFO SenderThread:30716 [sender.py:send_request_defer():304] handle sender defer: 4
112
+ 2021-07-09 11:52:33,629 INFO SenderThread:30716 [sender.py:transition_state():308] send defer: 5
113
+ 2021-07-09 11:52:33,629 DEBUG HandlerThread:30716 [handler.py:handle_request():124] handle_request: defer
114
+ 2021-07-09 11:52:33,630 INFO HandlerThread:30716 [handler.py:handle_request_defer():141] handle defer: 5
115
+ 2021-07-09 11:52:33,630 DEBUG SenderThread:30716 [sender.py:send_request():193] send_request: defer
116
+ 2021-07-09 11:52:33,630 INFO SenderThread:30716 [sender.py:send_request_defer():304] handle sender defer: 5
117
+ 2021-07-09 11:52:33,630 INFO SenderThread:30716 [dir_watcher.py:finish():282] shutting down directory watcher
118
+ 2021-07-09 11:52:33,648 DEBUG HandlerThread:30716 [handler.py:handle_request():124] handle_request: poll_exit
119
+ 2021-07-09 11:52:34,286 INFO SenderThread:30716 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/output.log
120
+ 2021-07-09 11:52:34,286 INFO SenderThread:30716 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/config.yaml
121
+ 2021-07-09 11:52:34,286 INFO SenderThread:30716 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/wandb-summary.json
122
+ 2021-07-09 11:52:34,287 INFO SenderThread:30716 [dir_watcher.py:finish():312] scan: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files
123
+ 2021-07-09 11:52:34,287 INFO SenderThread:30716 [dir_watcher.py:finish():318] scan save: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/requirements.txt requirements.txt
124
+ 2021-07-09 11:52:34,287 INFO SenderThread:30716 [dir_watcher.py:finish():318] scan save: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/output.log output.log
125
+ 2021-07-09 11:52:34,287 INFO SenderThread:30716 [dir_watcher.py:finish():318] scan save: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/wandb-metadata.json wandb-metadata.json
126
+ 2021-07-09 11:52:34,287 INFO SenderThread:30716 [dir_watcher.py:finish():318] scan save: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/config.yaml config.yaml
127
+ 2021-07-09 11:52:34,288 INFO SenderThread:30716 [dir_watcher.py:finish():318] scan save: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/wandb-summary.json wandb-summary.json
128
+ 2021-07-09 11:52:34,288 INFO SenderThread:30716 [sender.py:transition_state():308] send defer: 6
129
+ 2021-07-09 11:52:34,288 DEBUG SenderThread:30716 [sender.py:send_request():193] send_request: poll_exit
130
+ 2021-07-09 11:52:34,293 DEBUG HandlerThread:30716 [handler.py:handle_request():124] handle_request: defer
131
+ 2021-07-09 11:52:34,293 INFO HandlerThread:30716 [handler.py:handle_request_defer():141] handle defer: 6
132
+ 2021-07-09 11:52:34,294 DEBUG SenderThread:30716 [sender.py:send_request():193] send_request: defer
133
+ 2021-07-09 11:52:34,294 INFO SenderThread:30716 [sender.py:send_request_defer():304] handle sender defer: 6
134
+ 2021-07-09 11:52:34,294 INFO SenderThread:30716 [file_pusher.py:finish():177] shutting down file pusher
135
+ 2021-07-09 11:52:34,390 DEBUG HandlerThread:30716 [handler.py:handle_request():124] handle_request: poll_exit
136
+ 2021-07-09 11:52:34,390 DEBUG SenderThread:30716 [sender.py:send_request():193] send_request: poll_exit
137
+ 2021-07-09 11:52:34,492 INFO Thread-15 :30716 [upload_job.py:push():137] Uploaded file /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/wandb-summary.json
138
+ 2021-07-09 11:52:34,492 DEBUG HandlerThread:30716 [handler.py:handle_request():124] handle_request: poll_exit
139
+ 2021-07-09 11:52:34,493 DEBUG SenderThread:30716 [sender.py:send_request():193] send_request: poll_exit
140
+ 2021-07-09 11:52:34,497 INFO Thread-12 :30716 [upload_job.py:push():137] Uploaded file /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/requirements.txt
141
+ 2021-07-09 11:52:34,536 INFO Thread-13 :30716 [upload_job.py:push():137] Uploaded file /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/output.log
142
+ 2021-07-09 11:52:34,563 INFO Thread-14 :30716 [upload_job.py:push():137] Uploaded file /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/files/config.yaml
143
+ 2021-07-09 11:52:34,594 DEBUG HandlerThread:30716 [handler.py:handle_request():124] handle_request: poll_exit
144
+ 2021-07-09 11:52:34,595 DEBUG SenderThread:30716 [sender.py:send_request():193] send_request: poll_exit
145
+ 2021-07-09 11:52:34,696 DEBUG HandlerThread:30716 [handler.py:handle_request():124] handle_request: poll_exit
146
+ 2021-07-09 11:52:34,697 DEBUG SenderThread:30716 [sender.py:send_request():193] send_request: poll_exit
147
+ 2021-07-09 11:52:34,764 INFO Thread-7 :30716 [sender.py:transition_state():308] send defer: 7
148
+ 2021-07-09 11:52:34,765 DEBUG HandlerThread:30716 [handler.py:handle_request():124] handle_request: defer
149
+ 2021-07-09 11:52:34,765 INFO HandlerThread:30716 [handler.py:handle_request_defer():141] handle defer: 7
150
+ 2021-07-09 11:52:34,765 DEBUG SenderThread:30716 [sender.py:send_request():193] send_request: defer
151
+ 2021-07-09 11:52:34,765 INFO SenderThread:30716 [sender.py:send_request_defer():304] handle sender defer: 7
152
+ 2021-07-09 11:52:34,798 DEBUG HandlerThread:30716 [handler.py:handle_request():124] handle_request: poll_exit
153
+ 2021-07-09 11:52:34,838 INFO SenderThread:30716 [sender.py:transition_state():308] send defer: 8
154
+ 2021-07-09 11:52:34,838 DEBUG SenderThread:30716 [sender.py:send_request():193] send_request: poll_exit
155
+ 2021-07-09 11:52:34,839 DEBUG HandlerThread:30716 [handler.py:handle_request():124] handle_request: defer
156
+ 2021-07-09 11:52:34,839 INFO HandlerThread:30716 [handler.py:handle_request_defer():141] handle defer: 8
157
+ 2021-07-09 11:52:34,839 DEBUG SenderThread:30716 [sender.py:send_request():193] send_request: defer
158
+ 2021-07-09 11:52:34,839 INFO SenderThread:30716 [sender.py:send_request_defer():304] handle sender defer: 8
159
+ 2021-07-09 11:52:34,839 INFO SenderThread:30716 [sender.py:transition_state():308] send defer: 9
160
+ 2021-07-09 11:52:34,840 DEBUG SenderThread:30716 [sender.py:send():179] send: final
161
+ 2021-07-09 11:52:34,840 DEBUG SenderThread:30716 [sender.py:send():179] send: footer
162
+ 2021-07-09 11:52:34,840 DEBUG HandlerThread:30716 [handler.py:handle_request():124] handle_request: defer
163
+ 2021-07-09 11:52:34,840 INFO HandlerThread:30716 [handler.py:handle_request_defer():141] handle defer: 9
164
+ 2021-07-09 11:52:34,840 DEBUG SenderThread:30716 [sender.py:send_request():193] send_request: defer
165
+ 2021-07-09 11:52:34,840 INFO SenderThread:30716 [sender.py:send_request_defer():304] handle sender defer: 9
166
+ 2021-07-09 11:52:34,940 DEBUG HandlerThread:30716 [handler.py:handle_request():124] handle_request: poll_exit
167
+ 2021-07-09 11:52:34,940 DEBUG SenderThread:30716 [sender.py:send_request():193] send_request: poll_exit
168
+ 2021-07-09 11:52:34,941 INFO SenderThread:30716 [file_pusher.py:join():182] waiting for file pusher
169
+ 2021-07-09 11:52:34,942 DEBUG HandlerThread:30716 [handler.py:handle_request():124] handle_request: get_summary
170
+ 2021-07-09 11:52:34,943 DEBUG HandlerThread:30716 [handler.py:handle_request():124] handle_request: sampled_history
171
+ 2021-07-09 11:52:34,943 DEBUG HandlerThread:30716 [handler.py:handle_request():124] handle_request: shutdown
172
+ 2021-07-09 11:52:34,943 INFO HandlerThread:30716 [handler.py:finish():638] shutting down handler
173
+ 2021-07-09 11:52:35,840 INFO WriterThread:30716 [datastore.py:close():288] close: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/run-mgpt342u.wandb
174
+ 2021-07-09 11:52:35,941 INFO SenderThread:30716 [sender.py:finish():945] shutting down sender
175
+ 2021-07-09 11:52:35,941 INFO SenderThread:30716 [file_pusher.py:finish():177] shutting down file pusher
176
+ 2021-07-09 11:52:35,941 INFO SenderThread:30716 [file_pusher.py:join():182] waiting for file pusher
177
+ 2021-07-09 11:52:35,944 INFO MainThread:30716 [internal.py:handle_exit():78] Internal process exited
wandb/run-20210709_115016-mgpt342u/logs/debug.log ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2021-07-09 11:50:16,491 INFO MainThread:29662 [wandb_setup.py:_flush():69] Unhandled environment var: WANDB_WATCH
2
+ 2021-07-09 11:50:16,491 INFO MainThread:29662 [wandb_setup.py:_flush():69] setting env: {'project': 'hf-flax-robert-base-mr', 'entity': 'nipunsadvilkar'}
3
+ 2021-07-09 11:50:16,491 INFO MainThread:29662 [wandb_setup.py:_flush():69] setting login settings: {}
4
+ 2021-07-09 11:50:16,491 INFO MainThread:29662 [wandb_init.py:_log_setup():337] Logging user logs to /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/logs/debug.log
5
+ 2021-07-09 11:50:16,491 INFO MainThread:29662 [wandb_init.py:_log_setup():338] Logging internal logs to /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_115016-mgpt342u/logs/debug-internal.log
6
+ 2021-07-09 11:50:16,491 INFO MainThread:29662 [wandb_init.py:init():370] calling init triggers
7
+ 2021-07-09 11:50:16,491 INFO MainThread:29662 [wandb_init.py:init():375] wandb.init called with sweep_config: {}
8
+ config: {}
9
+ 2021-07-09 11:50:16,491 INFO MainThread:29662 [wandb_init.py:init():419] starting backend
10
+ 2021-07-09 11:50:16,491 INFO MainThread:29662 [backend.py:_multiprocessing_setup():70] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
11
+ 2021-07-09 11:50:16,516 INFO MainThread:29662 [backend.py:ensure_launched():135] starting backend process...
12
+ 2021-07-09 11:50:16,540 INFO MainThread:29662 [backend.py:ensure_launched():139] started backend process with pid: 30716
13
+ 2021-07-09 11:50:16,542 INFO MainThread:29662 [wandb_init.py:init():424] backend started and connected
14
+ 2021-07-09 11:50:16,545 INFO MainThread:29662 [wandb_init.py:init():472] updated telemetry
15
+ 2021-07-09 11:50:16,545 INFO MainThread:29662 [wandb_init.py:init():491] communicating current version
16
+ 2021-07-09 11:50:17,137 INFO MainThread:29662 [wandb_init.py:init():496] got version response
17
+ 2021-07-09 11:50:17,137 INFO MainThread:29662 [wandb_init.py:init():504] communicating run to backend with 30 second timeout
18
+ 2021-07-09 11:50:17,218 INFO MainThread:29662 [wandb_init.py:init():529] starting run threads in backend
19
+ 2021-07-09 11:50:17,269 INFO MainThread:29662 [wandb_run.py:_console_start():1623] atexit reg
20
+ 2021-07-09 11:50:17,269 INFO MainThread:29662 [wandb_run.py:_redirect():1497] redirect: SettingsConsole.REDIRECT
21
+ 2021-07-09 11:50:17,270 INFO MainThread:29662 [wandb_run.py:_redirect():1502] Redirecting console.
22
+ 2021-07-09 11:50:17,271 INFO MainThread:29662 [wandb_run.py:_redirect():1558] Redirects installed.
23
+ 2021-07-09 11:50:17,272 INFO MainThread:29662 [wandb_init.py:init():554] run started, returning control to user process
24
+ 2021-07-09 11:50:17,272 INFO MainThread:29662 [wandb_run.py:_config_callback():872] config_cb None None {'output_dir': './', 'overwrite_output_dir': True, 'do_train': False, 'do_eval': False, 'do_predict': False, 'evaluation_strategy': 'IntervalStrategy.NO', 'prediction_loss_only': False, 'per_device_train_batch_size': 4, 'per_device_eval_batch_size': 4, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'learning_rate': 0.0003, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 8.0, 'max_steps': -1, 'lr_scheduler_type': 'SchedulerType.LINEAR', 'warmup_ratio': 0.0, 'warmup_steps': 1000, 'log_level': -1, 'log_level_replica': -1, 'log_on_each_node': True, 'logging_dir': './runs/Jul09_11-50-10_t1v-n-112df4a9-w-0', 'logging_strategy': 'IntervalStrategy.STEPS', 'logging_first_step': False, 'logging_steps': 500, 'save_strategy': 'IntervalStrategy.STEPS', 'save_steps': 500, 'save_total_limit': None, 'save_on_each_node': False, 'no_cuda': False, 'seed': 42, 'fp16': False, 'fp16_opt_level': 'O1', 'fp16_backend': 'auto', 'fp16_full_eval': False, 'local_rank': -1, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': 500, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': './', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'sharded_ddp': [], 'deepspeed': None, 'label_smoothing_factor': 0.0, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'dataloader_pin_memory': True, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': False, 'resume_from_checkpoint': None, 'push_to_hub_model_id': '', 'push_to_hub_organization': None, 'push_to_hub_token': None, 'mp_parameters': ''}
25
+ 2021-07-09 11:50:17,273 INFO MainThread:29662 [wandb_run.py:_config_callback():872] config_cb None None {'model_name_or_path': None, 'model_type': 'roberta', 'config_name': './', 'tokenizer_name': './', 'cache_dir': None, 'use_fast_tokenizer': True, 'dtype': 'float32'}
26
+ 2021-07-09 11:50:17,274 INFO MainThread:29662 [wandb_run.py:_config_callback():872] config_cb None None {'dataset_name': 'oscar', 'dataset_config_name': 'unshuffled_deduplicated_als', 'train_file': None, 'validation_file': None, 'train_ref_file': None, 'validation_ref_file': None, 'overwrite_cache': False, 'validation_split_percentage': 5, 'max_seq_length': 128, 'preprocessing_num_workers': None, 'mlm_probability': 0.15, 'pad_to_max_length': False, 'line_by_line': False}
27
+ 2021-07-09 11:52:31,413 INFO MainThread:29662 [wandb_run.py:_atexit_cleanup():1593] got exitcode: 0
28
+ 2021-07-09 11:52:31,414 INFO MainThread:29662 [wandb_run.py:_restore():1565] restore
29
+ 2021-07-09 11:52:33,547 INFO MainThread:29662 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
30
+ wandb_count: 1
31
+ }
32
+ pusher_stats {
33
+ uploaded_bytes: 1200
34
+ total_bytes: 1200
35
+ }
36
+
37
+ 2021-07-09 11:52:34,289 INFO MainThread:29662 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
38
+ wandb_count: 2
39
+ }
40
+ pusher_stats {
41
+ uploaded_bytes: 1200
42
+ total_bytes: 2856
43
+ }
44
+
45
+ 2021-07-09 11:52:34,391 INFO MainThread:29662 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
46
+ wandb_count: 5
47
+ }
48
+ pusher_stats {
49
+ uploaded_bytes: 12265
50
+ total_bytes: 12265
51
+ }
52
+
53
+ 2021-07-09 11:52:34,494 INFO MainThread:29662 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
54
+ wandb_count: 5
55
+ }
56
+ pusher_stats {
57
+ uploaded_bytes: 12265
58
+ total_bytes: 12265
59
+ }
60
+
61
+ 2021-07-09 11:52:34,596 INFO MainThread:29662 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
62
+ wandb_count: 5
63
+ }
64
+ pusher_stats {
65
+ uploaded_bytes: 12265
66
+ total_bytes: 12265
67
+ }
68
+
69
+ 2021-07-09 11:52:34,698 INFO MainThread:29662 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
70
+ wandb_count: 5
71
+ }
72
+ pusher_stats {
73
+ uploaded_bytes: 12265
74
+ total_bytes: 12265
75
+ }
76
+
77
+ 2021-07-09 11:52:34,839 INFO MainThread:29662 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
78
+ wandb_count: 5
79
+ }
80
+ pusher_stats {
81
+ uploaded_bytes: 12265
82
+ total_bytes: 12265
83
+ }
84
+
85
+ 2021-07-09 11:52:34,941 INFO MainThread:29662 [wandb_run.py:_wait_for_finish():1715] got exit ret: done: true
86
+ exit_result {
87
+ }
88
+ file_counts {
89
+ wandb_count: 5
90
+ }
91
+ pusher_stats {
92
+ uploaded_bytes: 12265
93
+ total_bytes: 12265
94
+ }
95
+
96
+ 2021-07-09 11:52:36,012 INFO MainThread:29662 [wandb_run.py:_show_files():1937] logging synced files
wandb/run-20210709_115016-mgpt342u/run-mgpt342u.wandb ADDED
Binary file (16.4 kB). View file
 
wandb/run-20210709_122021-2porvgvv/files/config.yaml ADDED
@@ -0,0 +1,305 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ wandb_version: 1
2
+
3
+ _wandb:
4
+ desc: null
5
+ value:
6
+ cli_version: 0.10.33
7
+ framework: huggingface
8
+ huggingface_version: 4.9.0.dev0
9
+ is_jupyter_run: false
10
+ is_kaggle_kernel: false
11
+ python_version: 3.8.10
12
+ t:
13
+ 1:
14
+ - 11
15
+ 2:
16
+ - 11
17
+ 4: 3.8.10
18
+ 5: 0.10.33
19
+ 6: 4.9.0.dev0
20
+ 8:
21
+ - 5
22
+ adafactor:
23
+ desc: null
24
+ value: false
25
+ adam_beta1:
26
+ desc: null
27
+ value: 0.9
28
+ adam_beta2:
29
+ desc: null
30
+ value: 0.999
31
+ adam_epsilon:
32
+ desc: null
33
+ value: 1.0e-08
34
+ cache_dir:
35
+ desc: null
36
+ value: null
37
+ config_name:
38
+ desc: null
39
+ value: ./
40
+ dataloader_drop_last:
41
+ desc: null
42
+ value: false
43
+ dataloader_num_workers:
44
+ desc: null
45
+ value: 0
46
+ dataloader_pin_memory:
47
+ desc: null
48
+ value: true
49
+ dataset_config_name:
50
+ desc: null
51
+ value: unshuffled_deduplicated_als
52
+ dataset_name:
53
+ desc: null
54
+ value: oscar
55
+ ddp_find_unused_parameters:
56
+ desc: null
57
+ value: null
58
+ debug:
59
+ desc: null
60
+ value: []
61
+ deepspeed:
62
+ desc: null
63
+ value: null
64
+ disable_tqdm:
65
+ desc: null
66
+ value: false
67
+ do_eval:
68
+ desc: null
69
+ value: false
70
+ do_predict:
71
+ desc: null
72
+ value: false
73
+ do_train:
74
+ desc: null
75
+ value: false
76
+ dtype:
77
+ desc: null
78
+ value: float32
79
+ eval_accumulation_steps:
80
+ desc: null
81
+ value: null
82
+ eval_steps:
83
+ desc: null
84
+ value: 500
85
+ evaluation_strategy:
86
+ desc: null
87
+ value: IntervalStrategy.NO
88
+ fp16:
89
+ desc: null
90
+ value: false
91
+ fp16_backend:
92
+ desc: null
93
+ value: auto
94
+ fp16_full_eval:
95
+ desc: null
96
+ value: false
97
+ fp16_opt_level:
98
+ desc: null
99
+ value: O1
100
+ gradient_accumulation_steps:
101
+ desc: null
102
+ value: 1
103
+ greater_is_better:
104
+ desc: null
105
+ value: null
106
+ group_by_length:
107
+ desc: null
108
+ value: false
109
+ ignore_data_skip:
110
+ desc: null
111
+ value: false
112
+ label_names:
113
+ desc: null
114
+ value: null
115
+ label_smoothing_factor:
116
+ desc: null
117
+ value: 0.0
118
+ learning_rate:
119
+ desc: null
120
+ value: 0.0003
121
+ length_column_name:
122
+ desc: null
123
+ value: length
124
+ line_by_line:
125
+ desc: null
126
+ value: false
127
+ load_best_model_at_end:
128
+ desc: null
129
+ value: false
130
+ local_rank:
131
+ desc: null
132
+ value: -1
133
+ log_level:
134
+ desc: null
135
+ value: -1
136
+ log_level_replica:
137
+ desc: null
138
+ value: -1
139
+ log_on_each_node:
140
+ desc: null
141
+ value: true
142
+ logging_dir:
143
+ desc: null
144
+ value: ./runs/Jul09_12-20-15_t1v-n-112df4a9-w-0
145
+ logging_first_step:
146
+ desc: null
147
+ value: false
148
+ logging_steps:
149
+ desc: null
150
+ value: 500
151
+ logging_strategy:
152
+ desc: null
153
+ value: IntervalStrategy.STEPS
154
+ lr_scheduler_type:
155
+ desc: null
156
+ value: SchedulerType.LINEAR
157
+ max_grad_norm:
158
+ desc: null
159
+ value: 1.0
160
+ max_seq_length:
161
+ desc: null
162
+ value: 128
163
+ max_steps:
164
+ desc: null
165
+ value: -1
166
+ metric_for_best_model:
167
+ desc: null
168
+ value: null
169
+ mlm_probability:
170
+ desc: null
171
+ value: 0.15
172
+ model_name_or_path:
173
+ desc: null
174
+ value: null
175
+ model_type:
176
+ desc: null
177
+ value: roberta
178
+ mp_parameters:
179
+ desc: null
180
+ value: ''
181
+ no_cuda:
182
+ desc: null
183
+ value: false
184
+ num_train_epochs:
185
+ desc: null
186
+ value: 8.0
187
+ output_dir:
188
+ desc: null
189
+ value: ./
190
+ overwrite_cache:
191
+ desc: null
192
+ value: false
193
+ overwrite_output_dir:
194
+ desc: null
195
+ value: true
196
+ pad_to_max_length:
197
+ desc: null
198
+ value: false
199
+ past_index:
200
+ desc: null
201
+ value: -1
202
+ per_device_eval_batch_size:
203
+ desc: null
204
+ value: 4
205
+ per_device_train_batch_size:
206
+ desc: null
207
+ value: 4
208
+ per_gpu_eval_batch_size:
209
+ desc: null
210
+ value: null
211
+ per_gpu_train_batch_size:
212
+ desc: null
213
+ value: null
214
+ prediction_loss_only:
215
+ desc: null
216
+ value: false
217
+ preprocessing_num_workers:
218
+ desc: null
219
+ value: null
220
+ push_to_hub:
221
+ desc: null
222
+ value: false
223
+ push_to_hub_model_id:
224
+ desc: null
225
+ value: ''
226
+ push_to_hub_organization:
227
+ desc: null
228
+ value: null
229
+ push_to_hub_token:
230
+ desc: null
231
+ value: null
232
+ remove_unused_columns:
233
+ desc: null
234
+ value: true
235
+ report_to:
236
+ desc: null
237
+ value:
238
+ - tensorboard
239
+ - wandb
240
+ resume_from_checkpoint:
241
+ desc: null
242
+ value: null
243
+ run_name:
244
+ desc: null
245
+ value: ./
246
+ save_on_each_node:
247
+ desc: null
248
+ value: false
249
+ save_steps:
250
+ desc: null
251
+ value: 500
252
+ save_strategy:
253
+ desc: null
254
+ value: IntervalStrategy.STEPS
255
+ save_total_limit:
256
+ desc: null
257
+ value: null
258
+ seed:
259
+ desc: null
260
+ value: 42
261
+ sharded_ddp:
262
+ desc: null
263
+ value: []
264
+ skip_memory_metrics:
265
+ desc: null
266
+ value: true
267
+ tokenizer_name:
268
+ desc: null
269
+ value: ./
270
+ tpu_metrics_debug:
271
+ desc: null
272
+ value: false
273
+ tpu_num_cores:
274
+ desc: null
275
+ value: null
276
+ train_file:
277
+ desc: null
278
+ value: null
279
+ train_ref_file:
280
+ desc: null
281
+ value: null
282
+ use_fast_tokenizer:
283
+ desc: null
284
+ value: true
285
+ use_legacy_prediction_loop:
286
+ desc: null
287
+ value: false
288
+ validation_file:
289
+ desc: null
290
+ value: null
291
+ validation_ref_file:
292
+ desc: null
293
+ value: null
294
+ validation_split_percentage:
295
+ desc: null
296
+ value: 5
297
+ warmup_ratio:
298
+ desc: null
299
+ value: 0.0
300
+ warmup_steps:
301
+ desc: null
302
+ value: 1000
303
+ weight_decay:
304
+ desc: null
305
+ value: 0.0
wandb/run-20210709_122021-2porvgvv/files/output.log ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ [12:20:22] - WARNING - __main__ - Unable to display metrics through TensorBoard because some package are not installed: No module named 'tensorflow'
3
+ /home/nipunsadvilkar/roberta_mr_env/lib/python3.8/site-packages/jax/lib/xla_bridge.py:382: UserWarning: jax.host_count has been renamed to jax.process_count. This alias will eventually be removed; please update your code.
4
+ warnings.warn(
5
+ /home/nipunsadvilkar/roberta_mr_env/lib/python3.8/site-packages/jax/lib/xla_bridge.py:369: UserWarning: jax.host_id has been renamed to jax.process_index. This alias will eventually be removed; please update your code.
6
+ warnings.warn(
7
+ Epoch ... (1/8): 0%| | 0/8 [00:00<?, ?it/s]
8
+
9
+
10
+ Epoch ... (1/8): 12%|███████████████████ | 1/8 [01:18<09:06, 78.12s/it]
11
+
12
+
13
+ Epoch ... (1/8): 25%|██████████████████████████████████████ | 2/8 [01:22<03:30, 35.03s/it]
14
+
15
+
16
+ Epoch ... (1/8): 38%|█████████████████████████████████████████████████████████ | 3/8 [01:27<01:46, 21.23s/it]
17
+
18
+ Epoch ... (1/8): 38%|█████████████████████████████████████████████████████████ | 3/8 [01:31<02:31, 30.34s/it]
wandb/run-20210709_122021-2porvgvv/files/requirements.txt ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ absl-py==0.13.0
2
+ aiohttp==3.7.4.post0
3
+ async-timeout==3.0.1
4
+ attrs==21.2.0
5
+ backcall==0.2.0
6
+ cachetools==4.2.2
7
+ certifi==2021.5.30
8
+ chardet==4.0.0
9
+ chex==0.0.8
10
+ click==8.0.1
11
+ configparser==5.0.2
12
+ cycler==0.10.0
13
+ datasets==1.9.1.dev0
14
+ decorator==5.0.9
15
+ dill==0.3.4
16
+ dm-tree==0.1.6
17
+ docker-pycreds==0.4.0
18
+ filelock==3.0.12
19
+ flatbuffers==2.0
20
+ flax==0.3.4
21
+ fsspec==2021.6.1
22
+ gitdb==4.0.7
23
+ gitpython==3.1.18
24
+ google-auth-oauthlib==0.4.4
25
+ google-auth==1.32.1
26
+ grpcio==1.38.1
27
+ huggingface-hub==0.0.12
28
+ idna==2.10
29
+ ipython-genutils==0.2.0
30
+ ipython==7.25.0
31
+ jax==0.2.16
32
+ jaxlib==0.1.68
33
+ jedi==0.18.0
34
+ joblib==1.0.1
35
+ kiwisolver==1.3.1
36
+ libtpu-nightly==0.1.dev20210615
37
+ markdown==3.3.4
38
+ matplotlib-inline==0.1.2
39
+ matplotlib==3.4.2
40
+ msgpack==1.0.2
41
+ multidict==5.1.0
42
+ multiprocess==0.70.12.2
43
+ numpy==1.21.0
44
+ oauthlib==3.1.1
45
+ opt-einsum==3.3.0
46
+ optax==0.0.9
47
+ packaging==21.0
48
+ pandas==1.3.0
49
+ parso==0.8.2
50
+ pathtools==0.1.2
51
+ pexpect==4.8.0
52
+ pickleshare==0.7.5
53
+ pillow==8.3.1
54
+ pip==20.0.2
55
+ pkg-resources==0.0.0
56
+ promise==2.3
57
+ prompt-toolkit==3.0.19
58
+ protobuf==3.17.3
59
+ psutil==5.8.0
60
+ ptyprocess==0.7.0
61
+ pyarrow==4.0.1
62
+ pyasn1-modules==0.2.8
63
+ pyasn1==0.4.8
64
+ pygments==2.9.0
65
+ pyparsing==2.4.7
66
+ python-dateutil==2.8.1
67
+ pytz==2021.1
68
+ pyyaml==5.4.1
69
+ regex==2021.7.6
70
+ requests-oauthlib==1.3.0
71
+ requests==2.25.1
72
+ rsa==4.7.2
73
+ sacremoses==0.0.45
74
+ scipy==1.7.0
75
+ sentry-sdk==1.3.0
76
+ setuptools==44.0.0
77
+ shortuuid==1.0.1
78
+ six==1.16.0
79
+ smmap==4.0.0
80
+ subprocess32==3.5.4
81
+ tensorboard-data-server==0.6.1
82
+ tensorboard-plugin-wit==1.8.0
83
+ tensorboard==2.5.0
84
+ tokenizers==0.10.3
85
+ toolz==0.11.1
86
+ tqdm==4.61.2
87
+ traitlets==5.0.5
88
+ transformers==4.9.0.dev0
89
+ typing-extensions==3.10.0.0
90
+ urllib3==1.26.6
91
+ wandb==0.10.33
92
+ wcwidth==0.2.5
93
+ werkzeug==2.0.1
94
+ wheel==0.36.2
95
+ xxhash==2.0.2
96
+ yarl==1.6.3
wandb/run-20210709_122021-2porvgvv/files/wandb-metadata.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "os": "Linux-5.4.0-1043-gcp-x86_64-with-glibc2.29",
3
+ "python": "3.8.10",
4
+ "heartbeatAt": "2021-07-09T12:20:22.116773",
5
+ "startedAt": "2021-07-09T12:20:21.341845",
6
+ "docker": null,
7
+ "cpu_count": 96,
8
+ "cuda": null,
9
+ "args": [
10
+ "--output_dir=./",
11
+ "--model_type=roberta",
12
+ "--config_name=./",
13
+ "--tokenizer_name=./",
14
+ "--dataset_name=oscar",
15
+ "--dataset_config_name=unshuffled_deduplicated_als",
16
+ "--max_seq_length=128",
17
+ "--per_device_train_batch_size=4",
18
+ "--per_device_eval_batch_size=4",
19
+ "--learning_rate=3e-4",
20
+ "--warmup_steps=1000",
21
+ "--overwrite_output_dir",
22
+ "--num_train_epochs=8"
23
+ ],
24
+ "state": "running",
25
+ "program": "run_mlm_flax.py",
26
+ "codePath": "run_mlm_flax.py",
27
+ "git": {
28
+ "remote": "https://huggingface.co/flax-community/roberta-base-mr",
29
+ "commit": "faa64e8a79301832a56c78b2b293675039070bb0"
30
+ },
31
+ "email": "nipunsadvilkar@gmail.com",
32
+ "root": "/home/nipunsadvilkar/sample/roberta-base-mr",
33
+ "host": "t1v-n-112df4a9-w-0",
34
+ "username": "nipunsadvilkar",
35
+ "executable": "/home/nipunsadvilkar/roberta_mr_env/bin/python"
36
+ }
wandb/run-20210709_122021-2porvgvv/files/wandb-summary.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {}
wandb/run-20210709_122021-2porvgvv/logs/debug-internal.log ADDED
@@ -0,0 +1,156 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2021-07-09 12:20:21,976 INFO MainThread:32095 [internal.py:wandb_internal():88] W&B internal server running at pid: 32095, started at: 2021-07-09 12:20:21.975682
2
+ 2021-07-09 12:20:21,978 DEBUG HandlerThread:32095 [handler.py:handle_request():124] handle_request: check_version
3
+ 2021-07-09 12:20:21,978 INFO WriterThread:32095 [datastore.py:open_for_write():80] open: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_122021-2porvgvv/run-2porvgvv.wandb
4
+ 2021-07-09 12:20:21,979 DEBUG SenderThread:32095 [sender.py:send():179] send: header
5
+ 2021-07-09 12:20:21,979 DEBUG SenderThread:32095 [sender.py:send_request():193] send_request: check_version
6
+ 2021-07-09 12:20:22,045 DEBUG SenderThread:32095 [sender.py:send():179] send: run
7
+ 2021-07-09 12:20:22,114 INFO SenderThread:32095 [dir_watcher.py:__init__():168] watching files in: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_122021-2porvgvv/files
8
+ 2021-07-09 12:20:22,114 INFO SenderThread:32095 [sender.py:_start_run_threads():716] run started: 2porvgvv with start time 1625833221
9
+ 2021-07-09 12:20:22,114 DEBUG SenderThread:32095 [sender.py:send():179] send: summary
10
+ 2021-07-09 12:20:22,114 INFO SenderThread:32095 [sender.py:_save_file():841] saving file wandb-summary.json with policy end
11
+ 2021-07-09 12:20:22,115 DEBUG HandlerThread:32095 [handler.py:handle_request():124] handle_request: run_start
12
+ 2021-07-09 12:20:22,116 DEBUG HandlerThread:32095 [meta.py:__init__():39] meta init
13
+ 2021-07-09 12:20:22,116 DEBUG HandlerThread:32095 [meta.py:__init__():53] meta init done
14
+ 2021-07-09 12:20:22,116 DEBUG HandlerThread:32095 [meta.py:probe():210] probe
15
+ 2021-07-09 12:20:22,117 DEBUG HandlerThread:32095 [meta.py:_setup_git():200] setup git
16
+ 2021-07-09 12:20:22,137 DEBUG HandlerThread:32095 [meta.py:_setup_git():207] setup git done
17
+ 2021-07-09 12:20:22,138 DEBUG HandlerThread:32095 [meta.py:_save_pip():57] save pip
18
+ 2021-07-09 12:20:22,138 DEBUG HandlerThread:32095 [meta.py:_save_pip():71] save pip done
19
+ 2021-07-09 12:20:22,138 DEBUG HandlerThread:32095 [meta.py:probe():252] probe done
20
+ 2021-07-09 12:20:22,170 DEBUG SenderThread:32095 [sender.py:send():179] send: files
21
+ 2021-07-09 12:20:22,171 INFO SenderThread:32095 [sender.py:_save_file():841] saving file wandb-metadata.json with policy now
22
+ 2021-07-09 12:20:22,175 DEBUG HandlerThread:32095 [handler.py:handle_request():124] handle_request: stop_status
23
+ 2021-07-09 12:20:22,176 DEBUG SenderThread:32095 [sender.py:send_request():193] send_request: stop_status
24
+ 2021-07-09 12:20:22,201 DEBUG SenderThread:32095 [sender.py:send():179] send: config
25
+ 2021-07-09 12:20:22,202 DEBUG SenderThread:32095 [sender.py:send():179] send: config
26
+ 2021-07-09 12:20:22,202 DEBUG SenderThread:32095 [sender.py:send():179] send: config
27
+ 2021-07-09 12:20:22,407 INFO Thread-11 :32095 [upload_job.py:push():137] Uploaded file /tmp/tmp756bbzv5wandb/1jtttinj-wandb-metadata.json
28
+ 2021-07-09 12:20:23,116 INFO Thread-8 :32095 [dir_watcher.py:_on_file_created():216] file/dir created: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_122021-2porvgvv/files/wandb-summary.json
29
+ 2021-07-09 12:20:23,116 INFO Thread-8 :32095 [dir_watcher.py:_on_file_created():216] file/dir created: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_122021-2porvgvv/files/wandb-metadata.json
30
+ 2021-07-09 12:20:23,116 INFO Thread-8 :32095 [dir_watcher.py:_on_file_created():216] file/dir created: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_122021-2porvgvv/files/output.log
31
+ 2021-07-09 12:20:23,116 INFO Thread-8 :32095 [dir_watcher.py:_on_file_created():216] file/dir created: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_122021-2porvgvv/files/requirements.txt
32
+ 2021-07-09 12:20:25,115 INFO Thread-8 :32095 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_122021-2porvgvv/files/output.log
33
+ 2021-07-09 12:20:29,117 INFO Thread-8 :32095 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_122021-2porvgvv/files/output.log
34
+ 2021-07-09 12:20:31,118 INFO Thread-8 :32095 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_122021-2porvgvv/files/output.log
35
+ 2021-07-09 12:20:37,225 DEBUG HandlerThread:32095 [handler.py:handle_request():124] handle_request: stop_status
36
+ 2021-07-09 12:20:37,225 DEBUG SenderThread:32095 [sender.py:send_request():193] send_request: stop_status
37
+ 2021-07-09 12:20:50,195 DEBUG SenderThread:32095 [sender.py:send():179] send: stats
38
+ 2021-07-09 12:20:52,274 DEBUG HandlerThread:32095 [handler.py:handle_request():124] handle_request: stop_status
39
+ 2021-07-09 12:20:52,275 DEBUG SenderThread:32095 [sender.py:send_request():193] send_request: stop_status
40
+ 2021-07-09 12:20:53,127 INFO Thread-8 :32095 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_122021-2porvgvv/files/config.yaml
41
+ 2021-07-09 12:21:07,310 DEBUG HandlerThread:32095 [handler.py:handle_request():124] handle_request: stop_status
42
+ 2021-07-09 12:21:07,310 DEBUG SenderThread:32095 [sender.py:send_request():193] send_request: stop_status
43
+ 2021-07-09 12:21:20,275 DEBUG SenderThread:32095 [sender.py:send():179] send: stats
44
+ 2021-07-09 12:21:22,366 DEBUG HandlerThread:32095 [handler.py:handle_request():124] handle_request: stop_status
45
+ 2021-07-09 12:21:22,366 DEBUG SenderThread:32095 [sender.py:send_request():193] send_request: stop_status
46
+ 2021-07-09 12:21:37,397 DEBUG HandlerThread:32095 [handler.py:handle_request():124] handle_request: stop_status
47
+ 2021-07-09 12:21:37,397 DEBUG SenderThread:32095 [sender.py:send_request():193] send_request: stop_status
48
+ 2021-07-09 12:21:43,148 INFO Thread-8 :32095 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_122021-2porvgvv/files/output.log
49
+ 2021-07-09 12:21:45,149 INFO Thread-8 :32095 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_122021-2porvgvv/files/output.log
50
+ 2021-07-09 12:21:47,150 INFO Thread-8 :32095 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_122021-2porvgvv/files/output.log
51
+ 2021-07-09 12:21:49,151 INFO Thread-8 :32095 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_122021-2porvgvv/files/output.log
52
+ 2021-07-09 12:21:50,353 DEBUG SenderThread:32095 [sender.py:send():179] send: stats
53
+ 2021-07-09 12:21:51,152 INFO Thread-8 :32095 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_122021-2porvgvv/files/output.log
54
+ 2021-07-09 12:21:52,475 DEBUG HandlerThread:32095 [handler.py:handle_request():124] handle_request: stop_status
55
+ 2021-07-09 12:21:52,475 DEBUG SenderThread:32095 [sender.py:send_request():193] send_request: stop_status
56
+ 2021-07-09 12:21:53,153 INFO Thread-8 :32095 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_122021-2porvgvv/files/output.log
57
+ 2021-07-09 12:21:55,154 INFO Thread-8 :32095 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_122021-2porvgvv/files/output.log
58
+ 2021-07-09 12:21:57,155 INFO Thread-8 :32095 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_122021-2porvgvv/files/output.log
59
+ 2021-07-09 12:21:59,156 INFO Thread-8 :32095 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_122021-2porvgvv/files/output.log
60
+ 2021-07-09 12:22:00,555 DEBUG SenderThread:32095 [sender.py:send():179] send: telemetry
61
+ 2021-07-09 12:22:00,555 DEBUG HandlerThread:32095 [handler.py:handle_request():124] handle_request: poll_exit
62
+ 2021-07-09 12:22:00,555 DEBUG SenderThread:32095 [sender.py:send():179] send: exit
63
+ 2021-07-09 12:22:00,555 INFO SenderThread:32095 [sender.py:send_exit():287] handling exit code: 1
64
+ 2021-07-09 12:22:00,556 INFO SenderThread:32095 [sender.py:send_exit():295] send defer
65
+ 2021-07-09 12:22:00,556 DEBUG SenderThread:32095 [sender.py:send_request():193] send_request: poll_exit
66
+ 2021-07-09 12:22:00,556 DEBUG HandlerThread:32095 [handler.py:handle_request():124] handle_request: defer
67
+ 2021-07-09 12:22:00,556 INFO HandlerThread:32095 [handler.py:handle_request_defer():141] handle defer: 0
68
+ 2021-07-09 12:22:00,557 DEBUG SenderThread:32095 [sender.py:send_request():193] send_request: defer
69
+ 2021-07-09 12:22:00,557 INFO SenderThread:32095 [sender.py:send_request_defer():304] handle sender defer: 0
70
+ 2021-07-09 12:22:00,557 INFO SenderThread:32095 [sender.py:transition_state():308] send defer: 1
71
+ 2021-07-09 12:22:00,557 DEBUG HandlerThread:32095 [handler.py:handle_request():124] handle_request: defer
72
+ 2021-07-09 12:22:00,557 INFO HandlerThread:32095 [handler.py:handle_request_defer():141] handle defer: 1
73
+ 2021-07-09 12:22:00,578 DEBUG SenderThread:32095 [sender.py:send_request():193] send_request: defer
74
+ 2021-07-09 12:22:00,578 INFO SenderThread:32095 [sender.py:send_request_defer():304] handle sender defer: 1
75
+ 2021-07-09 12:22:00,578 INFO SenderThread:32095 [sender.py:transition_state():308] send defer: 2
76
+ 2021-07-09 12:22:00,579 DEBUG SenderThread:32095 [sender.py:send():179] send: stats
77
+ 2021-07-09 12:22:00,579 DEBUG HandlerThread:32095 [handler.py:handle_request():124] handle_request: defer
78
+ 2021-07-09 12:22:00,579 INFO HandlerThread:32095 [handler.py:handle_request_defer():141] handle defer: 2
79
+ 2021-07-09 12:22:00,579 DEBUG SenderThread:32095 [sender.py:send_request():193] send_request: defer
80
+ 2021-07-09 12:22:00,579 INFO SenderThread:32095 [sender.py:send_request_defer():304] handle sender defer: 2
81
+ 2021-07-09 12:22:00,579 INFO SenderThread:32095 [sender.py:transition_state():308] send defer: 3
82
+ 2021-07-09 12:22:00,579 DEBUG HandlerThread:32095 [handler.py:handle_request():124] handle_request: defer
83
+ 2021-07-09 12:22:00,580 INFO HandlerThread:32095 [handler.py:handle_request_defer():141] handle defer: 3
84
+ 2021-07-09 12:22:00,580 DEBUG SenderThread:32095 [sender.py:send():179] send: summary
85
+ 2021-07-09 12:22:00,580 INFO SenderThread:32095 [sender.py:_save_file():841] saving file wandb-summary.json with policy end
86
+ 2021-07-09 12:22:00,580 DEBUG SenderThread:32095 [sender.py:send_request():193] send_request: defer
87
+ 2021-07-09 12:22:00,580 INFO SenderThread:32095 [sender.py:send_request_defer():304] handle sender defer: 3
88
+ 2021-07-09 12:22:00,580 INFO SenderThread:32095 [sender.py:transition_state():308] send defer: 4
89
+ 2021-07-09 12:22:00,580 DEBUG HandlerThread:32095 [handler.py:handle_request():124] handle_request: defer
90
+ 2021-07-09 12:22:00,580 INFO HandlerThread:32095 [handler.py:handle_request_defer():141] handle defer: 4
91
+ 2021-07-09 12:22:00,581 DEBUG SenderThread:32095 [sender.py:send_request():193] send_request: defer
92
+ 2021-07-09 12:22:00,581 INFO SenderThread:32095 [sender.py:send_request_defer():304] handle sender defer: 4
93
+ 2021-07-09 12:22:00,651 INFO SenderThread:32095 [sender.py:transition_state():308] send defer: 5
94
+ 2021-07-09 12:22:00,652 DEBUG HandlerThread:32095 [handler.py:handle_request():124] handle_request: defer
95
+ 2021-07-09 12:22:00,652 INFO HandlerThread:32095 [handler.py:handle_request_defer():141] handle defer: 5
96
+ 2021-07-09 12:22:00,652 DEBUG SenderThread:32095 [sender.py:send_request():193] send_request: defer
97
+ 2021-07-09 12:22:00,652 INFO SenderThread:32095 [sender.py:send_request_defer():304] handle sender defer: 5
98
+ 2021-07-09 12:22:00,652 INFO SenderThread:32095 [dir_watcher.py:finish():282] shutting down directory watcher
99
+ 2021-07-09 12:22:00,658 DEBUG HandlerThread:32095 [handler.py:handle_request():124] handle_request: poll_exit
100
+ 2021-07-09 12:22:01,157 INFO SenderThread:32095 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_122021-2porvgvv/files/wandb-summary.json
101
+ 2021-07-09 12:22:01,158 INFO SenderThread:32095 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_122021-2porvgvv/files/output.log
102
+ 2021-07-09 12:22:01,158 INFO SenderThread:32095 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_122021-2porvgvv/files/config.yaml
103
+ 2021-07-09 12:22:01,158 INFO SenderThread:32095 [dir_watcher.py:finish():312] scan: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_122021-2porvgvv/files
104
+ 2021-07-09 12:22:01,158 INFO SenderThread:32095 [dir_watcher.py:finish():318] scan save: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_122021-2porvgvv/files/requirements.txt requirements.txt
105
+ 2021-07-09 12:22:01,158 INFO SenderThread:32095 [dir_watcher.py:finish():318] scan save: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_122021-2porvgvv/files/output.log output.log
106
+ 2021-07-09 12:22:01,158 INFO SenderThread:32095 [dir_watcher.py:finish():318] scan save: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_122021-2porvgvv/files/wandb-metadata.json wandb-metadata.json
107
+ 2021-07-09 12:22:01,158 INFO SenderThread:32095 [dir_watcher.py:finish():318] scan save: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_122021-2porvgvv/files/config.yaml config.yaml
108
+ 2021-07-09 12:22:01,158 INFO SenderThread:32095 [dir_watcher.py:finish():318] scan save: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_122021-2porvgvv/files/wandb-summary.json wandb-summary.json
109
+ 2021-07-09 12:22:01,159 INFO SenderThread:32095 [sender.py:transition_state():308] send defer: 6
110
+ 2021-07-09 12:22:01,159 DEBUG SenderThread:32095 [sender.py:send_request():193] send_request: poll_exit
111
+ 2021-07-09 12:22:01,162 DEBUG HandlerThread:32095 [handler.py:handle_request():124] handle_request: defer
112
+ 2021-07-09 12:22:01,162 INFO HandlerThread:32095 [handler.py:handle_request_defer():141] handle defer: 6
113
+ 2021-07-09 12:22:01,165 DEBUG SenderThread:32095 [sender.py:send_request():193] send_request: defer
114
+ 2021-07-09 12:22:01,165 INFO SenderThread:32095 [sender.py:send_request_defer():304] handle sender defer: 6
115
+ 2021-07-09 12:22:01,165 INFO SenderThread:32095 [file_pusher.py:finish():177] shutting down file pusher
116
+ 2021-07-09 12:22:01,263 DEBUG HandlerThread:32095 [handler.py:handle_request():124] handle_request: poll_exit
117
+ 2021-07-09 12:22:01,264 DEBUG SenderThread:32095 [sender.py:send_request():193] send_request: poll_exit
118
+ 2021-07-09 12:22:01,365 INFO Thread-14 :32095 [upload_job.py:push():137] Uploaded file /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_122021-2porvgvv/files/config.yaml
119
+ 2021-07-09 12:22:01,365 DEBUG HandlerThread:32095 [handler.py:handle_request():124] handle_request: poll_exit
120
+ 2021-07-09 12:22:01,366 DEBUG SenderThread:32095 [sender.py:send_request():193] send_request: poll_exit
121
+ 2021-07-09 12:22:01,372 INFO Thread-13 :32095 [upload_job.py:push():137] Uploaded file /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_122021-2porvgvv/files/output.log
122
+ 2021-07-09 12:22:01,388 INFO Thread-15 :32095 [upload_job.py:push():137] Uploaded file /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_122021-2porvgvv/files/wandb-summary.json
123
+ 2021-07-09 12:22:01,392 INFO Thread-12 :32095 [upload_job.py:push():137] Uploaded file /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_122021-2porvgvv/files/requirements.txt
124
+ 2021-07-09 12:22:01,467 DEBUG HandlerThread:32095 [handler.py:handle_request():124] handle_request: poll_exit
125
+ 2021-07-09 12:22:01,468 DEBUG SenderThread:32095 [sender.py:send_request():193] send_request: poll_exit
126
+ 2021-07-09 12:22:01,569 DEBUG HandlerThread:32095 [handler.py:handle_request():124] handle_request: poll_exit
127
+ 2021-07-09 12:22:01,570 DEBUG SenderThread:32095 [sender.py:send_request():193] send_request: poll_exit
128
+ 2021-07-09 12:22:01,592 INFO Thread-7 :32095 [sender.py:transition_state():308] send defer: 7
129
+ 2021-07-09 12:22:01,593 DEBUG HandlerThread:32095 [handler.py:handle_request():124] handle_request: defer
130
+ 2021-07-09 12:22:01,593 INFO HandlerThread:32095 [handler.py:handle_request_defer():141] handle defer: 7
131
+ 2021-07-09 12:22:01,593 DEBUG SenderThread:32095 [sender.py:send_request():193] send_request: defer
132
+ 2021-07-09 12:22:01,593 INFO SenderThread:32095 [sender.py:send_request_defer():304] handle sender defer: 7
133
+ 2021-07-09 12:22:01,663 INFO SenderThread:32095 [sender.py:transition_state():308] send defer: 8
134
+ 2021-07-09 12:22:01,664 DEBUG HandlerThread:32095 [handler.py:handle_request():124] handle_request: defer
135
+ 2021-07-09 12:22:01,664 INFO HandlerThread:32095 [handler.py:handle_request_defer():141] handle defer: 8
136
+ 2021-07-09 12:22:01,664 DEBUG SenderThread:32095 [sender.py:send_request():193] send_request: defer
137
+ 2021-07-09 12:22:01,664 INFO SenderThread:32095 [sender.py:send_request_defer():304] handle sender defer: 8
138
+ 2021-07-09 12:22:01,664 INFO SenderThread:32095 [sender.py:transition_state():308] send defer: 9
139
+ 2021-07-09 12:22:01,665 DEBUG SenderThread:32095 [sender.py:send():179] send: final
140
+ 2021-07-09 12:22:01,665 DEBUG SenderThread:32095 [sender.py:send():179] send: footer
141
+ 2021-07-09 12:22:01,665 DEBUG HandlerThread:32095 [handler.py:handle_request():124] handle_request: defer
142
+ 2021-07-09 12:22:01,665 INFO HandlerThread:32095 [handler.py:handle_request_defer():141] handle defer: 9
143
+ 2021-07-09 12:22:01,665 DEBUG SenderThread:32095 [sender.py:send_request():193] send_request: defer
144
+ 2021-07-09 12:22:01,665 INFO SenderThread:32095 [sender.py:send_request_defer():304] handle sender defer: 9
145
+ 2021-07-09 12:22:01,671 DEBUG HandlerThread:32095 [handler.py:handle_request():124] handle_request: poll_exit
146
+ 2021-07-09 12:22:01,671 DEBUG SenderThread:32095 [sender.py:send_request():193] send_request: poll_exit
147
+ 2021-07-09 12:22:01,672 INFO SenderThread:32095 [file_pusher.py:join():182] waiting for file pusher
148
+ 2021-07-09 12:22:01,673 DEBUG HandlerThread:32095 [handler.py:handle_request():124] handle_request: get_summary
149
+ 2021-07-09 12:22:01,674 DEBUG HandlerThread:32095 [handler.py:handle_request():124] handle_request: sampled_history
150
+ 2021-07-09 12:22:01,674 DEBUG HandlerThread:32095 [handler.py:handle_request():124] handle_request: shutdown
151
+ 2021-07-09 12:22:01,674 INFO HandlerThread:32095 [handler.py:finish():638] shutting down handler
152
+ 2021-07-09 12:22:02,665 INFO WriterThread:32095 [datastore.py:close():288] close: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_122021-2porvgvv/run-2porvgvv.wandb
153
+ 2021-07-09 12:22:02,672 INFO SenderThread:32095 [sender.py:finish():945] shutting down sender
154
+ 2021-07-09 12:22:02,672 INFO SenderThread:32095 [file_pusher.py:finish():177] shutting down file pusher
155
+ 2021-07-09 12:22:02,672 INFO SenderThread:32095 [file_pusher.py:join():182] waiting for file pusher
156
+ 2021-07-09 12:22:02,675 INFO MainThread:32095 [internal.py:handle_exit():78] Internal process exited
wandb/run-20210709_122021-2porvgvv/logs/debug.log ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2021-07-09 12:20:21,344 INFO MainThread:31038 [wandb_setup.py:_flush():69] Unhandled environment var: WANDB_WATCH
2
+ 2021-07-09 12:20:21,344 INFO MainThread:31038 [wandb_setup.py:_flush():69] setting env: {'project': 'hf-flax-robert-base-mr', 'entity': 'nipunsadvilkar'}
3
+ 2021-07-09 12:20:21,344 INFO MainThread:31038 [wandb_setup.py:_flush():69] setting login settings: {}
4
+ 2021-07-09 12:20:21,344 INFO MainThread:31038 [wandb_init.py:_log_setup():337] Logging user logs to /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_122021-2porvgvv/logs/debug.log
5
+ 2021-07-09 12:20:21,344 INFO MainThread:31038 [wandb_init.py:_log_setup():338] Logging internal logs to /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_122021-2porvgvv/logs/debug-internal.log
6
+ 2021-07-09 12:20:21,344 INFO MainThread:31038 [wandb_init.py:init():370] calling init triggers
7
+ 2021-07-09 12:20:21,344 INFO MainThread:31038 [wandb_init.py:init():375] wandb.init called with sweep_config: {}
8
+ config: {}
9
+ 2021-07-09 12:20:21,344 INFO MainThread:31038 [wandb_init.py:init():419] starting backend
10
+ 2021-07-09 12:20:21,344 INFO MainThread:31038 [backend.py:_multiprocessing_setup():70] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
11
+ 2021-07-09 12:20:21,378 INFO MainThread:31038 [backend.py:ensure_launched():135] starting backend process...
12
+ 2021-07-09 12:20:21,411 INFO MainThread:31038 [backend.py:ensure_launched():139] started backend process with pid: 32095
13
+ 2021-07-09 12:20:21,413 INFO MainThread:31038 [wandb_init.py:init():424] backend started and connected
14
+ 2021-07-09 12:20:21,416 INFO MainThread:31038 [wandb_init.py:init():472] updated telemetry
15
+ 2021-07-09 12:20:21,417 INFO MainThread:31038 [wandb_init.py:init():491] communicating current version
16
+ 2021-07-09 12:20:22,044 INFO MainThread:31038 [wandb_init.py:init():496] got version response
17
+ 2021-07-09 12:20:22,044 INFO MainThread:31038 [wandb_init.py:init():504] communicating run to backend with 30 second timeout
18
+ 2021-07-09 12:20:22,114 INFO MainThread:31038 [wandb_init.py:init():529] starting run threads in backend
19
+ 2021-07-09 12:20:22,173 INFO MainThread:31038 [wandb_run.py:_console_start():1623] atexit reg
20
+ 2021-07-09 12:20:22,174 INFO MainThread:31038 [wandb_run.py:_redirect():1497] redirect: SettingsConsole.REDIRECT
21
+ 2021-07-09 12:20:22,174 INFO MainThread:31038 [wandb_run.py:_redirect():1502] Redirecting console.
22
+ 2021-07-09 12:20:22,176 INFO MainThread:31038 [wandb_run.py:_redirect():1558] Redirects installed.
23
+ 2021-07-09 12:20:22,177 INFO MainThread:31038 [wandb_init.py:init():554] run started, returning control to user process
24
+ 2021-07-09 12:20:22,178 INFO MainThread:31038 [wandb_run.py:_config_callback():872] config_cb None None {'output_dir': './', 'overwrite_output_dir': True, 'do_train': False, 'do_eval': False, 'do_predict': False, 'evaluation_strategy': 'IntervalStrategy.NO', 'prediction_loss_only': False, 'per_device_train_batch_size': 4, 'per_device_eval_batch_size': 4, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'learning_rate': 0.0003, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 8.0, 'max_steps': -1, 'lr_scheduler_type': 'SchedulerType.LINEAR', 'warmup_ratio': 0.0, 'warmup_steps': 1000, 'log_level': -1, 'log_level_replica': -1, 'log_on_each_node': True, 'logging_dir': './runs/Jul09_12-20-15_t1v-n-112df4a9-w-0', 'logging_strategy': 'IntervalStrategy.STEPS', 'logging_first_step': False, 'logging_steps': 500, 'save_strategy': 'IntervalStrategy.STEPS', 'save_steps': 500, 'save_total_limit': None, 'save_on_each_node': False, 'no_cuda': False, 'seed': 42, 'fp16': False, 'fp16_opt_level': 'O1', 'fp16_backend': 'auto', 'fp16_full_eval': False, 'local_rank': -1, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': 500, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': './', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'sharded_ddp': [], 'deepspeed': None, 'label_smoothing_factor': 0.0, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'dataloader_pin_memory': True, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': False, 'resume_from_checkpoint': None, 'push_to_hub_model_id': '', 'push_to_hub_organization': None, 'push_to_hub_token': None, 'mp_parameters': ''}
25
+ 2021-07-09 12:20:22,179 INFO MainThread:31038 [wandb_run.py:_config_callback():872] config_cb None None {'model_name_or_path': None, 'model_type': 'roberta', 'config_name': './', 'tokenizer_name': './', 'cache_dir': None, 'use_fast_tokenizer': True, 'dtype': 'float32'}
26
+ 2021-07-09 12:20:22,179 INFO MainThread:31038 [wandb_run.py:_config_callback():872] config_cb None None {'dataset_name': 'oscar', 'dataset_config_name': 'unshuffled_deduplicated_als', 'train_file': None, 'validation_file': None, 'train_ref_file': None, 'validation_ref_file': None, 'overwrite_cache': False, 'validation_split_percentage': 5, 'max_seq_length': 128, 'preprocessing_num_workers': None, 'mlm_probability': 0.15, 'pad_to_max_length': False, 'line_by_line': False}
27
+ 2021-07-09 12:21:58,359 INFO MainThread:31038 [wandb_run.py:_atexit_cleanup():1593] got exitcode: 1
28
+ 2021-07-09 12:21:58,359 INFO MainThread:31038 [wandb_run.py:_restore():1565] restore
29
+ 2021-07-09 12:22:00,556 INFO MainThread:31038 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
30
+ wandb_count: 1
31
+ }
32
+ pusher_stats {
33
+ uploaded_bytes: 1200
34
+ total_bytes: 1200
35
+ }
36
+
37
+ 2021-07-09 12:22:01,162 INFO MainThread:31038 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
38
+ wandb_count: 4
39
+ }
40
+ pusher_stats {
41
+ uploaded_bytes: 1200
42
+ total_bytes: 9461
43
+ }
44
+
45
+ 2021-07-09 12:22:01,264 INFO MainThread:31038 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
46
+ wandb_count: 5
47
+ }
48
+ pusher_stats {
49
+ uploaded_bytes: 9463
50
+ total_bytes: 9463
51
+ }
52
+
53
+ 2021-07-09 12:22:01,366 INFO MainThread:31038 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
54
+ wandb_count: 5
55
+ }
56
+ pusher_stats {
57
+ uploaded_bytes: 9463
58
+ total_bytes: 9463
59
+ }
60
+
61
+ 2021-07-09 12:22:01,469 INFO MainThread:31038 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
62
+ wandb_count: 5
63
+ }
64
+ pusher_stats {
65
+ uploaded_bytes: 9463
66
+ total_bytes: 9463
67
+ }
68
+
69
+ 2021-07-09 12:22:01,570 INFO MainThread:31038 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
70
+ wandb_count: 5
71
+ }
72
+ pusher_stats {
73
+ uploaded_bytes: 9463
74
+ total_bytes: 9463
75
+ }
76
+
77
+ 2021-07-09 12:22:01,672 INFO MainThread:31038 [wandb_run.py:_wait_for_finish():1715] got exit ret: done: true
78
+ exit_result {
79
+ }
80
+ file_counts {
81
+ wandb_count: 5
82
+ }
83
+ pusher_stats {
84
+ uploaded_bytes: 9463
85
+ total_bytes: 9463
86
+ }
87
+
88
+ 2021-07-09 12:22:02,789 INFO MainThread:31038 [wandb_run.py:_show_files():1937] logging synced files
wandb/run-20210709_122021-2porvgvv/run-2porvgvv.wandb ADDED
Binary file (9.24 kB). View file
 
wandb/run-20210709_122709-2pc90wcd/files/config.yaml ADDED
@@ -0,0 +1,303 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ wandb_version: 1
2
+
3
+ _wandb:
4
+ desc: null
5
+ value:
6
+ cli_version: 0.10.33
7
+ framework: huggingface
8
+ huggingface_version: 4.9.0.dev0
9
+ is_jupyter_run: false
10
+ is_kaggle_kernel: false
11
+ python_version: 3.8.10
12
+ t:
13
+ 1:
14
+ - 11
15
+ 4: 3.8.10
16
+ 5: 0.10.33
17
+ 6: 4.9.0.dev0
18
+ 8:
19
+ - 5
20
+ adafactor:
21
+ desc: null
22
+ value: false
23
+ adam_beta1:
24
+ desc: null
25
+ value: 0.9
26
+ adam_beta2:
27
+ desc: null
28
+ value: 0.999
29
+ adam_epsilon:
30
+ desc: null
31
+ value: 1.0e-08
32
+ cache_dir:
33
+ desc: null
34
+ value: null
35
+ config_name:
36
+ desc: null
37
+ value: ./
38
+ dataloader_drop_last:
39
+ desc: null
40
+ value: false
41
+ dataloader_num_workers:
42
+ desc: null
43
+ value: 0
44
+ dataloader_pin_memory:
45
+ desc: null
46
+ value: true
47
+ dataset_config_name:
48
+ desc: null
49
+ value: unshuffled_deduplicated_als
50
+ dataset_name:
51
+ desc: null
52
+ value: oscar
53
+ ddp_find_unused_parameters:
54
+ desc: null
55
+ value: null
56
+ debug:
57
+ desc: null
58
+ value: []
59
+ deepspeed:
60
+ desc: null
61
+ value: null
62
+ disable_tqdm:
63
+ desc: null
64
+ value: false
65
+ do_eval:
66
+ desc: null
67
+ value: false
68
+ do_predict:
69
+ desc: null
70
+ value: false
71
+ do_train:
72
+ desc: null
73
+ value: false
74
+ dtype:
75
+ desc: null
76
+ value: float32
77
+ eval_accumulation_steps:
78
+ desc: null
79
+ value: null
80
+ eval_steps:
81
+ desc: null
82
+ value: 500
83
+ evaluation_strategy:
84
+ desc: null
85
+ value: IntervalStrategy.NO
86
+ fp16:
87
+ desc: null
88
+ value: false
89
+ fp16_backend:
90
+ desc: null
91
+ value: auto
92
+ fp16_full_eval:
93
+ desc: null
94
+ value: false
95
+ fp16_opt_level:
96
+ desc: null
97
+ value: O1
98
+ gradient_accumulation_steps:
99
+ desc: null
100
+ value: 1
101
+ greater_is_better:
102
+ desc: null
103
+ value: null
104
+ group_by_length:
105
+ desc: null
106
+ value: false
107
+ ignore_data_skip:
108
+ desc: null
109
+ value: false
110
+ label_names:
111
+ desc: null
112
+ value: null
113
+ label_smoothing_factor:
114
+ desc: null
115
+ value: 0.0
116
+ learning_rate:
117
+ desc: null
118
+ value: 0.0003
119
+ length_column_name:
120
+ desc: null
121
+ value: length
122
+ line_by_line:
123
+ desc: null
124
+ value: false
125
+ load_best_model_at_end:
126
+ desc: null
127
+ value: false
128
+ local_rank:
129
+ desc: null
130
+ value: -1
131
+ log_level:
132
+ desc: null
133
+ value: -1
134
+ log_level_replica:
135
+ desc: null
136
+ value: -1
137
+ log_on_each_node:
138
+ desc: null
139
+ value: true
140
+ logging_dir:
141
+ desc: null
142
+ value: ./runs/Jul09_12-27-03_t1v-n-112df4a9-w-0
143
+ logging_first_step:
144
+ desc: null
145
+ value: false
146
+ logging_steps:
147
+ desc: null
148
+ value: 500
149
+ logging_strategy:
150
+ desc: null
151
+ value: IntervalStrategy.STEPS
152
+ lr_scheduler_type:
153
+ desc: null
154
+ value: SchedulerType.LINEAR
155
+ max_grad_norm:
156
+ desc: null
157
+ value: 1.0
158
+ max_seq_length:
159
+ desc: null
160
+ value: 128
161
+ max_steps:
162
+ desc: null
163
+ value: -1
164
+ metric_for_best_model:
165
+ desc: null
166
+ value: null
167
+ mlm_probability:
168
+ desc: null
169
+ value: 0.15
170
+ model_name_or_path:
171
+ desc: null
172
+ value: null
173
+ model_type:
174
+ desc: null
175
+ value: roberta
176
+ mp_parameters:
177
+ desc: null
178
+ value: ''
179
+ no_cuda:
180
+ desc: null
181
+ value: false
182
+ num_train_epochs:
183
+ desc: null
184
+ value: 8.0
185
+ output_dir:
186
+ desc: null
187
+ value: ./
188
+ overwrite_cache:
189
+ desc: null
190
+ value: false
191
+ overwrite_output_dir:
192
+ desc: null
193
+ value: true
194
+ pad_to_max_length:
195
+ desc: null
196
+ value: false
197
+ past_index:
198
+ desc: null
199
+ value: -1
200
+ per_device_eval_batch_size:
201
+ desc: null
202
+ value: 4
203
+ per_device_train_batch_size:
204
+ desc: null
205
+ value: 4
206
+ per_gpu_eval_batch_size:
207
+ desc: null
208
+ value: null
209
+ per_gpu_train_batch_size:
210
+ desc: null
211
+ value: null
212
+ prediction_loss_only:
213
+ desc: null
214
+ value: false
215
+ preprocessing_num_workers:
216
+ desc: null
217
+ value: null
218
+ push_to_hub:
219
+ desc: null
220
+ value: false
221
+ push_to_hub_model_id:
222
+ desc: null
223
+ value: ''
224
+ push_to_hub_organization:
225
+ desc: null
226
+ value: null
227
+ push_to_hub_token:
228
+ desc: null
229
+ value: null
230
+ remove_unused_columns:
231
+ desc: null
232
+ value: true
233
+ report_to:
234
+ desc: null
235
+ value:
236
+ - tensorboard
237
+ - wandb
238
+ resume_from_checkpoint:
239
+ desc: null
240
+ value: null
241
+ run_name:
242
+ desc: null
243
+ value: ./
244
+ save_on_each_node:
245
+ desc: null
246
+ value: false
247
+ save_steps:
248
+ desc: null
249
+ value: 500
250
+ save_strategy:
251
+ desc: null
252
+ value: IntervalStrategy.STEPS
253
+ save_total_limit:
254
+ desc: null
255
+ value: null
256
+ seed:
257
+ desc: null
258
+ value: 42
259
+ sharded_ddp:
260
+ desc: null
261
+ value: []
262
+ skip_memory_metrics:
263
+ desc: null
264
+ value: true
265
+ tokenizer_name:
266
+ desc: null
267
+ value: ./
268
+ tpu_metrics_debug:
269
+ desc: null
270
+ value: false
271
+ tpu_num_cores:
272
+ desc: null
273
+ value: null
274
+ train_file:
275
+ desc: null
276
+ value: null
277
+ train_ref_file:
278
+ desc: null
279
+ value: null
280
+ use_fast_tokenizer:
281
+ desc: null
282
+ value: true
283
+ use_legacy_prediction_loop:
284
+ desc: null
285
+ value: false
286
+ validation_file:
287
+ desc: null
288
+ value: null
289
+ validation_ref_file:
290
+ desc: null
291
+ value: null
292
+ validation_split_percentage:
293
+ desc: null
294
+ value: 5
295
+ warmup_ratio:
296
+ desc: null
297
+ value: 0.0
298
+ warmup_steps:
299
+ desc: null
300
+ value: 1000
301
+ weight_decay:
302
+ desc: null
303
+ value: 0.0
wandb/run-20210709_122709-2pc90wcd/files/output.log ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ /home/nipunsadvilkar/roberta_mr_env/lib/python3.8/site-packages/jax/lib/xla_bridge.py:382: UserWarning: jax.host_count has been renamed to jax.process_count. This alias will eventually be removed; please update your code.
2
+ warnings.warn(
3
+ /home/nipunsadvilkar/roberta_mr_env/lib/python3.8/site-packages/jax/lib/xla_bridge.py:369: UserWarning: jax.host_id has been renamed to jax.process_index. This alias will eventually be removed; please update your code.
4
+ warnings.warn(
5
+ Epoch ... (1/8): 0%| | 0/8 [00:00<?, ?it/s]
6
+
7
+
8
+ Epoch ... (1/8): 12%|███████████████████ | 1/8 [01:15<08:49, 75.59s/it]
9
+
10
+
11
+ Epoch ... (1/8): 25%|██████████████████████████████████████ | 2/8 [01:20<03:23, 33.95s/it]
12
+
13
+ Epoch ... (1/8): 38%|█████████████████████████████████████████████████████████ | 3/8 [01:25<01:43, 20.77s/it]
14
+
15
+ Training...: 51%|█████████████████████████████████████████████████████████████████████████████▌ | 72/142 [00:02<00:01, 35.13it/s]
16
+ Step... (500 | Loss: 8.018753051757812, Learning Rate: 0.0001500000071246177)
17
+
18
+ Step... (500 | Loss: 8.205772399902344, Acc: 0.0773010179400444): 38%|██████████████████████████████████████▋ | 3/8 [01:33<02:35, 31.10s/it]
wandb/run-20210709_122709-2pc90wcd/files/requirements.txt ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ absl-py==0.13.0
2
+ aiohttp==3.7.4.post0
3
+ async-timeout==3.0.1
4
+ attrs==21.2.0
5
+ backcall==0.2.0
6
+ cachetools==4.2.2
7
+ certifi==2021.5.30
8
+ chardet==4.0.0
9
+ chex==0.0.8
10
+ click==8.0.1
11
+ configparser==5.0.2
12
+ cycler==0.10.0
13
+ datasets==1.9.1.dev0
14
+ decorator==5.0.9
15
+ dill==0.3.4
16
+ dm-tree==0.1.6
17
+ docker-pycreds==0.4.0
18
+ filelock==3.0.12
19
+ flatbuffers==2.0
20
+ flax==0.3.4
21
+ fsspec==2021.6.1
22
+ gitdb==4.0.7
23
+ gitpython==3.1.18
24
+ google-auth-oauthlib==0.4.4
25
+ google-auth==1.32.1
26
+ grpcio==1.38.1
27
+ huggingface-hub==0.0.12
28
+ idna==2.10
29
+ ipython-genutils==0.2.0
30
+ ipython==7.25.0
31
+ jax==0.2.16
32
+ jaxlib==0.1.68
33
+ jedi==0.18.0
34
+ joblib==1.0.1
35
+ kiwisolver==1.3.1
36
+ libtpu-nightly==0.1.dev20210615
37
+ markdown==3.3.4
38
+ matplotlib-inline==0.1.2
39
+ matplotlib==3.4.2
40
+ msgpack==1.0.2
41
+ multidict==5.1.0
42
+ multiprocess==0.70.12.2
43
+ numpy==1.21.0
44
+ oauthlib==3.1.1
45
+ opt-einsum==3.3.0
46
+ optax==0.0.9
47
+ packaging==21.0
48
+ pandas==1.3.0
49
+ parso==0.8.2
50
+ pathtools==0.1.2
51
+ pexpect==4.8.0
52
+ pickleshare==0.7.5
53
+ pillow==8.3.1
54
+ pip==20.0.2
55
+ pkg-resources==0.0.0
56
+ promise==2.3
57
+ prompt-toolkit==3.0.19
58
+ protobuf==3.17.3
59
+ psutil==5.8.0
60
+ ptyprocess==0.7.0
61
+ pyarrow==4.0.1
62
+ pyasn1-modules==0.2.8
63
+ pyasn1==0.4.8
64
+ pygments==2.9.0
65
+ pyparsing==2.4.7
66
+ python-dateutil==2.8.1
67
+ pytz==2021.1
68
+ pyyaml==5.4.1
69
+ regex==2021.7.6
70
+ requests-oauthlib==1.3.0
71
+ requests==2.25.1
72
+ rsa==4.7.2
73
+ sacremoses==0.0.45
74
+ scipy==1.7.0
75
+ sentry-sdk==1.3.0
76
+ setuptools==44.0.0
77
+ shortuuid==1.0.1
78
+ six==1.16.0
79
+ smmap==4.0.0
80
+ subprocess32==3.5.4
81
+ tensorboard-data-server==0.6.1
82
+ tensorboard-plugin-wit==1.8.0
83
+ tensorboard==2.5.0
84
+ tokenizers==0.10.3
85
+ toolz==0.11.1
86
+ tqdm==4.61.2
87
+ traitlets==5.0.5
88
+ transformers==4.9.0.dev0
89
+ typing-extensions==3.10.0.0
90
+ urllib3==1.26.6
91
+ wandb==0.10.33
92
+ wcwidth==0.2.5
93
+ werkzeug==2.0.1
94
+ wheel==0.36.2
95
+ xxhash==2.0.2
96
+ yarl==1.6.3
wandb/run-20210709_122709-2pc90wcd/files/wandb-metadata.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "os": "Linux-5.4.0-1043-gcp-x86_64-with-glibc2.29",
3
+ "python": "3.8.10",
4
+ "heartbeatAt": "2021-07-09T12:27:09.785328",
5
+ "startedAt": "2021-07-09T12:27:09.051375",
6
+ "docker": null,
7
+ "cpu_count": 96,
8
+ "cuda": null,
9
+ "args": [
10
+ "--output_dir=./",
11
+ "--model_type=roberta",
12
+ "--config_name=./",
13
+ "--tokenizer_name=./",
14
+ "--dataset_name=oscar",
15
+ "--dataset_config_name=unshuffled_deduplicated_als",
16
+ "--max_seq_length=128",
17
+ "--per_device_train_batch_size=4",
18
+ "--per_device_eval_batch_size=4",
19
+ "--learning_rate=3e-4",
20
+ "--warmup_steps=1000",
21
+ "--overwrite_output_dir",
22
+ "--num_train_epochs=8"
23
+ ],
24
+ "state": "running",
25
+ "program": "run_mlm_flax.py",
26
+ "codePath": "run_mlm_flax.py",
27
+ "git": {
28
+ "remote": "https://huggingface.co/flax-community/roberta-base-mr",
29
+ "commit": "faa64e8a79301832a56c78b2b293675039070bb0"
30
+ },
31
+ "email": "nipunsadvilkar@gmail.com",
32
+ "root": "/home/nipunsadvilkar/sample/roberta-base-mr",
33
+ "host": "t1v-n-112df4a9-w-0",
34
+ "username": "nipunsadvilkar",
35
+ "executable": "/home/nipunsadvilkar/roberta_mr_env/bin/python"
36
+ }
wandb/run-20210709_122709-2pc90wcd/files/wandb-summary.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"train_time": 3.0330424308776855, "_runtime": 99, "_timestamp": 1625833728, "_step": 303, "training_learning_rate": {"_type": "histogram", "values": [3, 2, 2, 3, 2, 2, 3, 2, 2, 3, 2, 2, 3, 2, 2, 2, 3, 2, 2, 3, 2, 2, 3, 2, 2, 3, 2, 2, 3, 2, 2, 3], "bins": [0.00012780001270584762, 0.00012849376071244478, 0.00012918750871904194, 0.0001298812567256391, 0.00013057500473223627, 0.00013126876729074866, 0.00013196251529734582, 0.00013265626330394298, 0.00013335001131054014, 0.0001340437593171373, 0.00013473750732373446, 0.00013543125533033162, 0.000136125017888844, 0.00013681876589544117, 0.00013751251390203834, 0.0001382062619086355, 0.00013890000991523266, 0.00013959375792182982, 0.00014028750592842698, 0.00014098125393502414, 0.0001416750019416213, 0.0001423687645001337, 0.00014306251250673085, 0.00014375626051332802, 0.00014445000851992518, 0.00014514375652652234, 0.0001458375045331195, 0.00014653125253971666, 0.00014722501509822905, 0.0001479187631048262, 0.00014861251111142337, 0.00014930625911802053, 0.0001500000071246177]}, "train_step": 500, "train_learning_rate": 0.0001500000071246177, "training_loss": {"_type": "histogram", "values": [1, 0, 1, 2, 2, 1, 2, 2, 2, 6, 3, 2, 2, 2, 6, 2, 3, 3, 0, 3, 5, 3, 3, 2, 2, 3, 1, 1, 1, 2, 5, 2], "bins": [7.636768341064453, 7.65283203125, 7.668895721435547, 7.684959411621094, 7.701023101806641, 7.7170867919921875, 7.733150482177734, 7.749214172363281, 7.765277862548828, 7.781341552734375, 7.797405242919922, 7.813468933105469, 7.829532623291016, 7.8455963134765625, 7.861660003662109, 7.877723693847656, 7.893787384033203, 7.90985107421875, 7.925914764404297, 7.941978454589844, 7.958042144775391, 7.9741058349609375, 7.990169525146484, 8.006233215332031, 8.022296905517578, 8.038360595703125, 8.054424285888672, 8.070487976074219, 8.086551666259766, 8.102615356445312, 8.11867904663086, 8.134742736816406, 8.150806427001953]}, "train_loss": 8.018753051757812, "eval_step": 426}
wandb/run-20210709_122709-2pc90wcd/logs/debug-internal.log ADDED
The diff for this file is too large to render. See raw diff
 
wandb/run-20210709_122709-2pc90wcd/logs/debug.log ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2021-07-09 12:27:09,053 INFO MainThread:32339 [wandb_setup.py:_flush():69] Unhandled environment var: WANDB_WATCH
2
+ 2021-07-09 12:27:09,053 INFO MainThread:32339 [wandb_setup.py:_flush():69] setting env: {'project': 'hf-flax-robert-base-mr', 'entity': 'nipunsadvilkar'}
3
+ 2021-07-09 12:27:09,053 INFO MainThread:32339 [wandb_setup.py:_flush():69] setting login settings: {}
4
+ 2021-07-09 12:27:09,053 INFO MainThread:32339 [wandb_init.py:_log_setup():337] Logging user logs to /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_122709-2pc90wcd/logs/debug.log
5
+ 2021-07-09 12:27:09,053 INFO MainThread:32339 [wandb_init.py:_log_setup():338] Logging internal logs to /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_122709-2pc90wcd/logs/debug-internal.log
6
+ 2021-07-09 12:27:09,053 INFO MainThread:32339 [wandb_init.py:init():370] calling init triggers
7
+ 2021-07-09 12:27:09,053 INFO MainThread:32339 [wandb_init.py:init():375] wandb.init called with sweep_config: {}
8
+ config: {}
9
+ 2021-07-09 12:27:09,053 INFO MainThread:32339 [wandb_init.py:init():419] starting backend
10
+ 2021-07-09 12:27:09,053 INFO MainThread:32339 [backend.py:_multiprocessing_setup():70] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
11
+ 2021-07-09 12:27:09,087 INFO MainThread:32339 [backend.py:ensure_launched():135] starting backend process...
12
+ 2021-07-09 12:27:09,119 INFO MainThread:32339 [backend.py:ensure_launched():139] started backend process with pid: 33395
13
+ 2021-07-09 12:27:09,122 INFO MainThread:32339 [wandb_init.py:init():424] backend started and connected
14
+ 2021-07-09 12:27:09,124 INFO MainThread:32339 [wandb_init.py:init():472] updated telemetry
15
+ 2021-07-09 12:27:09,125 INFO MainThread:32339 [wandb_init.py:init():491] communicating current version
16
+ 2021-07-09 12:27:09,709 INFO MainThread:32339 [wandb_init.py:init():496] got version response
17
+ 2021-07-09 12:27:09,709 INFO MainThread:32339 [wandb_init.py:init():504] communicating run to backend with 30 second timeout
18
+ 2021-07-09 12:27:09,783 INFO MainThread:32339 [wandb_init.py:init():529] starting run threads in backend
19
+ 2021-07-09 12:27:09,838 INFO MainThread:32339 [wandb_run.py:_console_start():1623] atexit reg
20
+ 2021-07-09 12:27:09,839 INFO MainThread:32339 [wandb_run.py:_redirect():1497] redirect: SettingsConsole.REDIRECT
21
+ 2021-07-09 12:27:09,839 INFO MainThread:32339 [wandb_run.py:_redirect():1502] Redirecting console.
22
+ 2021-07-09 12:27:09,841 INFO MainThread:32339 [wandb_run.py:_redirect():1558] Redirects installed.
23
+ 2021-07-09 12:27:09,841 INFO MainThread:32339 [wandb_init.py:init():554] run started, returning control to user process
24
+ 2021-07-09 12:27:09,842 INFO MainThread:32339 [wandb_run.py:_config_callback():872] config_cb None None {'output_dir': './', 'overwrite_output_dir': True, 'do_train': False, 'do_eval': False, 'do_predict': False, 'evaluation_strategy': 'IntervalStrategy.NO', 'prediction_loss_only': False, 'per_device_train_batch_size': 4, 'per_device_eval_batch_size': 4, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'learning_rate': 0.0003, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 8.0, 'max_steps': -1, 'lr_scheduler_type': 'SchedulerType.LINEAR', 'warmup_ratio': 0.0, 'warmup_steps': 1000, 'log_level': -1, 'log_level_replica': -1, 'log_on_each_node': True, 'logging_dir': './runs/Jul09_12-27-03_t1v-n-112df4a9-w-0', 'logging_strategy': 'IntervalStrategy.STEPS', 'logging_first_step': False, 'logging_steps': 500, 'save_strategy': 'IntervalStrategy.STEPS', 'save_steps': 500, 'save_total_limit': None, 'save_on_each_node': False, 'no_cuda': False, 'seed': 42, 'fp16': False, 'fp16_opt_level': 'O1', 'fp16_backend': 'auto', 'fp16_full_eval': False, 'local_rank': -1, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': 500, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': './', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'sharded_ddp': [], 'deepspeed': None, 'label_smoothing_factor': 0.0, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'dataloader_pin_memory': True, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': False, 'resume_from_checkpoint': None, 'push_to_hub_model_id': '', 'push_to_hub_organization': None, 'push_to_hub_token': None, 'mp_parameters': ''}
25
+ 2021-07-09 12:27:09,843 INFO MainThread:32339 [wandb_run.py:_config_callback():872] config_cb None None {'model_name_or_path': None, 'model_type': 'roberta', 'config_name': './', 'tokenizer_name': './', 'cache_dir': None, 'use_fast_tokenizer': True, 'dtype': 'float32'}
26
+ 2021-07-09 12:27:09,844 INFO MainThread:32339 [wandb_run.py:_config_callback():872] config_cb None None {'dataset_name': 'oscar', 'dataset_config_name': 'unshuffled_deduplicated_als', 'train_file': None, 'validation_file': None, 'train_ref_file': None, 'validation_ref_file': None, 'overwrite_cache': False, 'validation_split_percentage': 5, 'max_seq_length': 128, 'preprocessing_num_workers': None, 'mlm_probability': 0.15, 'pad_to_max_length': False, 'line_by_line': False}
27
+ 2021-07-09 12:28:48,239 INFO MainThread:32339 [wandb_run.py:_atexit_cleanup():1593] got exitcode: 1
28
+ 2021-07-09 12:28:48,240 INFO MainThread:32339 [wandb_run.py:_restore():1565] restore
29
+ 2021-07-09 12:28:52,518 ERROR MainThread:32339 [wandb_run.py:_atexit_cleanup():1611] Problem finishing run
30
+ Traceback (most recent call last):
31
+ File "/home/nipunsadvilkar/roberta_mr_env/lib/python3.8/site-packages/wandb/sdk/wandb_run.py", line 1601, in _atexit_cleanup
32
+ self._on_finish()
33
+ File "/home/nipunsadvilkar/roberta_mr_env/lib/python3.8/site-packages/wandb/sdk/wandb_run.py", line 1737, in _on_finish
34
+ self.history._flush()
35
+ File "/home/nipunsadvilkar/roberta_mr_env/lib/python3.8/site-packages/wandb/sdk/wandb_history.py", line 59, in _flush
36
+ self._callback(row=self._data, step=self._step)
37
+ File "/home/nipunsadvilkar/roberta_mr_env/lib/python3.8/site-packages/wandb/sdk/wandb_run.py", line 931, in _history_callback
38
+ self._backend.interface.publish_history(
39
+ File "/home/nipunsadvilkar/roberta_mr_env/lib/python3.8/site-packages/wandb/sdk/interface/interface.py", line 231, in publish_history
40
+ item.value_json = json_dumps_safer_history(v) # type: ignore
41
+ File "/home/nipunsadvilkar/roberta_mr_env/lib/python3.8/site-packages/wandb/util.py", line 667, in json_dumps_safer_history
42
+ return json.dumps(obj, cls=WandBHistoryJSONEncoder, **kwargs)
43
+ File "/usr/lib/python3.8/json/__init__.py", line 234, in dumps
44
+ return cls(
45
+ File "/usr/lib/python3.8/json/encoder.py", line 199, in encode
46
+ chunks = self.iterencode(o, _one_shot=True)
47
+ File "/usr/lib/python3.8/json/encoder.py", line 257, in iterencode
48
+ return _iterencode(o, 0)
49
+ File "/home/nipunsadvilkar/roberta_mr_env/lib/python3.8/site-packages/wandb/util.py", line 634, in default
50
+ return json.JSONEncoder.default(self, obj)
51
+ File "/usr/lib/python3.8/json/encoder.py", line 179, in default
52
+ raise TypeError(f'Object of type {o.__class__.__name__} '
53
+ TypeError: Object of type DeviceArray is not JSON serializable
wandb/run-20210709_122709-2pc90wcd/run-2pc90wcd.wandb ADDED
Binary file (40.5 kB). View file
 
wandb/run-20210709_124353-3pjvcule/files/config.yaml ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ wandb_version: 1
2
+
3
+ _wandb:
4
+ desc: null
5
+ value:
6
+ cli_version: 0.10.33
7
+ framework: huggingface
8
+ huggingface_version: 4.9.0.dev0
9
+ is_jupyter_run: false
10
+ is_kaggle_kernel: false
11
+ python_version: 3.8.10
12
+ t:
13
+ 1:
14
+ - 11
15
+ 4: 3.8.10
16
+ 5: 0.10.33
17
+ 6: 4.9.0.dev0
18
+ 8:
19
+ - 5
wandb/run-20210709_124353-3pjvcule/files/output.log ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ /home/nipunsadvilkar/roberta_mr_env/lib/python3.8/site-packages/jax/lib/xla_bridge.py:382: UserWarning: jax.host_count has been renamed to jax.process_count. This alias will eventually be removed; please update your code.
2
+ warnings.warn(
3
+ /home/nipunsadvilkar/roberta_mr_env/lib/python3.8/site-packages/jax/lib/xla_bridge.py:369: UserWarning: jax.host_id has been renamed to jax.process_index. This alias will eventually be removed; please update your code.
4
+ warnings.warn(
5
+ Epoch ... (1/8): 0%| | 0/8 [00:00<?, ?it/s]
wandb/run-20210709_124353-3pjvcule/files/requirements.txt ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ absl-py==0.13.0
2
+ aiohttp==3.7.4.post0
3
+ async-timeout==3.0.1
4
+ attrs==21.2.0
5
+ backcall==0.2.0
6
+ cachetools==4.2.2
7
+ certifi==2021.5.30
8
+ chardet==4.0.0
9
+ chex==0.0.8
10
+ click==8.0.1
11
+ configparser==5.0.2
12
+ cycler==0.10.0
13
+ datasets==1.9.1.dev0
14
+ decorator==5.0.9
15
+ dill==0.3.4
16
+ dm-tree==0.1.6
17
+ docker-pycreds==0.4.0
18
+ filelock==3.0.12
19
+ flatbuffers==2.0
20
+ flax==0.3.4
21
+ fsspec==2021.6.1
22
+ gitdb==4.0.7
23
+ gitpython==3.1.18
24
+ google-auth-oauthlib==0.4.4
25
+ google-auth==1.32.1
26
+ grpcio==1.38.1
27
+ huggingface-hub==0.0.12
28
+ idna==2.10
29
+ ipython-genutils==0.2.0
30
+ ipython==7.25.0
31
+ jax==0.2.16
32
+ jaxlib==0.1.68
33
+ jedi==0.18.0
34
+ joblib==1.0.1
35
+ kiwisolver==1.3.1
36
+ libtpu-nightly==0.1.dev20210615
37
+ markdown==3.3.4
38
+ matplotlib-inline==0.1.2
39
+ matplotlib==3.4.2
40
+ msgpack==1.0.2
41
+ multidict==5.1.0
42
+ multiprocess==0.70.12.2
43
+ numpy==1.21.0
44
+ oauthlib==3.1.1
45
+ opt-einsum==3.3.0
46
+ optax==0.0.9
47
+ packaging==21.0
48
+ pandas==1.3.0
49
+ parso==0.8.2
50
+ pathtools==0.1.2
51
+ pexpect==4.8.0
52
+ pickleshare==0.7.5
53
+ pillow==8.3.1
54
+ pip==20.0.2
55
+ pkg-resources==0.0.0
56
+ promise==2.3
57
+ prompt-toolkit==3.0.19
58
+ protobuf==3.17.3
59
+ psutil==5.8.0
60
+ ptyprocess==0.7.0
61
+ pyarrow==4.0.1
62
+ pyasn1-modules==0.2.8
63
+ pyasn1==0.4.8
64
+ pygments==2.9.0
65
+ pyparsing==2.4.7
66
+ python-dateutil==2.8.1
67
+ pytz==2021.1
68
+ pyyaml==5.4.1
69
+ regex==2021.7.6
70
+ requests-oauthlib==1.3.0
71
+ requests==2.25.1
72
+ rsa==4.7.2
73
+ sacremoses==0.0.45
74
+ scipy==1.7.0
75
+ sentry-sdk==1.3.0
76
+ setuptools==44.0.0
77
+ shortuuid==1.0.1
78
+ six==1.16.0
79
+ smmap==4.0.0
80
+ subprocess32==3.5.4
81
+ tensorboard-data-server==0.6.1
82
+ tensorboard-plugin-wit==1.8.0
83
+ tensorboard==2.5.0
84
+ tokenizers==0.10.3
85
+ toolz==0.11.1
86
+ tqdm==4.61.2
87
+ traitlets==5.0.5
88
+ transformers==4.9.0.dev0
89
+ typing-extensions==3.10.0.0
90
+ urllib3==1.26.6
91
+ wandb==0.10.33
92
+ wcwidth==0.2.5
93
+ werkzeug==2.0.1
94
+ wheel==0.36.2
95
+ xxhash==2.0.2
96
+ yarl==1.6.3
wandb/run-20210709_124353-3pjvcule/files/wandb-metadata.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "os": "Linux-5.4.0-1043-gcp-x86_64-with-glibc2.29",
3
+ "python": "3.8.10",
4
+ "heartbeatAt": "2021-07-09T12:43:54.473948",
5
+ "startedAt": "2021-07-09T12:43:53.659249",
6
+ "docker": null,
7
+ "cpu_count": 96,
8
+ "cuda": null,
9
+ "args": [
10
+ "--output_dir=./",
11
+ "--model_type=roberta",
12
+ "--config_name=./",
13
+ "--tokenizer_name=./",
14
+ "--dataset_name=oscar",
15
+ "--dataset_config_name=unshuffled_deduplicated_als",
16
+ "--max_seq_length=128",
17
+ "--per_device_train_batch_size=4",
18
+ "--per_device_eval_batch_size=4",
19
+ "--learning_rate=3e-4",
20
+ "--warmup_steps=1000",
21
+ "--overwrite_output_dir",
22
+ "--num_train_epochs=8"
23
+ ],
24
+ "state": "running",
25
+ "program": "run_mlm_flax.py",
26
+ "codePath": "run_mlm_flax.py",
27
+ "git": {
28
+ "remote": "https://huggingface.co/flax-community/roberta-base-mr",
29
+ "commit": "faa64e8a79301832a56c78b2b293675039070bb0"
30
+ },
31
+ "email": "nipunsadvilkar@gmail.com",
32
+ "root": "/home/nipunsadvilkar/sample/roberta-base-mr",
33
+ "host": "t1v-n-112df4a9-w-0",
34
+ "username": "nipunsadvilkar",
35
+ "executable": "/home/nipunsadvilkar/roberta_mr_env/bin/python"
36
+ }
wandb/run-20210709_124353-3pjvcule/files/wandb-summary.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {}
wandb/run-20210709_124353-3pjvcule/logs/debug-internal.log ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2021-07-09 12:43:54,336 INFO MainThread:34715 [internal.py:wandb_internal():88] W&B internal server running at pid: 34715, started at: 2021-07-09 12:43:54.336084
2
+ 2021-07-09 12:43:54,338 DEBUG HandlerThread:34715 [handler.py:handle_request():124] handle_request: check_version
3
+ 2021-07-09 12:43:54,339 INFO WriterThread:34715 [datastore.py:open_for_write():80] open: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_124353-3pjvcule/run-3pjvcule.wandb
4
+ 2021-07-09 12:43:54,340 DEBUG SenderThread:34715 [sender.py:send():179] send: header
5
+ 2021-07-09 12:43:54,340 DEBUG SenderThread:34715 [sender.py:send_request():193] send_request: check_version
6
+ 2021-07-09 12:43:54,404 DEBUG SenderThread:34715 [sender.py:send():179] send: run
7
+ 2021-07-09 12:43:54,471 INFO SenderThread:34715 [dir_watcher.py:__init__():168] watching files in: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_124353-3pjvcule/files
8
+ 2021-07-09 12:43:54,471 INFO SenderThread:34715 [sender.py:_start_run_threads():716] run started: 3pjvcule with start time 1625834633
9
+ 2021-07-09 12:43:54,471 DEBUG SenderThread:34715 [sender.py:send():179] send: summary
10
+ 2021-07-09 12:43:54,472 INFO SenderThread:34715 [sender.py:_save_file():841] saving file wandb-summary.json with policy end
11
+ 2021-07-09 12:43:54,472 DEBUG HandlerThread:34715 [handler.py:handle_request():124] handle_request: run_start
12
+ 2021-07-09 12:43:54,473 DEBUG HandlerThread:34715 [meta.py:__init__():39] meta init
13
+ 2021-07-09 12:43:54,473 DEBUG HandlerThread:34715 [meta.py:__init__():53] meta init done
14
+ 2021-07-09 12:43:54,473 DEBUG HandlerThread:34715 [meta.py:probe():210] probe
15
+ 2021-07-09 12:43:54,474 DEBUG HandlerThread:34715 [meta.py:_setup_git():200] setup git
16
+ 2021-07-09 12:43:54,494 DEBUG HandlerThread:34715 [meta.py:_setup_git():207] setup git done
17
+ 2021-07-09 12:43:54,494 DEBUG HandlerThread:34715 [meta.py:_save_pip():57] save pip
18
+ 2021-07-09 12:43:54,494 DEBUG HandlerThread:34715 [meta.py:_save_pip():71] save pip done
19
+ 2021-07-09 12:43:54,495 DEBUG HandlerThread:34715 [meta.py:probe():252] probe done
20
+ 2021-07-09 12:43:54,526 DEBUG SenderThread:34715 [sender.py:send():179] send: files
21
+ 2021-07-09 12:43:54,526 INFO SenderThread:34715 [sender.py:_save_file():841] saving file wandb-metadata.json with policy now
22
+ 2021-07-09 12:43:54,531 DEBUG HandlerThread:34715 [handler.py:handle_request():124] handle_request: stop_status
23
+ 2021-07-09 12:43:54,532 DEBUG SenderThread:34715 [sender.py:send_request():193] send_request: stop_status
24
+ 2021-07-09 12:43:54,558 DEBUG SenderThread:34715 [sender.py:send():179] send: config
25
+ 2021-07-09 12:43:54,559 DEBUG SenderThread:34715 [sender.py:send():179] send: config
26
+ 2021-07-09 12:43:54,559 DEBUG SenderThread:34715 [sender.py:send():179] send: config
27
+ 2021-07-09 12:43:54,734 INFO Thread-11 :34715 [upload_job.py:push():137] Uploaded file /tmp/tmp3gqpckyvwandb/1ct7grlp-wandb-metadata.json
28
+ 2021-07-09 12:43:55,472 INFO Thread-8 :34715 [dir_watcher.py:_on_file_created():216] file/dir created: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_124353-3pjvcule/files/requirements.txt
29
+ 2021-07-09 12:43:55,473 INFO Thread-8 :34715 [dir_watcher.py:_on_file_created():216] file/dir created: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_124353-3pjvcule/files/wandb-summary.json
30
+ 2021-07-09 12:43:55,473 INFO Thread-8 :34715 [dir_watcher.py:_on_file_created():216] file/dir created: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_124353-3pjvcule/files/wandb-metadata.json
31
+ 2021-07-09 12:43:55,473 INFO Thread-8 :34715 [dir_watcher.py:_on_file_created():216] file/dir created: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_124353-3pjvcule/files/output.log
32
+ 2021-07-09 12:44:01,474 INFO Thread-8 :34715 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_124353-3pjvcule/files/output.log
33
+ 2021-07-09 12:44:03,475 INFO Thread-8 :34715 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_124353-3pjvcule/files/output.log
34
+ 2021-07-09 12:44:09,435 WARNING MainThread:34715 [internal.py:wandb_internal():147] Internal process interrupt: 1
35
+ 2021-07-09 12:44:09,561 DEBUG HandlerThread:34715 [handler.py:handle_request():124] handle_request: stop_status
36
+ 2021-07-09 12:44:09,561 DEBUG SenderThread:34715 [sender.py:send_request():193] send_request: stop_status
37
+ 2021-07-09 12:44:10,614 WARNING MainThread:34715 [internal.py:wandb_internal():147] Internal process interrupt: 2
38
+ 2021-07-09 12:44:10,614 ERROR MainThread:34715 [internal.py:wandb_internal():150] Internal process interrupted.
39
+ 2021-07-09 12:44:10,625 INFO SenderThread:34715 [sender.py:finish():945] shutting down sender
40
+ 2021-07-09 12:44:10,626 INFO SenderThread:34715 [dir_watcher.py:finish():282] shutting down directory watcher
41
+ 2021-07-09 12:44:10,626 INFO HandlerThread:34715 [handler.py:finish():638] shutting down handler
42
+ 2021-07-09 12:44:11,514 INFO SenderThread:34715 [dir_watcher.py:finish():312] scan: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_124353-3pjvcule/files
43
+ 2021-07-09 12:44:11,514 INFO SenderThread:34715 [dir_watcher.py:finish():318] scan save: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_124353-3pjvcule/files/requirements.txt requirements.txt
44
+ 2021-07-09 12:44:11,514 INFO SenderThread:34715 [dir_watcher.py:finish():318] scan save: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_124353-3pjvcule/files/output.log output.log
45
+ 2021-07-09 12:44:11,515 INFO SenderThread:34715 [dir_watcher.py:finish():318] scan save: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_124353-3pjvcule/files/wandb-metadata.json wandb-metadata.json
46
+ 2021-07-09 12:44:11,515 INFO SenderThread:34715 [dir_watcher.py:finish():318] scan save: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_124353-3pjvcule/files/config.yaml config.yaml
47
+ 2021-07-09 12:44:11,515 INFO SenderThread:34715 [dir_watcher.py:finish():318] scan save: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_124353-3pjvcule/files/wandb-summary.json wandb-summary.json
48
+ 2021-07-09 12:44:11,515 INFO SenderThread:34715 [file_pusher.py:finish():177] shutting down file pusher
49
+ 2021-07-09 12:44:11,515 INFO SenderThread:34715 [file_pusher.py:join():182] waiting for file pusher
50
+ 2021-07-09 12:44:11,570 INFO WriterThread:34715 [datastore.py:close():288] close: /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_124353-3pjvcule/run-3pjvcule.wandb
51
+ 2021-07-09 12:44:11,810 INFO Thread-12 :34715 [upload_job.py:push():137] Uploaded file /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_124353-3pjvcule/files/requirements.txt
52
+ 2021-07-09 12:44:11,811 INFO Thread-14 :34715 [upload_job.py:push():137] Uploaded file /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_124353-3pjvcule/files/config.yaml
53
+ 2021-07-09 12:44:11,824 INFO Thread-13 :34715 [upload_job.py:push():137] Uploaded file /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_124353-3pjvcule/files/output.log
54
+ 2021-07-09 12:44:11,856 INFO Thread-15 :34715 [upload_job.py:push():137] Uploaded file /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_124353-3pjvcule/files/wandb-summary.json
55
+ 2021-07-09 12:44:12,589 INFO MainThread:34715 [internal.py:handle_exit():78] Internal process exited
wandb/run-20210709_124353-3pjvcule/logs/debug.log ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2021-07-09 12:43:53,661 INFO MainThread:33657 [wandb_setup.py:_flush():69] Unhandled environment var: WANDB_WATCH
2
+ 2021-07-09 12:43:53,661 INFO MainThread:33657 [wandb_setup.py:_flush():69] setting env: {'project': 'hf-flax-robert-base-mr', 'entity': 'nipunsadvilkar'}
3
+ 2021-07-09 12:43:53,661 INFO MainThread:33657 [wandb_setup.py:_flush():69] setting login settings: {}
4
+ 2021-07-09 12:43:53,662 INFO MainThread:33657 [wandb_init.py:_log_setup():337] Logging user logs to /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_124353-3pjvcule/logs/debug.log
5
+ 2021-07-09 12:43:53,662 INFO MainThread:33657 [wandb_init.py:_log_setup():338] Logging internal logs to /home/nipunsadvilkar/sample/roberta-base-mr/wandb/run-20210709_124353-3pjvcule/logs/debug-internal.log
6
+ 2021-07-09 12:43:53,662 INFO MainThread:33657 [wandb_init.py:init():370] calling init triggers
7
+ 2021-07-09 12:43:53,662 INFO MainThread:33657 [wandb_init.py:init():375] wandb.init called with sweep_config: {}
8
+ config: {}
9
+ 2021-07-09 12:43:53,662 INFO MainThread:33657 [wandb_init.py:init():419] starting backend
10
+ 2021-07-09 12:43:53,662 INFO MainThread:33657 [backend.py:_multiprocessing_setup():70] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
11
+ 2021-07-09 12:43:53,696 INFO MainThread:33657 [backend.py:ensure_launched():135] starting backend process...
12
+ 2021-07-09 12:43:53,729 INFO MainThread:33657 [backend.py:ensure_launched():139] started backend process with pid: 34715
13
+ 2021-07-09 12:43:53,731 INFO MainThread:33657 [wandb_init.py:init():424] backend started and connected
14
+ 2021-07-09 12:43:53,735 INFO MainThread:33657 [wandb_init.py:init():472] updated telemetry
15
+ 2021-07-09 12:43:53,736 INFO MainThread:33657 [wandb_init.py:init():491] communicating current version
16
+ 2021-07-09 12:43:54,402 INFO MainThread:33657 [wandb_init.py:init():496] got version response
17
+ 2021-07-09 12:43:54,402 INFO MainThread:33657 [wandb_init.py:init():504] communicating run to backend with 30 second timeout
18
+ 2021-07-09 12:43:54,471 INFO MainThread:33657 [wandb_init.py:init():529] starting run threads in backend
19
+ 2021-07-09 12:43:54,529 INFO MainThread:33657 [wandb_run.py:_console_start():1623] atexit reg
20
+ 2021-07-09 12:43:54,530 INFO MainThread:33657 [wandb_run.py:_redirect():1497] redirect: SettingsConsole.REDIRECT
21
+ 2021-07-09 12:43:54,530 INFO MainThread:33657 [wandb_run.py:_redirect():1502] Redirecting console.
22
+ 2021-07-09 12:43:54,533 INFO MainThread:33657 [wandb_run.py:_redirect():1558] Redirects installed.
23
+ 2021-07-09 12:43:54,533 INFO MainThread:33657 [wandb_init.py:init():554] run started, returning control to user process
24
+ 2021-07-09 12:43:54,534 INFO MainThread:33657 [wandb_run.py:_config_callback():872] config_cb None None {'output_dir': './', 'overwrite_output_dir': True, 'do_train': False, 'do_eval': False, 'do_predict': False, 'evaluation_strategy': 'IntervalStrategy.NO', 'prediction_loss_only': False, 'per_device_train_batch_size': 4, 'per_device_eval_batch_size': 4, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'learning_rate': 0.0003, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 8.0, 'max_steps': -1, 'lr_scheduler_type': 'SchedulerType.LINEAR', 'warmup_ratio': 0.0, 'warmup_steps': 1000, 'log_level': -1, 'log_level_replica': -1, 'log_on_each_node': True, 'logging_dir': './runs/Jul09_12-43-47_t1v-n-112df4a9-w-0', 'logging_strategy': 'IntervalStrategy.STEPS', 'logging_first_step': False, 'logging_steps': 500, 'save_strategy': 'IntervalStrategy.STEPS', 'save_steps': 500, 'save_total_limit': None, 'save_on_each_node': False, 'no_cuda': False, 'seed': 42, 'fp16': False, 'fp16_opt_level': 'O1', 'fp16_backend': 'auto', 'fp16_full_eval': False, 'local_rank': -1, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': 500, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': './', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'sharded_ddp': [], 'deepspeed': None, 'label_smoothing_factor': 0.0, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'dataloader_pin_memory': True, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': False, 'resume_from_checkpoint': None, 'push_to_hub_model_id': '', 'push_to_hub_organization': None, 'push_to_hub_token': None, 'mp_parameters': ''}
25
+ 2021-07-09 12:43:54,535 INFO MainThread:33657 [wandb_run.py:_config_callback():872] config_cb None None {'model_name_or_path': None, 'model_type': 'roberta', 'config_name': './', 'tokenizer_name': './', 'cache_dir': None, 'use_fast_tokenizer': True, 'dtype': 'float32'}
26
+ 2021-07-09 12:43:54,535 INFO MainThread:33657 [wandb_run.py:_config_callback():872] config_cb None None {'dataset_name': 'oscar', 'dataset_config_name': 'unshuffled_deduplicated_als', 'train_file': None, 'validation_file': None, 'train_ref_file': None, 'validation_ref_file': None, 'overwrite_cache': False, 'validation_split_percentage': 5, 'max_seq_length': 128, 'preprocessing_num_workers': None, 'mlm_probability': 0.15, 'pad_to_max_length': False, 'line_by_line': False}
27
+ 2021-07-09 12:44:09,645 INFO MainThread:33657 [wandb_run.py:_atexit_cleanup():1593] got exitcode: 255
28
+ 2021-07-09 12:44:09,646 INFO MainThread:33657 [wandb_run.py:_restore():1565] restore
wandb/run-20210709_124353-3pjvcule/run-3pjvcule.wandb ADDED
Binary file (3.81 kB). View file
 
wandb/run-20210709_124449-choidyfc/files/config.yaml ADDED
@@ -0,0 +1,305 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ wandb_version: 1
2
+
3
+ _wandb:
4
+ desc: null
5
+ value:
6
+ cli_version: 0.10.33
7
+ framework: huggingface
8
+ huggingface_version: 4.9.0.dev0
9
+ is_jupyter_run: false
10
+ is_kaggle_kernel: false
11
+ python_version: 3.8.10
12
+ t:
13
+ 1:
14
+ - 11
15
+ 2:
16
+ - 11
17
+ 4: 3.8.10
18
+ 5: 0.10.33
19
+ 6: 4.9.0.dev0
20
+ 8:
21
+ - 5
22
+ adafactor:
23
+ desc: null
24
+ value: false
25
+ adam_beta1:
26
+ desc: null
27
+ value: 0.9
28
+ adam_beta2:
29
+ desc: null
30
+ value: 0.999
31
+ adam_epsilon:
32
+ desc: null
33
+ value: 1.0e-08
34
+ cache_dir:
35
+ desc: null
36
+ value: null
37
+ config_name:
38
+ desc: null
39
+ value: ./
40
+ dataloader_drop_last:
41
+ desc: null
42
+ value: false
43
+ dataloader_num_workers:
44
+ desc: null
45
+ value: 0
46
+ dataloader_pin_memory:
47
+ desc: null
48
+ value: true
49
+ dataset_config_name:
50
+ desc: null
51
+ value: unshuffled_deduplicated_als
52
+ dataset_name:
53
+ desc: null
54
+ value: oscar
55
+ ddp_find_unused_parameters:
56
+ desc: null
57
+ value: null
58
+ debug:
59
+ desc: null
60
+ value: []
61
+ deepspeed:
62
+ desc: null
63
+ value: null
64
+ disable_tqdm:
65
+ desc: null
66
+ value: false
67
+ do_eval:
68
+ desc: null
69
+ value: false
70
+ do_predict:
71
+ desc: null
72
+ value: false
73
+ do_train:
74
+ desc: null
75
+ value: false
76
+ dtype:
77
+ desc: null
78
+ value: float32
79
+ eval_accumulation_steps:
80
+ desc: null
81
+ value: null
82
+ eval_steps:
83
+ desc: null
84
+ value: 500
85
+ evaluation_strategy:
86
+ desc: null
87
+ value: IntervalStrategy.NO
88
+ fp16:
89
+ desc: null
90
+ value: false
91
+ fp16_backend:
92
+ desc: null
93
+ value: auto
94
+ fp16_full_eval:
95
+ desc: null
96
+ value: false
97
+ fp16_opt_level:
98
+ desc: null
99
+ value: O1
100
+ gradient_accumulation_steps:
101
+ desc: null
102
+ value: 1
103
+ greater_is_better:
104
+ desc: null
105
+ value: null
106
+ group_by_length:
107
+ desc: null
108
+ value: false
109
+ ignore_data_skip:
110
+ desc: null
111
+ value: false
112
+ label_names:
113
+ desc: null
114
+ value: null
115
+ label_smoothing_factor:
116
+ desc: null
117
+ value: 0.0
118
+ learning_rate:
119
+ desc: null
120
+ value: 0.0003
121
+ length_column_name:
122
+ desc: null
123
+ value: length
124
+ line_by_line:
125
+ desc: null
126
+ value: false
127
+ load_best_model_at_end:
128
+ desc: null
129
+ value: false
130
+ local_rank:
131
+ desc: null
132
+ value: -1
133
+ log_level:
134
+ desc: null
135
+ value: -1
136
+ log_level_replica:
137
+ desc: null
138
+ value: -1
139
+ log_on_each_node:
140
+ desc: null
141
+ value: true
142
+ logging_dir:
143
+ desc: null
144
+ value: ./runs/Jul09_12-44-43_t1v-n-112df4a9-w-0
145
+ logging_first_step:
146
+ desc: null
147
+ value: false
148
+ logging_steps:
149
+ desc: null
150
+ value: 500
151
+ logging_strategy:
152
+ desc: null
153
+ value: IntervalStrategy.STEPS
154
+ lr_scheduler_type:
155
+ desc: null
156
+ value: SchedulerType.LINEAR
157
+ max_grad_norm:
158
+ desc: null
159
+ value: 1.0
160
+ max_seq_length:
161
+ desc: null
162
+ value: 128
163
+ max_steps:
164
+ desc: null
165
+ value: -1
166
+ metric_for_best_model:
167
+ desc: null
168
+ value: null
169
+ mlm_probability:
170
+ desc: null
171
+ value: 0.15
172
+ model_name_or_path:
173
+ desc: null
174
+ value: null
175
+ model_type:
176
+ desc: null
177
+ value: roberta
178
+ mp_parameters:
179
+ desc: null
180
+ value: ''
181
+ no_cuda:
182
+ desc: null
183
+ value: false
184
+ num_train_epochs:
185
+ desc: null
186
+ value: 8.0
187
+ output_dir:
188
+ desc: null
189
+ value: ./
190
+ overwrite_cache:
191
+ desc: null
192
+ value: false
193
+ overwrite_output_dir:
194
+ desc: null
195
+ value: true
196
+ pad_to_max_length:
197
+ desc: null
198
+ value: false
199
+ past_index:
200
+ desc: null
201
+ value: -1
202
+ per_device_eval_batch_size:
203
+ desc: null
204
+ value: 4
205
+ per_device_train_batch_size:
206
+ desc: null
207
+ value: 4
208
+ per_gpu_eval_batch_size:
209
+ desc: null
210
+ value: null
211
+ per_gpu_train_batch_size:
212
+ desc: null
213
+ value: null
214
+ prediction_loss_only:
215
+ desc: null
216
+ value: false
217
+ preprocessing_num_workers:
218
+ desc: null
219
+ value: null
220
+ push_to_hub:
221
+ desc: null
222
+ value: false
223
+ push_to_hub_model_id:
224
+ desc: null
225
+ value: ''
226
+ push_to_hub_organization:
227
+ desc: null
228
+ value: null
229
+ push_to_hub_token:
230
+ desc: null
231
+ value: null
232
+ remove_unused_columns:
233
+ desc: null
234
+ value: true
235
+ report_to:
236
+ desc: null
237
+ value:
238
+ - tensorboard
239
+ - wandb
240
+ resume_from_checkpoint:
241
+ desc: null
242
+ value: null
243
+ run_name:
244
+ desc: null
245
+ value: ./
246
+ save_on_each_node:
247
+ desc: null
248
+ value: false
249
+ save_steps:
250
+ desc: null
251
+ value: 500
252
+ save_strategy:
253
+ desc: null
254
+ value: IntervalStrategy.STEPS
255
+ save_total_limit:
256
+ desc: null
257
+ value: null
258
+ seed:
259
+ desc: null
260
+ value: 42
261
+ sharded_ddp:
262
+ desc: null
263
+ value: []
264
+ skip_memory_metrics:
265
+ desc: null
266
+ value: true
267
+ tokenizer_name:
268
+ desc: null
269
+ value: ./
270
+ tpu_metrics_debug:
271
+ desc: null
272
+ value: false
273
+ tpu_num_cores:
274
+ desc: null
275
+ value: null
276
+ train_file:
277
+ desc: null
278
+ value: null
279
+ train_ref_file:
280
+ desc: null
281
+ value: null
282
+ use_fast_tokenizer:
283
+ desc: null
284
+ value: true
285
+ use_legacy_prediction_loop:
286
+ desc: null
287
+ value: false
288
+ validation_file:
289
+ desc: null
290
+ value: null
291
+ validation_ref_file:
292
+ desc: null
293
+ value: null
294
+ validation_split_percentage:
295
+ desc: null
296
+ value: 5
297
+ warmup_ratio:
298
+ desc: null
299
+ value: 0.0
300
+ warmup_steps:
301
+ desc: null
302
+ value: 1000
303
+ weight_decay:
304
+ desc: null
305
+ value: 0.0