dat commited on
Commit
731244f
1 Parent(s): 9915204

update all

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. config.json +1 -1
  2. events.out.tfevents.1626304306.t1v-n-f5c06ea1-w-0.602807.3.v2 +3 -0
  3. events.out.tfevents.1626305223.t1v-n-f5c06ea1-w-0.605532.3.v2 +3 -0
  4. events.out.tfevents.1626306374.t1v-n-f5c06ea1-w-0.608526.3.v2 +3 -0
  5. events.out.tfevents.1626306537.t1v-n-f5c06ea1-w-0.610166.3.v2 +3 -0
  6. events.out.tfevents.1626306954.t1v-n-f5c06ea1-w-0.612049.3.v2 +3 -0
  7. events.out.tfevents.1626307676.t1v-n-f5c06ea1-w-0.614342.3.v2 +3 -0
  8. events.out.tfevents.1626308255.t1v-n-f5c06ea1-w-0.616592.3.v2 +3 -0
  9. events.out.tfevents.1626308889.t1v-n-f5c06ea1-w-0.618785.3.v2 +3 -0
  10. events.out.tfevents.1626309457.t1v-n-f5c06ea1-w-0.620917.3.v2 +3 -0
  11. events.out.tfevents.1626310347.t1v-n-f5c06ea1-w-0.623339.3.v2 +3 -0
  12. events.out.tfevents.1626310837.t1v-n-f5c06ea1-w-0.625421.3.v2 +3 -0
  13. events.out.tfevents.1626311317.t1v-n-f5c06ea1-w-0.626982.3.v2 +3 -0
  14. events.out.tfevents.1626311757.t1v-n-f5c06ea1-w-0.628566.3.v2 +3 -0
  15. events.out.tfevents.1626312025.t1v-n-f5c06ea1-w-0.630273.3.v2 +3 -0
  16. events.out.tfevents.1626312342.t1v-n-f5c06ea1-w-0.631837.3.v2 +3 -0
  17. events.out.tfevents.1626312869.t1v-n-f5c06ea1-w-0.634228.3.v2 +3 -0
  18. events.out.tfevents.1626312958.t1v-n-f5c06ea1-w-0.635913.3.v2 +3 -0
  19. events.out.tfevents.1626313509.t1v-n-f5c06ea1-w-0.638079.3.v2 +3 -0
  20. events.out.tfevents.1626314417.t1v-n-f5c06ea1-w-0.640692.3.v2 +3 -0
  21. run.sh +7 -8
  22. run_mlm_flax.py +3 -3
  23. run_mlm_flax_no_accum.py +3 -3
  24. wandb/debug-internal.log +1 -1
  25. wandb/debug.log +1 -1
  26. wandb/latest-run +1 -1
  27. wandb/run-20210714_225820-1dpoijkp/files/config.yaml +3 -0
  28. wandb/run-20210714_225820-1dpoijkp/files/output.log +33 -0
  29. wandb/run-20210714_225820-1dpoijkp/logs/debug-internal.log +195 -0
  30. wandb/run-20210714_225820-1dpoijkp/logs/debug.log +110 -0
  31. wandb/run-20210714_225820-1dpoijkp/run-1dpoijkp.wandb +0 -0
  32. wandb/run-20210714_231147-gkn68kcy/files/config.yaml +307 -0
  33. wandb/run-20210714_231147-gkn68kcy/files/output.log +32 -0
  34. wandb/run-20210714_231147-gkn68kcy/files/requirements.txt +94 -0
  35. wandb/run-20210714_231147-gkn68kcy/files/wandb-metadata.json +46 -0
  36. wandb/run-20210714_231147-gkn68kcy/files/wandb-summary.json +1 -0
  37. wandb/run-20210714_231147-gkn68kcy/logs/debug-internal.log +279 -0
  38. wandb/run-20210714_231147-gkn68kcy/logs/debug.log +119 -0
  39. wandb/run-20210714_231147-gkn68kcy/run-gkn68kcy.wandb +0 -0
  40. wandb/run-20210714_232703-1jijl27o/files/config.yaml +307 -0
  41. wandb/run-20210714_232703-1jijl27o/files/output.log +34 -0
  42. wandb/run-20210714_232703-1jijl27o/files/requirements.txt +94 -0
  43. wandb/run-20210714_232703-1jijl27o/files/wandb-metadata.json +47 -0
  44. wandb/run-20210714_232703-1jijl27o/files/wandb-summary.json +1 -0
  45. wandb/run-20210714_232703-1jijl27o/logs/debug-internal.log +275 -0
  46. wandb/run-20210714_232703-1jijl27o/logs/debug.log +127 -0
  47. wandb/run-20210714_232703-1jijl27o/run-1jijl27o.wandb +0 -0
  48. wandb/run-20210714_234615-3p6vlfc3/files/config.yaml +304 -0
  49. wandb/run-20210714_234615-3p6vlfc3/files/output.log +6 -0
  50. wandb/run-20210714_234615-3p6vlfc3/files/requirements.txt +94 -0
config.json CHANGED
@@ -4,7 +4,7 @@
4
  ],
5
  "attention_probs_dropout_prob": 0.1,
6
  "attention_type": "block_sparse",
7
- "block_size": 64,
8
  "bos_token_id": 1,
9
  "eos_token_id": 2,
10
  "gradient_checkpointing": false,
4
  ],
5
  "attention_probs_dropout_prob": 0.1,
6
  "attention_type": "block_sparse",
7
+ "block_size": 128,
8
  "bos_token_id": 1,
9
  "eos_token_id": 2,
10
  "gradient_checkpointing": false,
events.out.tfevents.1626304306.t1v-n-f5c06ea1-w-0.602807.3.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5af1d6e48b81f0b9d7a35be9c91ffce03eee366544729e50b2f6158dda353896
3
+ size 40
events.out.tfevents.1626305223.t1v-n-f5c06ea1-w-0.605532.3.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50736e35dba095f7e44007a17a7f2702b81215a45256c8a92304137fb1352920
3
+ size 40
events.out.tfevents.1626306374.t1v-n-f5c06ea1-w-0.608526.3.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c754bf3ea8fba0ce37ab52a99fc32dbd0370af24af9c99ff82c5d66f750ccf9
3
+ size 40
events.out.tfevents.1626306537.t1v-n-f5c06ea1-w-0.610166.3.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a0c43d6c44047fae8000715c934e7f0ecbdcde1074ad33da1da321c3b27e0fa
3
+ size 40
events.out.tfevents.1626306954.t1v-n-f5c06ea1-w-0.612049.3.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:399e413d5125b81deb4821e6cf2d48594b856250dc9a25b5b5a640e53b05dff1
3
+ size 40
events.out.tfevents.1626307676.t1v-n-f5c06ea1-w-0.614342.3.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14bf286b75218519d67d5dfc8dd5186890bde2fc12fad6c71348d0dc35a5c0d8
3
+ size 40
events.out.tfevents.1626308255.t1v-n-f5c06ea1-w-0.616592.3.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eba6714d53d12785a3f81e899889244c67dcbc04cb9fad8562008dcf8302a212
3
+ size 40
events.out.tfevents.1626308889.t1v-n-f5c06ea1-w-0.618785.3.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3b826e6696483c676eb0da8b48cd3811887b854b324027f4c4f58af92933d17
3
+ size 40
events.out.tfevents.1626309457.t1v-n-f5c06ea1-w-0.620917.3.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d144d24c7f4699737d4dcd0b3619027b85af5478c55be0142c8ba091253568fc
3
+ size 40
events.out.tfevents.1626310347.t1v-n-f5c06ea1-w-0.623339.3.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83fbcbad2d35506b956452a251f6ed447335e90407b067c149ba3127b303632a
3
+ size 40
events.out.tfevents.1626310837.t1v-n-f5c06ea1-w-0.625421.3.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b99cff29b8871cd8db3f8fa198969b985fea2ffc47e79089d3d725ef9f29080
3
+ size 40
events.out.tfevents.1626311317.t1v-n-f5c06ea1-w-0.626982.3.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f09f06cc74a2b6e25df6452b382ba19720ee66dbaf384048c15058d496280a8
3
+ size 40
events.out.tfevents.1626311757.t1v-n-f5c06ea1-w-0.628566.3.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7465c4dbbaee983519373fb924605fb6aacc585352185e9d2950814da4100c3b
3
+ size 7499
events.out.tfevents.1626312025.t1v-n-f5c06ea1-w-0.630273.3.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:635dcd8f0941e3cc687e76b31e5803cfcf80f17f9d50615fe8e93c2a0768e08c
3
+ size 40
events.out.tfevents.1626312342.t1v-n-f5c06ea1-w-0.631837.3.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a47b8e795ffa4867c8acf33eb5022d1bdaad588280c75b3bdebf47dda704101a
3
+ size 40
events.out.tfevents.1626312869.t1v-n-f5c06ea1-w-0.634228.3.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8228686009da130e2b1ae2918f1b8afc864f280b17fc48e479c5342dc466bec2
3
+ size 40
events.out.tfevents.1626312958.t1v-n-f5c06ea1-w-0.635913.3.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c7381fc3fe2646dc9fa2397819b0db0d19f859ddbd6061a67f237b2e1dd61e5
3
+ size 40
events.out.tfevents.1626313509.t1v-n-f5c06ea1-w-0.638079.3.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c70c504b2ddc63c6d6ffb5846f09dd37ed05743155ecae6469ce433583aca0bc
3
+ size 40
events.out.tfevents.1626314417.t1v-n-f5c06ea1-w-0.640692.3.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a907482f1b09a2b5e4e62b66f168db6d65bc1c98b9a140174cfe918b8039be5e
3
+ size 40
run.sh CHANGED
@@ -2,7 +2,7 @@
2
 
3
  #export TOKENIZERS_PARALLELISM=0
4
 
5
- python ./run_mlm_flax.py \
6
  --push_to_hub \
7
  --output_dir="./" \
8
  --model_type="big_bird" \
@@ -14,18 +14,17 @@ python ./run_mlm_flax.py \
14
  --overwrite_output_dir \
15
  --adam_beta1="0.9" \
16
  --adam_beta2="0.98" \
17
- --logging_steps="500" \
18
  --eval_steps="20000" \
19
  --num_train_epochs="5" \
20
  --preprocessing_num_workers="96" \
21
  --save_steps="20000" \
22
- --learning_rate="5e-5" \
23
- --per_device_train_batch_size="2" \
24
- --per_device_eval_batch_size="2" \
25
  --save_total_limit="5"\
26
- --max_eval_samples="2000"\
27
- --overwrite_cache False \
28
- --gradient_accumulation_steps="8" \
29
  #--resume_from_checkpoint="./"\
30
  #--adafactor \
31
  #--dtype="bfloat16" \
2
 
3
  #export TOKENIZERS_PARALLELISM=0
4
 
5
+ python ./run_mlm_flax_no_accum.py \
6
  --push_to_hub \
7
  --output_dir="./" \
8
  --model_type="big_bird" \
14
  --overwrite_output_dir \
15
  --adam_beta1="0.9" \
16
  --adam_beta2="0.98" \
17
+ --logging_steps="50" \
18
  --eval_steps="20000" \
19
  --num_train_epochs="5" \
20
  --preprocessing_num_workers="96" \
21
  --save_steps="20000" \
22
+ --learning_rate="3e-5" \
23
+ --per_device_train_batch_size="1" \
24
+ --per_device_eval_batch_size="1" \
25
  --save_total_limit="5"\
26
+ --max_eval_samples="500"\
27
+ #--gradient_accumulation_steps="4"\
 
28
  #--resume_from_checkpoint="./"\
29
  #--adafactor \
30
  #--dtype="bfloat16" \
run_mlm_flax.py CHANGED
@@ -525,10 +525,10 @@ if __name__ == "__main__":
525
  if load_grouped:
526
  logger.info("Loading tokenized and grouped dataset")
527
  tokenized_datasets = DatasetDict.load_from_disk("/data/tokenized_data")
528
- logger.info("Setting max validation examples to ")
529
- print(f"Number of validation examples {data_args.max_eval_samples}")
530
- #tokenized_datasets["train"]= tokenized_datasets["train"].select(range(20000))
531
  if data_args.max_eval_samples is not None:
 
 
532
  tokenized_datasets["validation"] = tokenized_datasets["validation"].select(range(data_args.max_eval_samples))
533
  else:
534
  if training_args.do_train:
525
  if load_grouped:
526
  logger.info("Loading tokenized and grouped dataset")
527
  tokenized_datasets = DatasetDict.load_from_disk("/data/tokenized_data")
528
+ tokenized_datasets["train"]= tokenized_datasets["train"].select(range(int(0.3*len(tokenized_datasets["train"]))))
 
 
529
  if data_args.max_eval_samples is not None:
530
+ logger.info("Setting max validation examples to ")
531
+ print(f"Number of validation examples {data_args.max_eval_samples}")
532
  tokenized_datasets["validation"] = tokenized_datasets["validation"].select(range(data_args.max_eval_samples))
533
  else:
534
  if training_args.do_train:
run_mlm_flax_no_accum.py CHANGED
@@ -25,7 +25,7 @@ import os
25
  import sys
26
  import time
27
  from dataclasses import dataclass, field
28
-
29
  # You can also adapt this script on your own masked language modeling task. Pointers for this are left as comments.
30
  from pathlib import Path
31
  from typing import Dict, List, Optional, Tuple
@@ -421,7 +421,7 @@ if __name__ == "__main__":
421
  tokenized_datasets = DatasetDict.load_from_disk("/data/tokenized_data")
422
  logger.info("Setting max validation examples to ")
423
  print(f"Number of validation examples {data_args.max_eval_samples}")
424
- tokenized_datasets["train"]= tokenized_datasets["train"].select(range(20000))
425
  if data_args.max_eval_samples is not None:
426
  tokenized_datasets["validation"] = tokenized_datasets["validation"].select(range(data_args.max_eval_samples))
427
  else:
@@ -604,7 +604,7 @@ if __name__ == "__main__":
604
  mask=decay_mask_fn,
605
  )
606
  optimizer = optax.chain(
607
- optax.clip_grad_by_global_norm(1.),
608
  optimizer
609
  )
610
 
25
  import sys
26
  import time
27
  from dataclasses import dataclass, field
28
+ from optax import clip_by_global_norm
29
  # You can also adapt this script on your own masked language modeling task. Pointers for this are left as comments.
30
  from pathlib import Path
31
  from typing import Dict, List, Optional, Tuple
421
  tokenized_datasets = DatasetDict.load_from_disk("/data/tokenized_data")
422
  logger.info("Setting max validation examples to ")
423
  print(f"Number of validation examples {data_args.max_eval_samples}")
424
+ #tokenized_datasets["train"]= tokenized_datasets["train"].select(range(int(0.3*len(tokenized_datasets["train"]))))
425
  if data_args.max_eval_samples is not None:
426
  tokenized_datasets["validation"] = tokenized_datasets["validation"].select(range(data_args.max_eval_samples))
427
  else:
604
  mask=decay_mask_fn,
605
  )
606
  optimizer = optax.chain(
607
+ optax.clip_by_global_norm(1.),
608
  optimizer
609
  )
610
 
wandb/debug-internal.log CHANGED
@@ -1 +1 @@
1
- run-20210714_225820-1dpoijkp/logs/debug-internal.log
1
+ run-20210715_020018-3i0mvo08/logs/debug-internal.log
wandb/debug.log CHANGED
@@ -1 +1 @@
1
- run-20210714_225820-1dpoijkp/logs/debug.log
1
+ run-20210715_020018-3i0mvo08/logs/debug.log
wandb/latest-run CHANGED
@@ -1 +1 @@
1
- run-20210714_225820-1dpoijkp
1
+ run-20210715_020018-3i0mvo08
wandb/run-20210714_225820-1dpoijkp/files/config.yaml CHANGED
@@ -13,6 +13,9 @@ _wandb:
13
  1:
14
  - 3
15
  - 11
 
 
 
16
  4: 3.8.10
17
  5: 0.10.33
18
  6: 4.9.0.dev0
13
  1:
14
  - 3
15
  - 11
16
+ 2:
17
+ - 3
18
+ - 11
19
  4: 3.8.10
20
  5: 0.10.33
21
  6: 4.9.0.dev0
wandb/run-20210714_225820-1dpoijkp/files/output.log CHANGED
@@ -4,3 +4,36 @@
4
  warnings.warn(
5
  /home/dat/pino/lib/python3.8/site-packages/jax/lib/xla_bridge.py:373: UserWarning: jax.host_id has been renamed to jax.process_index. This alias will eventually be removed; please update your code.
6
  warnings.warn(
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  warnings.warn(
5
  /home/dat/pino/lib/python3.8/site-packages/jax/lib/xla_bridge.py:373: 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 ... (1/5): 0%| | 0/5 [00:00<?, ?it/s]
8
+ Training...: 0%| | 0/503952 [01:28<?, ?it/s]
9
+ Epoch ... (1/5): 0%| | 0/5 [09:12<?, ?it/s]
10
+ Traceback (most recent call last):
11
+ File "./run_mlm_flax.py", line 815, in <module>
12
+ state, train_metric, dropout_rngs = p_train_step(state, model_inputs, dropout_rngs)
13
+ File "/home/dat/pino/lib/python3.8/site-packages/jax/_src/traceback_util.py", line 183, in reraise_with_filtered_traceback
14
+ return fun(*args, **kwargs)
15
+ File "/home/dat/pino/lib/python3.8/site-packages/jax/_src/api.py", line 1669, in f_pmapped
16
+ out = pxla.xla_pmap(
17
+ File "/home/dat/pino/lib/python3.8/site-packages/jax/core.py", line 1620, in bind
18
+ return call_bind(self, fun, *args, **params)
19
+ File "/home/dat/pino/lib/python3.8/site-packages/jax/core.py", line 1551, in call_bind
20
+ outs = primitive.process(top_trace, fun, tracers, params)
21
+ File "/home/dat/pino/lib/python3.8/site-packages/jax/core.py", line 1623, in process
22
+ return trace.process_map(self, fun, tracers, params)
23
+ File "/home/dat/pino/lib/python3.8/site-packages/jax/core.py", line 606, in process_call
24
+ return primitive.impl(f, *tracers, **params)
25
+ File "/home/dat/pino/lib/python3.8/site-packages/jax/interpreters/pxla.py", line 637, in xla_pmap_impl
26
+ return compiled_fun(*args)
27
+ File "/home/dat/pino/lib/python3.8/site-packages/jax/interpreters/pxla.py", line 1159, in execute_replicated
28
+ out_bufs = compiled.execute_sharded_on_local_devices(input_bufs)
29
+ jax._src.traceback_util.UnfilteredStackTrace: RuntimeError: Resource exhausted: Attempting to reserve 12.58G at the bottom of memory. That was not possible. There are 5.86G free, 0B reserved, and 5.66G reservable.: while running replica 0 and partition 0 of a replicated computation (other replicas may have failed as well).
30
+ The stack trace below excludes JAX-internal frames.
31
+ The preceding is the original exception that occurred, unmodified.
32
+ --------------------
33
+ The above exception was the direct cause of the following exception:
34
+ Traceback (most recent call last):
35
+ File "./run_mlm_flax.py", line 815, in <module>
36
+ state, train_metric, dropout_rngs = p_train_step(state, model_inputs, dropout_rngs)
37
+ File "/home/dat/pino/lib/python3.8/site-packages/jax/interpreters/pxla.py", line 1159, in execute_replicated
38
+ out_bufs = compiled.execute_sharded_on_local_devices(input_bufs)
39
+ RuntimeError: Resource exhausted: Attempting to reserve 12.58G at the bottom of memory. That was not possible. There are 5.86G free, 0B reserved, and 5.66G reservable.: while running replica 0 and partition 0 of a replicated computation (other replicas may have failed as well).
wandb/run-20210714_225820-1dpoijkp/logs/debug-internal.log CHANGED
@@ -38,3 +38,198 @@
38
  2021-07-14 22:58:53,006 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: stop_status
39
  2021-07-14 22:59:08,141 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: stop_status
40
  2021-07-14 22:59:08,141 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: stop_status
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
38
  2021-07-14 22:58:53,006 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: stop_status
39
  2021-07-14 22:59:08,141 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: stop_status
40
  2021-07-14 22:59:08,141 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: stop_status
41
+ 2021-07-14 22:59:20,866 DEBUG SenderThread:601574 [sender.py:send():179] send: stats
42
+ 2021-07-14 22:59:23,276 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: stop_status
43
+ 2021-07-14 22:59:23,277 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: stop_status
44
+ 2021-07-14 22:59:38,415 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: stop_status
45
+ 2021-07-14 22:59:38,415 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: stop_status
46
+ 2021-07-14 22:59:50,943 DEBUG SenderThread:601574 [sender.py:send():179] send: stats
47
+ 2021-07-14 22:59:53,547 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: stop_status
48
+ 2021-07-14 22:59:53,547 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: stop_status
49
+ 2021-07-14 23:00:08,680 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: stop_status
50
+ 2021-07-14 23:00:08,680 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: stop_status
51
+ 2021-07-14 23:00:21,020 DEBUG SenderThread:601574 [sender.py:send():179] send: stats
52
+ 2021-07-14 23:00:23,810 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: stop_status
53
+ 2021-07-14 23:00:23,811 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: stop_status
54
+ 2021-07-14 23:00:38,944 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: stop_status
55
+ 2021-07-14 23:00:38,945 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: stop_status
56
+ 2021-07-14 23:00:51,098 DEBUG SenderThread:601574 [sender.py:send():179] send: stats
57
+ 2021-07-14 23:00:54,080 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: stop_status
58
+ 2021-07-14 23:00:54,080 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: stop_status
59
+ 2021-07-14 23:01:09,212 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: stop_status
60
+ 2021-07-14 23:01:09,212 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: stop_status
61
+ 2021-07-14 23:01:21,176 DEBUG SenderThread:601574 [sender.py:send():179] send: stats
62
+ 2021-07-14 23:01:24,345 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: stop_status
63
+ 2021-07-14 23:01:24,346 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: stop_status
64
+ 2021-07-14 23:01:39,477 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: stop_status
65
+ 2021-07-14 23:01:39,478 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: stop_status
66
+ 2021-07-14 23:01:51,254 DEBUG SenderThread:601574 [sender.py:send():179] send: stats
67
+ 2021-07-14 23:01:54,612 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: stop_status
68
+ 2021-07-14 23:01:54,612 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: stop_status
69
+ 2021-07-14 23:02:09,744 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: stop_status
70
+ 2021-07-14 23:02:09,744 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: stop_status
71
+ 2021-07-14 23:02:21,332 DEBUG SenderThread:601574 [sender.py:send():179] send: stats
72
+ 2021-07-14 23:02:24,932 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: stop_status
73
+ 2021-07-14 23:02:24,932 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: stop_status
74
+ 2021-07-14 23:02:40,066 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: stop_status
75
+ 2021-07-14 23:02:40,067 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: stop_status
76
+ 2021-07-14 23:02:51,409 DEBUG SenderThread:601574 [sender.py:send():179] send: stats
77
+ 2021-07-14 23:02:55,209 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: stop_status
78
+ 2021-07-14 23:02:55,209 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: stop_status
79
+ 2021-07-14 23:03:10,341 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: stop_status
80
+ 2021-07-14 23:03:10,341 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: stop_status
81
+ 2021-07-14 23:03:21,484 DEBUG SenderThread:601574 [sender.py:send():179] send: stats
82
+ 2021-07-14 23:03:25,483 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: stop_status
83
+ 2021-07-14 23:03:25,483 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: stop_status
84
+ 2021-07-14 23:03:40,615 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: stop_status
85
+ 2021-07-14 23:03:40,615 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: stop_status
86
+ 2021-07-14 23:03:51,547 DEBUG SenderThread:601574 [sender.py:send():179] send: stats
87
+ 2021-07-14 23:03:56,377 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: stop_status
88
+ 2021-07-14 23:03:56,377 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: stop_status
89
+ 2021-07-14 23:04:11,520 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: stop_status
90
+ 2021-07-14 23:04:11,520 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: stop_status
91
+ 2021-07-14 23:04:21,610 DEBUG SenderThread:601574 [sender.py:send():179] send: stats
92
+ 2021-07-14 23:04:26,652 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: stop_status
93
+ 2021-07-14 23:04:26,652 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: stop_status
94
+ 2021-07-14 23:04:41,781 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: stop_status
95
+ 2021-07-14 23:04:41,781 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: stop_status
96
+ 2021-07-14 23:04:51,676 DEBUG SenderThread:601574 [sender.py:send():179] send: stats
97
+ 2021-07-14 23:04:56,913 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: stop_status
98
+ 2021-07-14 23:04:56,913 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: stop_status
99
+ 2021-07-14 23:05:13,026 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: stop_status
100
+ 2021-07-14 23:05:13,027 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: stop_status
101
+ 2021-07-14 23:05:21,744 DEBUG SenderThread:601574 [sender.py:send():179] send: stats
102
+ 2021-07-14 23:05:28,237 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: stop_status
103
+ 2021-07-14 23:05:28,238 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: stop_status
104
+ 2021-07-14 23:05:44,049 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: stop_status
105
+ 2021-07-14 23:05:44,049 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: stop_status
106
+ 2021-07-14 23:05:51,809 DEBUG SenderThread:601574 [sender.py:send():179] send: stats
107
+ 2021-07-14 23:05:59,179 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: stop_status
108
+ 2021-07-14 23:05:59,180 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: stop_status
109
+ 2021-07-14 23:06:14,311 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: stop_status
110
+ 2021-07-14 23:06:14,311 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: stop_status
111
+ 2021-07-14 23:06:21,764 INFO Thread-8 :601574 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210714_225820-1dpoijkp/files/output.log
112
+ 2021-07-14 23:06:21,877 DEBUG SenderThread:601574 [sender.py:send():179] send: stats
113
+ 2021-07-14 23:06:29,456 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: stop_status
114
+ 2021-07-14 23:06:29,457 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: stop_status
115
+ 2021-07-14 23:06:44,749 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: stop_status
116
+ 2021-07-14 23:06:44,749 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: stop_status
117
+ 2021-07-14 23:06:51,950 DEBUG SenderThread:601574 [sender.py:send():179] send: stats
118
+ 2021-07-14 23:06:59,941 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: stop_status
119
+ 2021-07-14 23:06:59,941 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: stop_status
120
+ 2021-07-14 23:07:15,073 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: stop_status
121
+ 2021-07-14 23:07:15,077 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: stop_status
122
+ 2021-07-14 23:07:22,025 DEBUG SenderThread:601574 [sender.py:send():179] send: stats
123
+ 2021-07-14 23:07:30,221 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: stop_status
124
+ 2021-07-14 23:07:30,221 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: stop_status
125
+ 2021-07-14 23:07:45,363 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: stop_status
126
+ 2021-07-14 23:07:45,364 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: stop_status
127
+ 2021-07-14 23:07:50,438 DEBUG SenderThread:601574 [sender.py:send():179] send: telemetry
128
+ 2021-07-14 23:07:50,439 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: poll_exit
129
+ 2021-07-14 23:07:50,439 DEBUG SenderThread:601574 [sender.py:send():179] send: exit
130
+ 2021-07-14 23:07:50,439 INFO SenderThread:601574 [sender.py:send_exit():287] handling exit code: 1
131
+ 2021-07-14 23:07:50,440 INFO SenderThread:601574 [sender.py:send_exit():295] send defer
132
+ 2021-07-14 23:07:50,440 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: poll_exit
133
+ 2021-07-14 23:07:50,441 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: defer
134
+ 2021-07-14 23:07:50,441 INFO HandlerThread:601574 [handler.py:handle_request_defer():141] handle defer: 0
135
+ 2021-07-14 23:07:50,441 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: defer
136
+ 2021-07-14 23:07:50,441 INFO SenderThread:601574 [sender.py:send_request_defer():304] handle sender defer: 0
137
+ 2021-07-14 23:07:50,441 INFO SenderThread:601574 [sender.py:transition_state():308] send defer: 1
138
+ 2021-07-14 23:07:50,442 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: defer
139
+ 2021-07-14 23:07:50,442 INFO HandlerThread:601574 [handler.py:handle_request_defer():141] handle defer: 1
140
+ 2021-07-14 23:07:50,497 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: defer
141
+ 2021-07-14 23:07:50,497 INFO SenderThread:601574 [sender.py:send_request_defer():304] handle sender defer: 1
142
+ 2021-07-14 23:07:50,497 INFO SenderThread:601574 [sender.py:transition_state():308] send defer: 2
143
+ 2021-07-14 23:07:50,497 DEBUG SenderThread:601574 [sender.py:send():179] send: stats
144
+ 2021-07-14 23:07:50,498 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: defer
145
+ 2021-07-14 23:07:50,498 INFO HandlerThread:601574 [handler.py:handle_request_defer():141] handle defer: 2
146
+ 2021-07-14 23:07:50,498 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: defer
147
+ 2021-07-14 23:07:50,498 INFO SenderThread:601574 [sender.py:send_request_defer():304] handle sender defer: 2
148
+ 2021-07-14 23:07:50,498 INFO SenderThread:601574 [sender.py:transition_state():308] send defer: 3
149
+ 2021-07-14 23:07:50,499 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: defer
150
+ 2021-07-14 23:07:50,499 INFO HandlerThread:601574 [handler.py:handle_request_defer():141] handle defer: 3
151
+ 2021-07-14 23:07:50,499 DEBUG SenderThread:601574 [sender.py:send():179] send: summary
152
+ 2021-07-14 23:07:50,499 INFO SenderThread:601574 [sender.py:_save_file():841] saving file wandb-summary.json with policy end
153
+ 2021-07-14 23:07:50,499 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: defer
154
+ 2021-07-14 23:07:50,499 INFO SenderThread:601574 [sender.py:send_request_defer():304] handle sender defer: 3
155
+ 2021-07-14 23:07:50,499 INFO SenderThread:601574 [sender.py:transition_state():308] send defer: 4
156
+ 2021-07-14 23:07:50,500 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: defer
157
+ 2021-07-14 23:07:50,500 INFO HandlerThread:601574 [handler.py:handle_request_defer():141] handle defer: 4
158
+ 2021-07-14 23:07:50,500 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: defer
159
+ 2021-07-14 23:07:50,500 INFO SenderThread:601574 [sender.py:send_request_defer():304] handle sender defer: 4
160
+ 2021-07-14 23:07:50,543 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: poll_exit
161
+ 2021-07-14 23:07:50,746 INFO SenderThread:601574 [sender.py:transition_state():308] send defer: 5
162
+ 2021-07-14 23:07:50,746 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: poll_exit
163
+ 2021-07-14 23:07:50,747 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: defer
164
+ 2021-07-14 23:07:50,747 INFO HandlerThread:601574 [handler.py:handle_request_defer():141] handle defer: 5
165
+ 2021-07-14 23:07:50,747 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: defer
166
+ 2021-07-14 23:07:50,747 INFO SenderThread:601574 [sender.py:send_request_defer():304] handle sender defer: 5
167
+ 2021-07-14 23:07:50,747 INFO SenderThread:601574 [dir_watcher.py:finish():282] shutting down directory watcher
168
+ 2021-07-14 23:07:50,787 INFO SenderThread:601574 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210714_225820-1dpoijkp/files/output.log
169
+ 2021-07-14 23:07:50,787 INFO SenderThread:601574 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210714_225820-1dpoijkp/files/config.yaml
170
+ 2021-07-14 23:07:50,787 INFO SenderThread:601574 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210714_225820-1dpoijkp/files/wandb-summary.json
171
+ 2021-07-14 23:07:50,788 INFO SenderThread:601574 [dir_watcher.py:finish():312] scan: /home/dat/pino-roberta-base/wandb/run-20210714_225820-1dpoijkp/files
172
+ 2021-07-14 23:07:50,788 INFO SenderThread:601574 [dir_watcher.py:finish():318] scan save: /home/dat/pino-roberta-base/wandb/run-20210714_225820-1dpoijkp/files/requirements.txt requirements.txt
173
+ 2021-07-14 23:07:50,788 INFO SenderThread:601574 [dir_watcher.py:finish():318] scan save: /home/dat/pino-roberta-base/wandb/run-20210714_225820-1dpoijkp/files/output.log output.log
174
+ 2021-07-14 23:07:50,788 INFO SenderThread:601574 [dir_watcher.py:finish():318] scan save: /home/dat/pino-roberta-base/wandb/run-20210714_225820-1dpoijkp/files/wandb-metadata.json wandb-metadata.json
175
+ 2021-07-14 23:07:50,788 INFO SenderThread:601574 [dir_watcher.py:finish():318] scan save: /home/dat/pino-roberta-base/wandb/run-20210714_225820-1dpoijkp/files/config.yaml config.yaml
176
+ 2021-07-14 23:07:50,789 INFO SenderThread:601574 [dir_watcher.py:finish():318] scan save: /home/dat/pino-roberta-base/wandb/run-20210714_225820-1dpoijkp/files/wandb-summary.json wandb-summary.json
177
+ 2021-07-14 23:07:50,792 INFO SenderThread:601574 [sender.py:transition_state():308] send defer: 6
178
+ 2021-07-14 23:07:50,792 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: defer
179
+ 2021-07-14 23:07:50,792 INFO HandlerThread:601574 [handler.py:handle_request_defer():141] handle defer: 6
180
+ 2021-07-14 23:07:50,795 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: defer
181
+ 2021-07-14 23:07:50,795 INFO SenderThread:601574 [sender.py:send_request_defer():304] handle sender defer: 6
182
+ 2021-07-14 23:07:50,795 INFO SenderThread:601574 [file_pusher.py:finish():177] shutting down file pusher
183
+ 2021-07-14 23:07:50,848 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: poll_exit
184
+ 2021-07-14 23:07:50,849 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: poll_exit
185
+ 2021-07-14 23:07:50,951 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: poll_exit
186
+ 2021-07-14 23:07:50,951 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: poll_exit
187
+ 2021-07-14 23:07:51,053 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: poll_exit
188
+ 2021-07-14 23:07:51,053 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: poll_exit
189
+ 2021-07-14 23:07:51,155 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: poll_exit
190
+ 2021-07-14 23:07:51,155 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: poll_exit
191
+ 2021-07-14 23:07:51,257 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: poll_exit
192
+ 2021-07-14 23:07:51,257 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: poll_exit
193
+ 2021-07-14 23:07:51,284 INFO Thread-12 :601574 [upload_job.py:push():137] Uploaded file /home/dat/pino-roberta-base/wandb/run-20210714_225820-1dpoijkp/files/requirements.txt
194
+ 2021-07-14 23:07:51,311 INFO Thread-14 :601574 [upload_job.py:push():137] Uploaded file /home/dat/pino-roberta-base/wandb/run-20210714_225820-1dpoijkp/files/config.yaml
195
+ 2021-07-14 23:07:51,322 INFO Thread-13 :601574 [upload_job.py:push():137] Uploaded file /home/dat/pino-roberta-base/wandb/run-20210714_225820-1dpoijkp/files/output.log
196
+ 2021-07-14 23:07:51,359 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: poll_exit
197
+ 2021-07-14 23:07:51,359 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: poll_exit
198
+ 2021-07-14 23:07:51,461 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: poll_exit
199
+ 2021-07-14 23:07:51,461 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: poll_exit
200
+ 2021-07-14 23:07:51,466 INFO Thread-15 :601574 [upload_job.py:push():137] Uploaded file /home/dat/pino-roberta-base/wandb/run-20210714_225820-1dpoijkp/files/wandb-summary.json
201
+ 2021-07-14 23:07:51,563 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: poll_exit
202
+ 2021-07-14 23:07:51,563 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: poll_exit
203
+ 2021-07-14 23:07:51,665 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: poll_exit
204
+ 2021-07-14 23:07:51,665 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: poll_exit
205
+ 2021-07-14 23:07:51,666 INFO Thread-7 :601574 [sender.py:transition_state():308] send defer: 7
206
+ 2021-07-14 23:07:51,667 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: defer
207
+ 2021-07-14 23:07:51,667 INFO HandlerThread:601574 [handler.py:handle_request_defer():141] handle defer: 7
208
+ 2021-07-14 23:07:51,667 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: defer
209
+ 2021-07-14 23:07:51,667 INFO SenderThread:601574 [sender.py:send_request_defer():304] handle sender defer: 7
210
+ 2021-07-14 23:07:51,766 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: poll_exit
211
+ 2021-07-14 23:07:51,941 INFO SenderThread:601574 [sender.py:transition_state():308] send defer: 8
212
+ 2021-07-14 23:07:51,941 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: poll_exit
213
+ 2021-07-14 23:07:51,942 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: defer
214
+ 2021-07-14 23:07:51,942 INFO HandlerThread:601574 [handler.py:handle_request_defer():141] handle defer: 8
215
+ 2021-07-14 23:07:51,942 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: defer
216
+ 2021-07-14 23:07:51,942 INFO SenderThread:601574 [sender.py:send_request_defer():304] handle sender defer: 8
217
+ 2021-07-14 23:07:51,942 INFO SenderThread:601574 [sender.py:transition_state():308] send defer: 9
218
+ 2021-07-14 23:07:51,942 DEBUG SenderThread:601574 [sender.py:send():179] send: final
219
+ 2021-07-14 23:07:51,942 DEBUG SenderThread:601574 [sender.py:send():179] send: footer
220
+ 2021-07-14 23:07:51,943 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: defer
221
+ 2021-07-14 23:07:51,943 INFO HandlerThread:601574 [handler.py:handle_request_defer():141] handle defer: 9
222
+ 2021-07-14 23:07:51,943 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: defer
223
+ 2021-07-14 23:07:51,943 INFO SenderThread:601574 [sender.py:send_request_defer():304] handle sender defer: 9
224
+ 2021-07-14 23:07:52,043 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: poll_exit
225
+ 2021-07-14 23:07:52,043 DEBUG SenderThread:601574 [sender.py:send_request():193] send_request: poll_exit
226
+ 2021-07-14 23:07:52,044 INFO SenderThread:601574 [file_pusher.py:join():182] waiting for file pusher
227
+ 2021-07-14 23:07:52,045 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: get_summary
228
+ 2021-07-14 23:07:52,045 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: sampled_history
229
+ 2021-07-14 23:07:52,046 DEBUG HandlerThread:601574 [handler.py:handle_request():124] handle_request: shutdown
230
+ 2021-07-14 23:07:52,046 INFO HandlerThread:601574 [handler.py:finish():638] shutting down handler
231
+ 2021-07-14 23:07:52,943 INFO WriterThread:601574 [datastore.py:close():288] close: /home/dat/pino-roberta-base/wandb/run-20210714_225820-1dpoijkp/run-1dpoijkp.wandb
232
+ 2021-07-14 23:07:53,044 INFO SenderThread:601574 [sender.py:finish():945] shutting down sender
233
+ 2021-07-14 23:07:53,044 INFO SenderThread:601574 [file_pusher.py:finish():177] shutting down file pusher
234
+ 2021-07-14 23:07:53,044 INFO SenderThread:601574 [file_pusher.py:join():182] waiting for file pusher
235
+ 2021-07-14 23:07:53,047 INFO MainThread:601574 [internal.py:handle_exit():78] Internal process exited
wandb/run-20210714_225820-1dpoijkp/logs/debug.log CHANGED
@@ -23,3 +23,113 @@ config: {}
23
  2021-07-14 22:58:22,750 INFO MainThread:600323 [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': 2, 'per_device_eval_batch_size': 2, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 8, 'eval_accumulation_steps': None, 'learning_rate': 5e-05, 'weight_decay': 0.0095, 'adam_beta1': 0.9, 'adam_beta2': 0.98, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 5.0, 'max_steps': -1, 'lr_scheduler_type': 'SchedulerType.LINEAR', 'warmup_ratio': 0.0, 'warmup_steps': 10000, 'log_level': -1, 'log_level_replica': -1, 'log_on_each_node': True, 'logging_dir': './runs/Jul14_22-58-13_t1v-n-f5c06ea1-w-0', 'logging_strategy': 'IntervalStrategy.STEPS', 'logging_first_step': False, 'logging_steps': 500, 'save_strategy': 'IntervalStrategy.STEPS', 'save_steps': 20000, 'save_total_limit': 5, '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': 20000, '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': True, 'resume_from_checkpoint': None, 'push_to_hub_model_id': '', 'push_to_hub_organization': None, 'push_to_hub_token': None, 'mp_parameters': ''}
24
  2021-07-14 22:58:22,752 INFO MainThread:600323 [wandb_run.py:_config_callback():872] config_cb None None {'model_name_or_path': None, 'model_type': 'big_bird', 'config_name': './', 'tokenizer_name': './', 'cache_dir': None, 'use_fast_tokenizer': True, 'dtype': 'float32', 'save_optimizer': True}
25
  2021-07-14 22:58:22,753 INFO MainThread:600323 [wandb_run.py:_config_callback():872] config_cb None None {'dataset_name': None, 'dataset_config_name': None, 'train_ref_file': None, 'validation_ref_file': None, 'overwrite_cache': False, 'validation_split_percentage': 5, 'max_seq_length': 4096, 'preprocessing_num_workers': 96, 'mlm_probability': 0.15, 'pad_to_max_length': False, 'line_by_line': False, 'max_eval_samples': 2000}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
23
  2021-07-14 22:58:22,750 INFO MainThread:600323 [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': 2, 'per_device_eval_batch_size': 2, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 8, 'eval_accumulation_steps': None, 'learning_rate': 5e-05, 'weight_decay': 0.0095, 'adam_beta1': 0.9, 'adam_beta2': 0.98, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 5.0, 'max_steps': -1, 'lr_scheduler_type': 'SchedulerType.LINEAR', 'warmup_ratio': 0.0, 'warmup_steps': 10000, 'log_level': -1, 'log_level_replica': -1, 'log_on_each_node': True, 'logging_dir': './runs/Jul14_22-58-13_t1v-n-f5c06ea1-w-0', 'logging_strategy': 'IntervalStrategy.STEPS', 'logging_first_step': False, 'logging_steps': 500, 'save_strategy': 'IntervalStrategy.STEPS', 'save_steps': 20000, 'save_total_limit': 5, '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': 20000, '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': True, 'resume_from_checkpoint': None, 'push_to_hub_model_id': '', 'push_to_hub_organization': None, 'push_to_hub_token': None, 'mp_parameters': ''}
24
  2021-07-14 22:58:22,752 INFO MainThread:600323 [wandb_run.py:_config_callback():872] config_cb None None {'model_name_or_path': None, 'model_type': 'big_bird', 'config_name': './', 'tokenizer_name': './', 'cache_dir': None, 'use_fast_tokenizer': True, 'dtype': 'float32', 'save_optimizer': True}
25
  2021-07-14 22:58:22,753 INFO MainThread:600323 [wandb_run.py:_config_callback():872] config_cb None None {'dataset_name': None, 'dataset_config_name': None, 'train_ref_file': None, 'validation_ref_file': None, 'overwrite_cache': False, 'validation_split_percentage': 5, 'max_seq_length': 4096, 'preprocessing_num_workers': 96, 'mlm_probability': 0.15, 'pad_to_max_length': False, 'line_by_line': False, 'max_eval_samples': 2000}
26
+ 2021-07-14 23:07:48,138 INFO MainThread:600323 [wandb_run.py:_atexit_cleanup():1593] got exitcode: 1
27
+ 2021-07-14 23:07:48,139 INFO MainThread:600323 [wandb_run.py:_restore():1565] restore
28
+ 2021-07-14 23:07:50,441 INFO MainThread:600323 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
29
+ wandb_count: 1
30
+ }
31
+ pusher_stats {
32
+ uploaded_bytes: 1448
33
+ total_bytes: 1448
34
+ }
35
+
36
+ 2021-07-14 23:07:50,747 INFO MainThread:600323 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
37
+ wandb_count: 1
38
+ }
39
+ pusher_stats {
40
+ uploaded_bytes: 1448
41
+ total_bytes: 1448
42
+ }
43
+
44
+ 2021-07-14 23:07:50,849 INFO MainThread:600323 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
45
+ wandb_count: 5
46
+ }
47
+ pusher_stats {
48
+ uploaded_bytes: 1448
49
+ total_bytes: 11717
50
+ }
51
+
52
+ 2021-07-14 23:07:50,951 INFO MainThread:600323 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
53
+ wandb_count: 5
54
+ }
55
+ pusher_stats {
56
+ uploaded_bytes: 1448
57
+ total_bytes: 11717
58
+ }
59
+
60
+ 2021-07-14 23:07:51,054 INFO MainThread:600323 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
61
+ wandb_count: 5
62
+ }
63
+ pusher_stats {
64
+ uploaded_bytes: 11717
65
+ total_bytes: 11717
66
+ }
67
+
68
+ 2021-07-14 23:07:51,156 INFO MainThread:600323 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
69
+ wandb_count: 5
70
+ }
71
+ pusher_stats {
72
+ uploaded_bytes: 11717
73
+ total_bytes: 11717
74
+ }
75
+
76
+ 2021-07-14 23:07:51,258 INFO MainThread:600323 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
77
+ wandb_count: 5
78
+ }
79
+ pusher_stats {
80
+ uploaded_bytes: 11717
81
+ total_bytes: 11717
82
+ }
83
+
84
+ 2021-07-14 23:07:51,360 INFO MainThread:600323 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
85
+ wandb_count: 5
86
+ }
87
+ pusher_stats {
88
+ uploaded_bytes: 11717
89
+ total_bytes: 11717
90
+ }
91
+
92
+ 2021-07-14 23:07:51,462 INFO MainThread:600323 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
93
+ wandb_count: 5
94
+ }
95
+ pusher_stats {
96
+ uploaded_bytes: 11717
97
+ total_bytes: 11717
98
+ }
99
+
100
+ 2021-07-14 23:07:51,564 INFO MainThread:600323 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
101
+ wandb_count: 5
102
+ }
103
+ pusher_stats {
104
+ uploaded_bytes: 11717
105
+ total_bytes: 11717
106
+ }
107
+
108
+ 2021-07-14 23:07:51,665 INFO MainThread:600323 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
109
+ wandb_count: 5
110
+ }
111
+ pusher_stats {
112
+ uploaded_bytes: 11717
113
+ total_bytes: 11717
114
+ }
115
+
116
+ 2021-07-14 23:07:51,942 INFO MainThread:600323 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
117
+ wandb_count: 5
118
+ }
119
+ pusher_stats {
120
+ uploaded_bytes: 11717
121
+ total_bytes: 11717
122
+ }
123
+
124
+ 2021-07-14 23:07:52,044 INFO MainThread:600323 [wandb_run.py:_wait_for_finish():1715] got exit ret: done: true
125
+ exit_result {
126
+ }
127
+ file_counts {
128
+ wandb_count: 5
129
+ }
130
+ pusher_stats {
131
+ uploaded_bytes: 11717
132
+ total_bytes: 11717
133
+ }
134
+
135
+ 2021-07-14 23:07:53,341 INFO MainThread:600323 [wandb_run.py:_show_files():1937] logging synced files
wandb/run-20210714_225820-1dpoijkp/run-1dpoijkp.wandb CHANGED
Binary files a/wandb/run-20210714_225820-1dpoijkp/run-1dpoijkp.wandb and b/wandb/run-20210714_225820-1dpoijkp/run-1dpoijkp.wandb differ
wandb/run-20210714_231147-gkn68kcy/files/config.yaml ADDED
@@ -0,0 +1,307 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ - 3
15
+ - 11
16
+ 2:
17
+ - 3
18
+ - 11
19
+ 4: 3.8.10
20
+ 5: 0.10.33
21
+ 6: 4.9.0.dev0
22
+ 8:
23
+ - 5
24
+ adafactor:
25
+ desc: null
26
+ value: false
27
+ adam_beta1:
28
+ desc: null
29
+ value: 0.9
30
+ adam_beta2:
31
+ desc: null
32
+ value: 0.98
33
+ adam_epsilon:
34
+ desc: null
35
+ value: 1.0e-08
36
+ cache_dir:
37
+ desc: null
38
+ value: null
39
+ config_name:
40
+ desc: null
41
+ value: ./
42
+ dataloader_drop_last:
43
+ desc: null
44
+ value: false
45
+ dataloader_num_workers:
46
+ desc: null
47
+ value: 0
48
+ dataloader_pin_memory:
49
+ desc: null
50
+ value: true
51
+ dataset_config_name:
52
+ desc: null
53
+ value: null
54
+ dataset_name:
55
+ desc: null
56
+ value: null
57
+ ddp_find_unused_parameters:
58
+ desc: null
59
+ value: null
60
+ debug:
61
+ desc: null
62
+ value: []
63
+ deepspeed:
64
+ desc: null
65
+ value: null
66
+ disable_tqdm:
67
+ desc: null
68
+ value: false
69
+ do_eval:
70
+ desc: null
71
+ value: false
72
+ do_predict:
73
+ desc: null
74
+ value: false
75
+ do_train:
76
+ desc: null
77
+ value: false
78
+ dtype:
79
+ desc: null
80
+ value: float32
81
+ eval_accumulation_steps:
82
+ desc: null
83
+ value: null
84
+ eval_steps:
85
+ desc: null
86
+ value: 20000
87
+ evaluation_strategy:
88
+ desc: null
89
+ value: IntervalStrategy.NO
90
+ fp16:
91
+ desc: null
92
+ value: false
93
+ fp16_backend:
94
+ desc: null
95
+ value: auto
96
+ fp16_full_eval:
97
+ desc: null
98
+ value: false
99
+ fp16_opt_level:
100
+ desc: null
101
+ value: O1
102
+ gradient_accumulation_steps:
103
+ desc: null
104
+ value: 1
105
+ greater_is_better:
106
+ desc: null
107
+ value: null
108
+ group_by_length:
109
+ desc: null
110
+ value: false
111
+ ignore_data_skip:
112
+ desc: null
113
+ value: false
114
+ label_names:
115
+ desc: null
116
+ value: null
117
+ label_smoothing_factor:
118
+ desc: null
119
+ value: 0.0
120
+ learning_rate:
121
+ desc: null
122
+ value: 5.0e-05
123
+ length_column_name:
124
+ desc: null
125
+ value: length
126
+ line_by_line:
127
+ desc: null
128
+ value: false
129
+ load_best_model_at_end:
130
+ desc: null
131
+ value: false
132
+ local_rank:
133
+ desc: null
134
+ value: -1
135
+ log_level:
136
+ desc: null
137
+ value: -1
138
+ log_level_replica:
139
+ desc: null
140
+ value: -1
141
+ log_on_each_node:
142
+ desc: null
143
+ value: true
144
+ logging_dir:
145
+ desc: null
146
+ value: ./runs/Jul14_23-11-40_t1v-n-f5c06ea1-w-0
147
+ logging_first_step:
148
+ desc: null
149
+ value: false
150
+ logging_steps:
151
+ desc: null
152
+ value: 500
153
+ logging_strategy:
154
+ desc: null
155
+ value: IntervalStrategy.STEPS
156
+ lr_scheduler_type:
157
+ desc: null
158
+ value: SchedulerType.LINEAR
159
+ max_eval_samples:
160
+ desc: null
161
+ value: 2000
162
+ max_grad_norm:
163
+ desc: null
164
+ value: 1.0
165
+ max_seq_length:
166
+ desc: null
167
+ value: 4096
168
+ max_steps:
169
+ desc: null
170
+ value: -1
171
+ metric_for_best_model:
172
+ desc: null
173
+ value: null
174
+ mlm_probability:
175
+ desc: null
176
+ value: 0.15
177
+ model_name_or_path:
178
+ desc: null
179
+ value: null
180
+ model_type:
181
+ desc: null
182
+ value: big_bird
183
+ mp_parameters:
184
+ desc: null
185
+ value: ''
186
+ no_cuda:
187
+ desc: null
188
+ value: false
189
+ num_train_epochs:
190
+ desc: null
191
+ value: 5.0
192
+ output_dir:
193
+ desc: null
194
+ value: ./
195
+ overwrite_cache:
196
+ desc: null
197
+ value: false
198
+ overwrite_output_dir:
199
+ desc: null
200
+ value: true
201
+ pad_to_max_length:
202
+ desc: null
203
+ value: false
204
+ past_index:
205
+ desc: null
206
+ value: -1
207
+ per_device_eval_batch_size:
208
+ desc: null
209
+ value: 1
210
+ per_device_train_batch_size:
211
+ desc: null
212
+ value: 1
213
+ per_gpu_eval_batch_size:
214
+ desc: null
215
+ value: null
216
+ per_gpu_train_batch_size:
217
+ desc: null
218
+ value: null
219
+ prediction_loss_only:
220
+ desc: null
221
+ value: false
222
+ preprocessing_num_workers:
223
+ desc: null
224
+ value: 96
225
+ push_to_hub:
226
+ desc: null
227
+ value: true
228
+ push_to_hub_model_id:
229
+ desc: null
230
+ value: ''
231
+ push_to_hub_organization:
232
+ desc: null
233
+ value: null
234
+ push_to_hub_token:
235
+ desc: null
236
+ value: null
237
+ remove_unused_columns:
238
+ desc: null
239
+ value: true
240
+ report_to:
241
+ desc: null
242
+ value:
243
+ - tensorboard
244
+ - wandb
245
+ resume_from_checkpoint:
246
+ desc: null
247
+ value: null
248
+ run_name:
249
+ desc: null
250
+ value: ./
251
+ save_on_each_node:
252
+ desc: null
253
+ value: false
254
+ save_optimizer:
255
+ desc: null
256
+ value: true
257
+ save_steps:
258
+ desc: null
259
+ value: 20000
260
+ save_strategy:
261
+ desc: null
262
+ value: IntervalStrategy.STEPS
263
+ save_total_limit:
264
+ desc: null
265
+ value: 5
266
+ seed:
267
+ desc: null
268
+ value: 42
269
+ sharded_ddp:
270
+ desc: null
271
+ value: []
272
+ skip_memory_metrics:
273
+ desc: null
274
+ value: true
275
+ tokenizer_name:
276
+ desc: null
277
+ value: ./
278
+ tpu_metrics_debug:
279
+ desc: null
280
+ value: false
281
+ tpu_num_cores:
282
+ desc: null
283
+ value: null
284
+ train_ref_file:
285
+ desc: null
286
+ value: null
287
+ use_fast_tokenizer:
288
+ desc: null
289
+ value: true
290
+ use_legacy_prediction_loop:
291
+ desc: null
292
+ value: false
293
+ validation_ref_file:
294
+ desc: null
295
+ value: null
296
+ validation_split_percentage:
297
+ desc: null
298
+ value: 5
299
+ warmup_ratio:
300
+ desc: null
301
+ value: 0.0
302
+ warmup_steps:
303
+ desc: null
304
+ value: 10000
305
+ weight_decay:
306
+ desc: null
307
+ value: 0.0095
wandb/run-20210714_231147-gkn68kcy/files/output.log ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ /home/dat/pino/lib/python3.8/site-packages/jax/lib/xla_bridge.py:386: 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/dat/pino/lib/python3.8/site-packages/jax/lib/xla_bridge.py:373: 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 ... (1/5): 0%| | 0/5 [00:00<?, ?it/s]2021-07-14 23:26:04.701487: E external/org_tensorflow/tensorflow/compiler/xla/pjrt/pjrt_stream_executor_client.cc:2036] Execution of replica 0 failed: Resource exhausted: Attempting to allocate 17.0K. That was not possible. There are 48.0K free. Due to fragmentation, the largest contiguous region of free memory is 16.0K.; (0x0x0_HBM0)
6
+ Epoch ... (1/5): 0%| | 0/5 [14:02<?, ?it/s]
7
+ Traceback (most recent call last):
8
+ File "./run_mlm_flax.py", line 806, in <module>
9
+ train_batch_idx = generate_batch_splits(train_samples_idx, train_batch_size // grad_accum_steps)
10
+ File "./run_mlm_flax.py", line 263, in generate_batch_splits
11
+ batch_idx = np.split(samples_idx, sections_split)
12
+ File "<__array_function__ internals>", line 5, in split
13
+ File "/home/dat/pino/lib/python3.8/site-packages/numpy/lib/shape_base.py", line 874, in split
14
+ return array_split(ary, indices_or_sections, axis)
15
+ File "<__array_function__ internals>", line 5, in array_split
16
+ File "/home/dat/pino/lib/python3.8/site-packages/numpy/lib/shape_base.py", line 790, in array_split
17
+ sub_arys.append(_nx.swapaxes(sary[st:end], axis, 0))
18
+ File "/home/dat/pino/lib/python3.8/site-packages/jax/_src/numpy/lax_numpy.py", line 5009, in _rewriting_take
19
+ return _gather(arr, treedef, static_idx, dynamic_idx, indices_are_sorted,
20
+ File "/home/dat/pino/lib/python3.8/site-packages/jax/_src/numpy/lax_numpy.py", line 5028, in _gather
21
+ y = lax.gather(
22
+ File "/home/dat/pino/lib/python3.8/site-packages/jax/_src/lax/lax.py", line 984, in gather
23
+ return gather_p.bind(
24
+ File "/home/dat/pino/lib/python3.8/site-packages/jax/core.py", line 264, in bind
25
+ out = top_trace.process_primitive(self, tracers, params)
26
+ File "/home/dat/pino/lib/python3.8/site-packages/jax/core.py", line 603, in process_primitive
27
+ return primitive.impl(*tracers, **params)
28
+ File "/home/dat/pino/lib/python3.8/site-packages/jax/interpreters/xla.py", line 249, in apply_primitive
29
+ return compiled_fun(*args)
30
+ File "/home/dat/pino/lib/python3.8/site-packages/jax/interpreters/xla.py", line 365, in _execute_compiled_primitive
31
+ out_bufs = compiled.execute(input_bufs)
32
+ RuntimeError: Resource exhausted: Attempting to allocate 17.0K. That was not possible. There are 48.0K free. Due to fragmentation, the largest contiguous region of free memory is 16.0K.; (0x0x0_HBM0)
wandb/run-20210714_231147-gkn68kcy/files/requirements.txt ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ absl-py==0.13.0
2
+ aiohttp==3.7.4.post0
3
+ astunparse==1.6.3
4
+ async-timeout==3.0.1
5
+ attrs==21.2.0
6
+ cachetools==4.2.2
7
+ certifi==2021.5.30
8
+ chardet==4.0.0
9
+ charset-normalizer==2.0.1
10
+ chex==0.0.8
11
+ click==8.0.1
12
+ configparser==5.0.2
13
+ cycler==0.10.0
14
+ datasets==1.9.1.dev0
15
+ dill==0.3.4
16
+ dm-tree==0.1.6
17
+ docker-pycreds==0.4.0
18
+ filelock==3.0.12
19
+ flatbuffers==1.12
20
+ flax==0.3.4
21
+ fsspec==2021.7.0
22
+ gast==0.4.0
23
+ gitdb==4.0.7
24
+ gitpython==3.1.18
25
+ google-auth-oauthlib==0.4.4
26
+ google-auth==1.32.1
27
+ google-pasta==0.2.0
28
+ grpcio==1.34.1
29
+ h5py==3.1.0
30
+ huggingface-hub==0.0.12
31
+ idna==3.2
32
+ install==1.3.4
33
+ jax==0.2.17
34
+ jaxlib==0.1.68
35
+ joblib==1.0.1
36
+ keras-nightly==2.5.0.dev2021032900
37
+ keras-preprocessing==1.1.2
38
+ kiwisolver==1.3.1
39
+ libtpu-nightly==0.1.dev20210615
40
+ markdown==3.3.4
41
+ matplotlib==3.4.2
42
+ msgpack==1.0.2
43
+ multidict==5.1.0
44
+ multiprocess==0.70.12.2
45
+ numpy==1.19.5
46
+ oauthlib==3.1.1
47
+ opt-einsum==3.3.0
48
+ optax==0.0.9
49
+ packaging==21.0
50
+ pandas==1.3.0
51
+ pathtools==0.1.2
52
+ pillow==8.3.1
53
+ pip==20.0.2
54
+ pkg-resources==0.0.0
55
+ promise==2.3
56
+ protobuf==3.17.3
57
+ psutil==5.8.0
58
+ pyarrow==4.0.1
59
+ pyasn1-modules==0.2.8
60
+ pyasn1==0.4.8
61
+ pyparsing==2.4.7
62
+ python-dateutil==2.8.1
63
+ pytz==2021.1
64
+ pyyaml==5.4.1
65
+ regex==2021.7.6
66
+ requests-oauthlib==1.3.0
67
+ requests==2.26.0
68
+ rsa==4.7.2
69
+ sacremoses==0.0.45
70
+ scipy==1.7.0
71
+ sentry-sdk==1.3.0
72
+ setuptools==44.0.0
73
+ shortuuid==1.0.1
74
+ six==1.15.0
75
+ smmap==4.0.0
76
+ subprocess32==3.5.4
77
+ tensorboard-data-server==0.6.1
78
+ tensorboard-plugin-wit==1.8.0
79
+ tensorboard==2.5.0
80
+ tensorflow-estimator==2.5.0
81
+ tensorflow==2.5.0
82
+ termcolor==1.1.0
83
+ tokenizers==0.10.3
84
+ toolz==0.11.1
85
+ tqdm==4.61.2
86
+ transformers==4.9.0.dev0
87
+ typing-extensions==3.7.4.3
88
+ urllib3==1.26.6
89
+ wandb==0.10.33
90
+ werkzeug==2.0.1
91
+ wheel==0.36.2
92
+ wrapt==1.12.1
93
+ xxhash==2.0.2
94
+ yarl==1.6.3
wandb/run-20210714_231147-gkn68kcy/files/wandb-metadata.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "os": "Linux-5.4.0-1043-gcp-x86_64-with-glibc2.29",
3
+ "python": "3.8.10",
4
+ "heartbeatAt": "2021-07-14T23:11:49.155779",
5
+ "startedAt": "2021-07-14T23:11:47.117291",
6
+ "docker": null,
7
+ "cpu_count": 96,
8
+ "cuda": null,
9
+ "args": [
10
+ "--push_to_hub",
11
+ "--output_dir=./",
12
+ "--model_type=big_bird",
13
+ "--config_name=./",
14
+ "--tokenizer_name=./",
15
+ "--max_seq_length=4096",
16
+ "--weight_decay=0.0095",
17
+ "--warmup_steps=10000",
18
+ "--overwrite_output_dir",
19
+ "--adam_beta1=0.9",
20
+ "--adam_beta2=0.98",
21
+ "--logging_steps=500",
22
+ "--eval_steps=20000",
23
+ "--num_train_epochs=5",
24
+ "--preprocessing_num_workers=96",
25
+ "--save_steps=20000",
26
+ "--learning_rate=5e-5",
27
+ "--per_device_train_batch_size=1",
28
+ "--per_device_eval_batch_size=1",
29
+ "--save_total_limit=5",
30
+ "--max_eval_samples=2000",
31
+ "--overwrite_cache",
32
+ "False"
33
+ ],
34
+ "state": "running",
35
+ "program": "./run_mlm_flax.py",
36
+ "codePath": "run_mlm_flax.py",
37
+ "git": {
38
+ "remote": "https://huggingface.co/flax-community/pino-roberta-base",
39
+ "commit": "9915204ae8501d6ae8425aa8f0b4b290cbc7e5b6"
40
+ },
41
+ "email": null,
42
+ "root": "/home/dat/pino-roberta-base",
43
+ "host": "t1v-n-f5c06ea1-w-0",
44
+ "username": "dat",
45
+ "executable": "/home/dat/pino/bin/python"
46
+ }
wandb/run-20210714_231147-gkn68kcy/files/wandb-summary.json ADDED
@@ -0,0 +1 @@
 
1
+ {}
wandb/run-20210714_231147-gkn68kcy/logs/debug-internal.log ADDED
@@ -0,0 +1,279 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2021-07-14 23:11:47,821 INFO MainThread:604064 [internal.py:wandb_internal():88] W&B internal server running at pid: 604064, started at: 2021-07-14 23:11:47.821366
2
+ 2021-07-14 23:11:47,823 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: check_version
3
+ 2021-07-14 23:11:47,824 INFO WriterThread:604064 [datastore.py:open_for_write():80] open: /home/dat/pino-roberta-base/wandb/run-20210714_231147-gkn68kcy/run-gkn68kcy.wandb
4
+ 2021-07-14 23:11:47,824 DEBUG SenderThread:604064 [sender.py:send():179] send: header
5
+ 2021-07-14 23:11:47,825 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: check_version
6
+ 2021-07-14 23:11:47,862 DEBUG SenderThread:604064 [sender.py:send():179] send: run
7
+ 2021-07-14 23:11:48,044 INFO SenderThread:604064 [dir_watcher.py:__init__():168] watching files in: /home/dat/pino-roberta-base/wandb/run-20210714_231147-gkn68kcy/files
8
+ 2021-07-14 23:11:48,044 INFO SenderThread:604064 [sender.py:_start_run_threads():716] run started: gkn68kcy with start time 1626304307
9
+ 2021-07-14 23:11:48,044 DEBUG SenderThread:604064 [sender.py:send():179] send: summary
10
+ 2021-07-14 23:11:48,044 INFO SenderThread:604064 [sender.py:_save_file():841] saving file wandb-summary.json with policy end
11
+ 2021-07-14 23:11:48,045 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: run_start
12
+ 2021-07-14 23:11:49,047 INFO Thread-8 :604064 [dir_watcher.py:_on_file_created():216] file/dir created: /home/dat/pino-roberta-base/wandb/run-20210714_231147-gkn68kcy/files/wandb-summary.json
13
+ 2021-07-14 23:11:49,155 DEBUG HandlerThread:604064 [meta.py:__init__():39] meta init
14
+ 2021-07-14 23:11:49,155 DEBUG HandlerThread:604064 [meta.py:__init__():53] meta init done
15
+ 2021-07-14 23:11:49,155 DEBUG HandlerThread:604064 [meta.py:probe():210] probe
16
+ 2021-07-14 23:11:49,156 DEBUG HandlerThread:604064 [meta.py:_setup_git():200] setup git
17
+ 2021-07-14 23:11:49,187 DEBUG HandlerThread:604064 [meta.py:_setup_git():207] setup git done
18
+ 2021-07-14 23:11:49,188 DEBUG HandlerThread:604064 [meta.py:_save_pip():57] save pip
19
+ 2021-07-14 23:11:49,188 DEBUG HandlerThread:604064 [meta.py:_save_pip():71] save pip done
20
+ 2021-07-14 23:11:49,188 DEBUG HandlerThread:604064 [meta.py:probe():252] probe done
21
+ 2021-07-14 23:11:49,192 DEBUG SenderThread:604064 [sender.py:send():179] send: files
22
+ 2021-07-14 23:11:49,192 INFO SenderThread:604064 [sender.py:_save_file():841] saving file wandb-metadata.json with policy now
23
+ 2021-07-14 23:11:49,199 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
24
+ 2021-07-14 23:11:49,200 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
25
+ 2021-07-14 23:11:49,336 DEBUG SenderThread:604064 [sender.py:send():179] send: config
26
+ 2021-07-14 23:11:49,336 DEBUG SenderThread:604064 [sender.py:send():179] send: config
27
+ 2021-07-14 23:11:49,337 DEBUG SenderThread:604064 [sender.py:send():179] send: config
28
+ 2021-07-14 23:11:49,685 INFO Thread-11 :604064 [upload_job.py:push():137] Uploaded file /tmp/tmpnh56hsgtwandb/3jt8aozu-wandb-metadata.json
29
+ 2021-07-14 23:11:50,046 INFO Thread-8 :604064 [dir_watcher.py:_on_file_created():216] file/dir created: /home/dat/pino-roberta-base/wandb/run-20210714_231147-gkn68kcy/files/output.log
30
+ 2021-07-14 23:11:50,046 INFO Thread-8 :604064 [dir_watcher.py:_on_file_created():216] file/dir created: /home/dat/pino-roberta-base/wandb/run-20210714_231147-gkn68kcy/files/requirements.txt
31
+ 2021-07-14 23:11:50,046 INFO Thread-8 :604064 [dir_watcher.py:_on_file_created():216] file/dir created: /home/dat/pino-roberta-base/wandb/run-20210714_231147-gkn68kcy/files/wandb-metadata.json
32
+ 2021-07-14 23:12:04,051 INFO Thread-8 :604064 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210714_231147-gkn68kcy/files/output.log
33
+ 2021-07-14 23:12:04,338 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
34
+ 2021-07-14 23:12:04,339 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
35
+ 2021-07-14 23:12:17,233 DEBUG SenderThread:604064 [sender.py:send():179] send: stats
36
+ 2021-07-14 23:12:19,058 INFO Thread-8 :604064 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210714_231147-gkn68kcy/files/config.yaml
37
+ 2021-07-14 23:12:19,470 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
38
+ 2021-07-14 23:12:19,471 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
39
+ 2021-07-14 23:12:34,607 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
40
+ 2021-07-14 23:12:34,607 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
41
+ 2021-07-14 23:12:47,304 DEBUG SenderThread:604064 [sender.py:send():179] send: stats
42
+ 2021-07-14 23:12:49,759 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
43
+ 2021-07-14 23:12:49,760 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
44
+ 2021-07-14 23:13:04,899 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
45
+ 2021-07-14 23:13:04,899 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
46
+ 2021-07-14 23:13:17,375 DEBUG SenderThread:604064 [sender.py:send():179] send: stats
47
+ 2021-07-14 23:13:20,032 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
48
+ 2021-07-14 23:13:20,032 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
49
+ 2021-07-14 23:13:35,167 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
50
+ 2021-07-14 23:13:35,168 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
51
+ 2021-07-14 23:13:47,450 DEBUG SenderThread:604064 [sender.py:send():179] send: stats
52
+ 2021-07-14 23:13:50,301 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
53
+ 2021-07-14 23:13:50,301 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
54
+ 2021-07-14 23:14:05,433 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
55
+ 2021-07-14 23:14:05,434 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
56
+ 2021-07-14 23:14:17,527 DEBUG SenderThread:604064 [sender.py:send():179] send: stats
57
+ 2021-07-14 23:14:20,564 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
58
+ 2021-07-14 23:14:20,564 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
59
+ 2021-07-14 23:14:35,694 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
60
+ 2021-07-14 23:14:35,695 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
61
+ 2021-07-14 23:14:47,605 DEBUG SenderThread:604064 [sender.py:send():179] send: stats
62
+ 2021-07-14 23:14:50,827 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
63
+ 2021-07-14 23:14:50,827 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
64
+ 2021-07-14 23:15:05,965 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
65
+ 2021-07-14 23:15:05,965 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
66
+ 2021-07-14 23:15:17,682 DEBUG SenderThread:604064 [sender.py:send():179] send: stats
67
+ 2021-07-14 23:15:21,099 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
68
+ 2021-07-14 23:15:21,100 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
69
+ 2021-07-14 23:15:36,236 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
70
+ 2021-07-14 23:15:36,237 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
71
+ 2021-07-14 23:15:47,752 DEBUG SenderThread:604064 [sender.py:send():179] send: stats
72
+ 2021-07-14 23:15:51,383 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
73
+ 2021-07-14 23:15:51,384 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
74
+ 2021-07-14 23:16:06,514 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
75
+ 2021-07-14 23:16:06,515 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
76
+ 2021-07-14 23:16:17,832 DEBUG SenderThread:604064 [sender.py:send():179] send: stats
77
+ 2021-07-14 23:16:21,647 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
78
+ 2021-07-14 23:16:21,647 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
79
+ 2021-07-14 23:16:36,777 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
80
+ 2021-07-14 23:16:36,778 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
81
+ 2021-07-14 23:16:47,906 DEBUG SenderThread:604064 [sender.py:send():179] send: stats
82
+ 2021-07-14 23:16:51,911 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
83
+ 2021-07-14 23:16:51,911 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
84
+ 2021-07-14 23:17:07,045 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
85
+ 2021-07-14 23:17:07,045 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
86
+ 2021-07-14 23:17:17,984 DEBUG SenderThread:604064 [sender.py:send():179] send: stats
87
+ 2021-07-14 23:17:22,180 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
88
+ 2021-07-14 23:17:22,180 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
89
+ 2021-07-14 23:17:37,312 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
90
+ 2021-07-14 23:17:37,313 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
91
+ 2021-07-14 23:17:48,061 DEBUG SenderThread:604064 [sender.py:send():179] send: stats
92
+ 2021-07-14 23:17:52,447 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
93
+ 2021-07-14 23:17:52,447 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
94
+ 2021-07-14 23:18:07,584 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
95
+ 2021-07-14 23:18:07,584 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
96
+ 2021-07-14 23:18:18,134 DEBUG SenderThread:604064 [sender.py:send():179] send: stats
97
+ 2021-07-14 23:18:22,718 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
98
+ 2021-07-14 23:18:22,718 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
99
+ 2021-07-14 23:18:37,852 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
100
+ 2021-07-14 23:18:37,852 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
101
+ 2021-07-14 23:18:48,202 DEBUG SenderThread:604064 [sender.py:send():179] send: stats
102
+ 2021-07-14 23:18:52,983 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
103
+ 2021-07-14 23:18:52,984 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
104
+ 2021-07-14 23:19:08,118 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
105
+ 2021-07-14 23:19:08,118 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
106
+ 2021-07-14 23:19:18,280 DEBUG SenderThread:604064 [sender.py:send():179] send: stats
107
+ 2021-07-14 23:19:23,249 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
108
+ 2021-07-14 23:19:23,249 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
109
+ 2021-07-14 23:19:38,406 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
110
+ 2021-07-14 23:19:38,407 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
111
+ 2021-07-14 23:19:48,357 DEBUG SenderThread:604064 [sender.py:send():179] send: stats
112
+ 2021-07-14 23:19:53,538 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
113
+ 2021-07-14 23:19:53,539 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
114
+ 2021-07-14 23:20:08,668 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
115
+ 2021-07-14 23:20:08,668 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
116
+ 2021-07-14 23:20:18,431 DEBUG SenderThread:604064 [sender.py:send():179] send: stats
117
+ 2021-07-14 23:20:23,808 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
118
+ 2021-07-14 23:20:23,809 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
119
+ 2021-07-14 23:20:38,943 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
120
+ 2021-07-14 23:20:38,943 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
121
+ 2021-07-14 23:20:48,507 DEBUG SenderThread:604064 [sender.py:send():179] send: stats
122
+ 2021-07-14 23:20:54,079 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
123
+ 2021-07-14 23:20:54,079 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
124
+ 2021-07-14 23:21:09,222 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
125
+ 2021-07-14 23:21:09,223 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
126
+ 2021-07-14 23:21:18,586 DEBUG SenderThread:604064 [sender.py:send():179] send: stats
127
+ 2021-07-14 23:21:24,353 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
128
+ 2021-07-14 23:21:24,354 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
129
+ 2021-07-14 23:21:39,483 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
130
+ 2021-07-14 23:21:39,484 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
131
+ 2021-07-14 23:21:48,663 DEBUG SenderThread:604064 [sender.py:send():179] send: stats
132
+ 2021-07-14 23:21:55,394 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
133
+ 2021-07-14 23:21:55,394 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
134
+ 2021-07-14 23:22:10,527 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
135
+ 2021-07-14 23:22:10,528 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
136
+ 2021-07-14 23:22:18,741 DEBUG SenderThread:604064 [sender.py:send():179] send: stats
137
+ 2021-07-14 23:22:25,659 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
138
+ 2021-07-14 23:22:25,659 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
139
+ 2021-07-14 23:22:40,790 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
140
+ 2021-07-14 23:22:40,790 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
141
+ 2021-07-14 23:22:48,820 DEBUG SenderThread:604064 [sender.py:send():179] send: stats
142
+ 2021-07-14 23:22:55,922 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
143
+ 2021-07-14 23:22:55,923 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
144
+ 2021-07-14 23:23:11,058 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
145
+ 2021-07-14 23:23:11,059 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
146
+ 2021-07-14 23:23:18,897 DEBUG SenderThread:604064 [sender.py:send():179] send: stats
147
+ 2021-07-14 23:23:26,197 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
148
+ 2021-07-14 23:23:26,198 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
149
+ 2021-07-14 23:23:41,329 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
150
+ 2021-07-14 23:23:41,329 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
151
+ 2021-07-14 23:23:48,974 DEBUG SenderThread:604064 [sender.py:send():179] send: stats
152
+ 2021-07-14 23:23:56,463 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
153
+ 2021-07-14 23:23:56,463 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
154
+ 2021-07-14 23:24:11,593 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
155
+ 2021-07-14 23:24:11,593 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
156
+ 2021-07-14 23:24:19,051 DEBUG SenderThread:604064 [sender.py:send():179] send: stats
157
+ 2021-07-14 23:24:26,724 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
158
+ 2021-07-14 23:24:26,724 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
159
+ 2021-07-14 23:24:41,858 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
160
+ 2021-07-14 23:24:41,858 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
161
+ 2021-07-14 23:24:49,130 DEBUG SenderThread:604064 [sender.py:send():179] send: stats
162
+ 2021-07-14 23:24:56,991 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
163
+ 2021-07-14 23:24:56,991 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
164
+ 2021-07-14 23:25:12,121 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
165
+ 2021-07-14 23:25:12,122 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
166
+ 2021-07-14 23:25:19,207 DEBUG SenderThread:604064 [sender.py:send():179] send: stats
167
+ 2021-07-14 23:25:27,253 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
168
+ 2021-07-14 23:25:27,254 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
169
+ 2021-07-14 23:25:42,385 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
170
+ 2021-07-14 23:25:42,386 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
171
+ 2021-07-14 23:25:49,284 DEBUG SenderThread:604064 [sender.py:send():179] send: stats
172
+ 2021-07-14 23:25:57,527 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: stop_status
173
+ 2021-07-14 23:25:57,527 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: stop_status
174
+ 2021-07-14 23:26:06,351 INFO Thread-8 :604064 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210714_231147-gkn68kcy/files/output.log
175
+ 2021-07-14 23:26:07,081 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: poll_exit
176
+ 2021-07-14 23:26:07,082 DEBUG SenderThread:604064 [sender.py:send():179] send: telemetry
177
+ 2021-07-14 23:26:07,082 DEBUG SenderThread:604064 [sender.py:send():179] send: exit
178
+ 2021-07-14 23:26:07,082 INFO SenderThread:604064 [sender.py:send_exit():287] handling exit code: 1
179
+ 2021-07-14 23:26:07,083 INFO SenderThread:604064 [sender.py:send_exit():295] send defer
180
+ 2021-07-14 23:26:07,084 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: poll_exit
181
+ 2021-07-14 23:26:07,084 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: defer
182
+ 2021-07-14 23:26:07,085 INFO HandlerThread:604064 [handler.py:handle_request_defer():141] handle defer: 0
183
+ 2021-07-14 23:26:07,085 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: defer
184
+ 2021-07-14 23:26:07,085 INFO SenderThread:604064 [sender.py:send_request_defer():304] handle sender defer: 0
185
+ 2021-07-14 23:26:07,085 INFO SenderThread:604064 [sender.py:transition_state():308] send defer: 1
186
+ 2021-07-14 23:26:07,085 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: defer
187
+ 2021-07-14 23:26:07,085 INFO HandlerThread:604064 [handler.py:handle_request_defer():141] handle defer: 1
188
+ 2021-07-14 23:26:07,130 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: defer
189
+ 2021-07-14 23:26:07,130 INFO SenderThread:604064 [sender.py:send_request_defer():304] handle sender defer: 1
190
+ 2021-07-14 23:26:07,130 INFO SenderThread:604064 [sender.py:transition_state():308] send defer: 2
191
+ 2021-07-14 23:26:07,131 DEBUG SenderThread:604064 [sender.py:send():179] send: stats
192
+ 2021-07-14 23:26:07,131 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: defer
193
+ 2021-07-14 23:26:07,131 INFO HandlerThread:604064 [handler.py:handle_request_defer():141] handle defer: 2
194
+ 2021-07-14 23:26:07,132 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: defer
195
+ 2021-07-14 23:26:07,132 INFO SenderThread:604064 [sender.py:send_request_defer():304] handle sender defer: 2
196
+ 2021-07-14 23:26:07,132 INFO SenderThread:604064 [sender.py:transition_state():308] send defer: 3
197
+ 2021-07-14 23:26:07,132 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: defer
198
+ 2021-07-14 23:26:07,132 INFO HandlerThread:604064 [handler.py:handle_request_defer():141] handle defer: 3
199
+ 2021-07-14 23:26:07,132 DEBUG SenderThread:604064 [sender.py:send():179] send: summary
200
+ 2021-07-14 23:26:07,133 INFO SenderThread:604064 [sender.py:_save_file():841] saving file wandb-summary.json with policy end
201
+ 2021-07-14 23:26:07,133 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: defer
202
+ 2021-07-14 23:26:07,133 INFO SenderThread:604064 [sender.py:send_request_defer():304] handle sender defer: 3
203
+ 2021-07-14 23:26:07,133 INFO SenderThread:604064 [sender.py:transition_state():308] send defer: 4
204
+ 2021-07-14 23:26:07,134 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: defer
205
+ 2021-07-14 23:26:07,134 INFO HandlerThread:604064 [handler.py:handle_request_defer():141] handle defer: 4
206
+ 2021-07-14 23:26:07,134 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: defer
207
+ 2021-07-14 23:26:07,134 INFO SenderThread:604064 [sender.py:send_request_defer():304] handle sender defer: 4
208
+ 2021-07-14 23:26:07,228 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: poll_exit
209
+ 2021-07-14 23:26:07,305 INFO SenderThread:604064 [sender.py:transition_state():308] send defer: 5
210
+ 2021-07-14 23:26:07,305 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: poll_exit
211
+ 2021-07-14 23:26:07,306 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: defer
212
+ 2021-07-14 23:26:07,306 INFO HandlerThread:604064 [handler.py:handle_request_defer():141] handle defer: 5
213
+ 2021-07-14 23:26:07,306 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: defer
214
+ 2021-07-14 23:26:07,306 INFO SenderThread:604064 [sender.py:send_request_defer():304] handle sender defer: 5
215
+ 2021-07-14 23:26:07,306 INFO SenderThread:604064 [dir_watcher.py:finish():282] shutting down directory watcher
216
+ 2021-07-14 23:26:07,351 INFO Thread-8 :604064 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210714_231147-gkn68kcy/files/config.yaml
217
+ 2021-07-14 23:26:07,351 INFO SenderThread:604064 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210714_231147-gkn68kcy/files/output.log
218
+ 2021-07-14 23:26:07,352 INFO SenderThread:604064 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210714_231147-gkn68kcy/files/wandb-summary.json
219
+ 2021-07-14 23:26:07,352 INFO SenderThread:604064 [dir_watcher.py:finish():312] scan: /home/dat/pino-roberta-base/wandb/run-20210714_231147-gkn68kcy/files
220
+ 2021-07-14 23:26:07,352 INFO SenderThread:604064 [dir_watcher.py:finish():318] scan save: /home/dat/pino-roberta-base/wandb/run-20210714_231147-gkn68kcy/files/requirements.txt requirements.txt
221
+ 2021-07-14 23:26:07,352 INFO SenderThread:604064 [dir_watcher.py:finish():318] scan save: /home/dat/pino-roberta-base/wandb/run-20210714_231147-gkn68kcy/files/output.log output.log
222
+ 2021-07-14 23:26:07,352 INFO SenderThread:604064 [dir_watcher.py:finish():318] scan save: /home/dat/pino-roberta-base/wandb/run-20210714_231147-gkn68kcy/files/wandb-metadata.json wandb-metadata.json
223
+ 2021-07-14 23:26:07,352 INFO SenderThread:604064 [dir_watcher.py:finish():318] scan save: /home/dat/pino-roberta-base/wandb/run-20210714_231147-gkn68kcy/files/config.yaml config.yaml
224
+ 2021-07-14 23:26:07,356 INFO SenderThread:604064 [dir_watcher.py:finish():318] scan save: /home/dat/pino-roberta-base/wandb/run-20210714_231147-gkn68kcy/files/wandb-summary.json wandb-summary.json
225
+ 2021-07-14 23:26:07,359 INFO SenderThread:604064 [sender.py:transition_state():308] send defer: 6
226
+ 2021-07-14 23:26:07,360 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: defer
227
+ 2021-07-14 23:26:07,360 INFO HandlerThread:604064 [handler.py:handle_request_defer():141] handle defer: 6
228
+ 2021-07-14 23:26:07,360 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: defer
229
+ 2021-07-14 23:26:07,361 INFO SenderThread:604064 [sender.py:send_request_defer():304] handle sender defer: 6
230
+ 2021-07-14 23:26:07,361 INFO SenderThread:604064 [file_pusher.py:finish():177] shutting down file pusher
231
+ 2021-07-14 23:26:07,407 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: poll_exit
232
+ 2021-07-14 23:26:07,408 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: poll_exit
233
+ 2021-07-14 23:26:07,513 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: poll_exit
234
+ 2021-07-14 23:26:07,514 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: poll_exit
235
+ 2021-07-14 23:26:07,616 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: poll_exit
236
+ 2021-07-14 23:26:07,616 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: poll_exit
237
+ 2021-07-14 23:26:07,718 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: poll_exit
238
+ 2021-07-14 23:26:07,718 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: poll_exit
239
+ 2021-07-14 23:26:07,820 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: poll_exit
240
+ 2021-07-14 23:26:07,820 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: poll_exit
241
+ 2021-07-14 23:26:07,840 INFO Thread-14 :604064 [upload_job.py:push():137] Uploaded file /home/dat/pino-roberta-base/wandb/run-20210714_231147-gkn68kcy/files/config.yaml
242
+ 2021-07-14 23:26:07,841 INFO Thread-13 :604064 [upload_job.py:push():137] Uploaded file /home/dat/pino-roberta-base/wandb/run-20210714_231147-gkn68kcy/files/output.log
243
+ 2021-07-14 23:26:07,874 INFO Thread-12 :604064 [upload_job.py:push():137] Uploaded file /home/dat/pino-roberta-base/wandb/run-20210714_231147-gkn68kcy/files/requirements.txt
244
+ 2021-07-14 23:26:07,875 INFO Thread-15 :604064 [upload_job.py:push():137] Uploaded file /home/dat/pino-roberta-base/wandb/run-20210714_231147-gkn68kcy/files/wandb-summary.json
245
+ 2021-07-14 23:26:07,922 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: poll_exit
246
+ 2021-07-14 23:26:07,922 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: poll_exit
247
+ 2021-07-14 23:26:08,024 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: poll_exit
248
+ 2021-07-14 23:26:08,024 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: poll_exit
249
+ 2021-07-14 23:26:08,076 INFO Thread-7 :604064 [sender.py:transition_state():308] send defer: 7
250
+ 2021-07-14 23:26:08,077 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: defer
251
+ 2021-07-14 23:26:08,077 INFO HandlerThread:604064 [handler.py:handle_request_defer():141] handle defer: 7
252
+ 2021-07-14 23:26:08,077 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: defer
253
+ 2021-07-14 23:26:08,077 INFO SenderThread:604064 [sender.py:send_request_defer():304] handle sender defer: 7
254
+ 2021-07-14 23:26:08,126 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: poll_exit
255
+ 2021-07-14 23:26:08,360 INFO SenderThread:604064 [sender.py:transition_state():308] send defer: 8
256
+ 2021-07-14 23:26:08,360 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: poll_exit
257
+ 2021-07-14 23:26:08,361 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: defer
258
+ 2021-07-14 23:26:08,361 INFO HandlerThread:604064 [handler.py:handle_request_defer():141] handle defer: 8
259
+ 2021-07-14 23:26:08,361 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: defer
260
+ 2021-07-14 23:26:08,361 INFO SenderThread:604064 [sender.py:send_request_defer():304] handle sender defer: 8
261
+ 2021-07-14 23:26:08,361 INFO SenderThread:604064 [sender.py:transition_state():308] send defer: 9
262
+ 2021-07-14 23:26:08,362 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: defer
263
+ 2021-07-14 23:26:08,362 INFO HandlerThread:604064 [handler.py:handle_request_defer():141] handle defer: 9
264
+ 2021-07-14 23:26:08,362 DEBUG SenderThread:604064 [sender.py:send():179] send: final
265
+ 2021-07-14 23:26:08,362 DEBUG SenderThread:604064 [sender.py:send():179] send: footer
266
+ 2021-07-14 23:26:08,362 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: defer
267
+ 2021-07-14 23:26:08,362 INFO SenderThread:604064 [sender.py:send_request_defer():304] handle sender defer: 9
268
+ 2021-07-14 23:26:08,462 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: poll_exit
269
+ 2021-07-14 23:26:08,462 DEBUG SenderThread:604064 [sender.py:send_request():193] send_request: poll_exit
270
+ 2021-07-14 23:26:08,463 INFO SenderThread:604064 [file_pusher.py:join():182] waiting for file pusher
271
+ 2021-07-14 23:26:08,464 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: get_summary
272
+ 2021-07-14 23:26:08,465 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: sampled_history
273
+ 2021-07-14 23:26:08,465 DEBUG HandlerThread:604064 [handler.py:handle_request():124] handle_request: shutdown
274
+ 2021-07-14 23:26:08,465 INFO HandlerThread:604064 [handler.py:finish():638] shutting down handler
275
+ 2021-07-14 23:26:09,363 INFO WriterThread:604064 [datastore.py:close():288] close: /home/dat/pino-roberta-base/wandb/run-20210714_231147-gkn68kcy/run-gkn68kcy.wandb
276
+ 2021-07-14 23:26:09,463 INFO SenderThread:604064 [sender.py:finish():945] shutting down sender
277
+ 2021-07-14 23:26:09,463 INFO SenderThread:604064 [file_pusher.py:finish():177] shutting down file pusher
278
+ 2021-07-14 23:26:09,463 INFO SenderThread:604064 [file_pusher.py:join():182] waiting for file pusher
279
+ 2021-07-14 23:26:09,466 INFO MainThread:604064 [internal.py:handle_exit():78] Internal process exited
wandb/run-20210714_231147-gkn68kcy/logs/debug.log ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2021-07-14 23:11:47,119 INFO MainThread:602807 [wandb_setup.py:_flush():69] setting env: {}
2
+ 2021-07-14 23:11:47,119 INFO MainThread:602807 [wandb_setup.py:_flush():69] setting login settings: {}
3
+ 2021-07-14 23:11:47,119 INFO MainThread:602807 [wandb_init.py:_log_setup():337] Logging user logs to /home/dat/pino-roberta-base/wandb/run-20210714_231147-gkn68kcy/logs/debug.log
4
+ 2021-07-14 23:11:47,119 INFO MainThread:602807 [wandb_init.py:_log_setup():338] Logging internal logs to /home/dat/pino-roberta-base/wandb/run-20210714_231147-gkn68kcy/logs/debug-internal.log
5
+ 2021-07-14 23:11:47,119 INFO MainThread:602807 [wandb_init.py:init():370] calling init triggers
6
+ 2021-07-14 23:11:47,119 INFO MainThread:602807 [wandb_init.py:init():375] wandb.init called with sweep_config: {}
7
+ config: {}
8
+ 2021-07-14 23:11:47,119 INFO MainThread:602807 [wandb_init.py:init():419] starting backend
9
+ 2021-07-14 23:11:47,120 INFO MainThread:602807 [backend.py:_multiprocessing_setup():70] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
10
+ 2021-07-14 23:11:47,167 INFO MainThread:602807 [backend.py:ensure_launched():135] starting backend process...
11
+ 2021-07-14 23:11:47,212 INFO MainThread:602807 [backend.py:ensure_launched():139] started backend process with pid: 604064
12
+ 2021-07-14 23:11:47,214 INFO MainThread:602807 [wandb_init.py:init():424] backend started and connected
13
+ 2021-07-14 23:11:47,217 INFO MainThread:602807 [wandb_init.py:init():472] updated telemetry
14
+ 2021-07-14 23:11:47,218 INFO MainThread:602807 [wandb_init.py:init():491] communicating current version
15
+ 2021-07-14 23:11:47,860 INFO MainThread:602807 [wandb_init.py:init():496] got version response
16
+ 2021-07-14 23:11:47,860 INFO MainThread:602807 [wandb_init.py:init():504] communicating run to backend with 30 second timeout
17
+ 2021-07-14 23:11:48,044 INFO MainThread:602807 [wandb_init.py:init():529] starting run threads in backend
18
+ 2021-07-14 23:11:49,195 INFO MainThread:602807 [wandb_run.py:_console_start():1623] atexit reg
19
+ 2021-07-14 23:11:49,196 INFO MainThread:602807 [wandb_run.py:_redirect():1497] redirect: SettingsConsole.REDIRECT
20
+ 2021-07-14 23:11:49,196 INFO MainThread:602807 [wandb_run.py:_redirect():1502] Redirecting console.
21
+ 2021-07-14 23:11:49,199 INFO MainThread:602807 [wandb_run.py:_redirect():1558] Redirects installed.
22
+ 2021-07-14 23:11:49,199 INFO MainThread:602807 [wandb_init.py:init():554] run started, returning control to user process
23
+ 2021-07-14 23:11:49,207 INFO MainThread:602807 [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': 1, 'per_device_eval_batch_size': 1, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'learning_rate': 5e-05, 'weight_decay': 0.0095, 'adam_beta1': 0.9, 'adam_beta2': 0.98, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 5.0, 'max_steps': -1, 'lr_scheduler_type': 'SchedulerType.LINEAR', 'warmup_ratio': 0.0, 'warmup_steps': 10000, 'log_level': -1, 'log_level_replica': -1, 'log_on_each_node': True, 'logging_dir': './runs/Jul14_23-11-40_t1v-n-f5c06ea1-w-0', 'logging_strategy': 'IntervalStrategy.STEPS', 'logging_first_step': False, 'logging_steps': 500, 'save_strategy': 'IntervalStrategy.STEPS', 'save_steps': 20000, 'save_total_limit': 5, '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': 20000, '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': True, 'resume_from_checkpoint': None, 'push_to_hub_model_id': '', 'push_to_hub_organization': None, 'push_to_hub_token': None, 'mp_parameters': ''}
24
+ 2021-07-14 23:11:49,209 INFO MainThread:602807 [wandb_run.py:_config_callback():872] config_cb None None {'model_name_or_path': None, 'model_type': 'big_bird', 'config_name': './', 'tokenizer_name': './', 'cache_dir': None, 'use_fast_tokenizer': True, 'dtype': 'float32', 'save_optimizer': True}
25
+ 2021-07-14 23:11:49,210 INFO MainThread:602807 [wandb_run.py:_config_callback():872] config_cb None None {'dataset_name': None, 'dataset_config_name': None, 'train_ref_file': None, 'validation_ref_file': None, 'overwrite_cache': False, 'validation_split_percentage': 5, 'max_seq_length': 4096, 'preprocessing_num_workers': 96, 'mlm_probability': 0.15, 'pad_to_max_length': False, 'line_by_line': False, 'max_eval_samples': 2000}
26
+ 2021-07-14 23:26:04,706 INFO MainThread:602807 [wandb_run.py:_atexit_cleanup():1593] got exitcode: 1
27
+ 2021-07-14 23:26:04,707 INFO MainThread:602807 [wandb_run.py:_restore():1565] restore
28
+ 2021-07-14 23:26:07,085 INFO MainThread:602807 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
29
+ wandb_count: 1
30
+ }
31
+ pusher_stats {
32
+ uploaded_bytes: 1405
33
+ total_bytes: 1405
34
+ }
35
+
36
+ 2021-07-14 23:26:07,306 INFO MainThread:602807 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
37
+ wandb_count: 1
38
+ }
39
+ pusher_stats {
40
+ uploaded_bytes: 1405
41
+ total_bytes: 1405
42
+ }
43
+
44
+ 2021-07-14 23:26:07,408 INFO MainThread:602807 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
45
+ wandb_count: 5
46
+ }
47
+ pusher_stats {
48
+ uploaded_bytes: 1405
49
+ total_bytes: 10798
50
+ }
51
+
52
+ 2021-07-14 23:26:07,515 INFO MainThread:602807 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
53
+ wandb_count: 5
54
+ }
55
+ pusher_stats {
56
+ uploaded_bytes: 1405
57
+ total_bytes: 10798
58
+ }
59
+
60
+ 2021-07-14 23:26:07,617 INFO MainThread:602807 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
61
+ wandb_count: 5
62
+ }
63
+ pusher_stats {
64
+ uploaded_bytes: 10798
65
+ total_bytes: 10798
66
+ }
67
+
68
+ 2021-07-14 23:26:07,719 INFO MainThread:602807 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
69
+ wandb_count: 5
70
+ }
71
+ pusher_stats {
72
+ uploaded_bytes: 10798
73
+ total_bytes: 10798
74
+ }
75
+
76
+ 2021-07-14 23:26:07,821 INFO MainThread:602807 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
77
+ wandb_count: 5
78
+ }
79
+ pusher_stats {
80
+ uploaded_bytes: 10798
81
+ total_bytes: 10798
82
+ }
83
+
84
+ 2021-07-14 23:26:07,923 INFO MainThread:602807 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
85
+ wandb_count: 5
86
+ }
87
+ pusher_stats {
88
+ uploaded_bytes: 10798
89
+ total_bytes: 10798
90
+ }
91
+
92
+ 2021-07-14 23:26:08,025 INFO MainThread:602807 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
93
+ wandb_count: 5
94
+ }
95
+ pusher_stats {
96
+ uploaded_bytes: 10798
97
+ total_bytes: 10798
98
+ }
99
+
100
+ 2021-07-14 23:26:08,361 INFO MainThread:602807 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
101
+ wandb_count: 5
102
+ }
103
+ pusher_stats {
104
+ uploaded_bytes: 10798
105
+ total_bytes: 10798
106
+ }
107
+
108
+ 2021-07-14 23:26:08,463 INFO MainThread:602807 [wandb_run.py:_wait_for_finish():1715] got exit ret: done: true
109
+ exit_result {
110
+ }
111
+ file_counts {
112
+ wandb_count: 5
113
+ }
114
+ pusher_stats {
115
+ uploaded_bytes: 10798
116
+ total_bytes: 10798
117
+ }
118
+
119
+ 2021-07-14 23:26:09,799 INFO MainThread:602807 [wandb_run.py:_show_files():1937] logging synced files
wandb/run-20210714_231147-gkn68kcy/run-gkn68kcy.wandb ADDED
Binary file (13.4 kB). View file
wandb/run-20210714_232703-1jijl27o/files/config.yaml ADDED
@@ -0,0 +1,307 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ - 3
15
+ - 11
16
+ 2:
17
+ - 3
18
+ - 11
19
+ 4: 3.8.10
20
+ 5: 0.10.33
21
+ 6: 4.9.0.dev0
22
+ 8:
23
+ - 5
24
+ adafactor:
25
+ desc: null
26
+ value: false
27
+ adam_beta1:
28
+ desc: null
29
+ value: 0.9
30
+ adam_beta2:
31
+ desc: null
32
+ value: 0.98
33
+ adam_epsilon:
34
+ desc: null
35
+ value: 1.0e-08
36
+ cache_dir:
37
+ desc: null
38
+ value: null
39
+ config_name:
40
+ desc: null
41
+ value: ./
42
+ dataloader_drop_last:
43
+ desc: null
44
+ value: false
45
+ dataloader_num_workers:
46
+ desc: null
47
+ value: 0
48
+ dataloader_pin_memory:
49
+ desc: null
50
+ value: true
51
+ dataset_config_name:
52
+ desc: null
53
+ value: null
54
+ dataset_name:
55
+ desc: null
56
+ value: null
57
+ ddp_find_unused_parameters:
58
+ desc: null
59
+ value: null
60
+ debug:
61
+ desc: null
62
+ value: []
63
+ deepspeed:
64
+ desc: null
65
+ value: null
66
+ disable_tqdm:
67
+ desc: null
68
+ value: false
69
+ do_eval:
70
+ desc: null
71
+ value: false
72
+ do_predict:
73
+ desc: null
74
+ value: false
75
+ do_train:
76
+ desc: null
77
+ value: false
78
+ dtype:
79
+ desc: null
80
+ value: float32
81
+ eval_accumulation_steps:
82
+ desc: null
83
+ value: null
84
+ eval_steps:
85
+ desc: null
86
+ value: 20000
87
+ evaluation_strategy:
88
+ desc: null
89
+ value: IntervalStrategy.NO
90
+ fp16:
91
+ desc: null
92
+ value: false
93
+ fp16_backend:
94
+ desc: null
95
+ value: auto
96
+ fp16_full_eval:
97
+ desc: null
98
+ value: false
99
+ fp16_opt_level:
100
+ desc: null
101
+ value: O1
102
+ gradient_accumulation_steps:
103
+ desc: null
104
+ value: 4
105
+ greater_is_better:
106
+ desc: null
107
+ value: null
108
+ group_by_length:
109
+ desc: null
110
+ value: false
111
+ ignore_data_skip:
112
+ desc: null
113
+ value: false
114
+ label_names:
115
+ desc: null
116
+ value: null
117
+ label_smoothing_factor:
118
+ desc: null
119
+ value: 0.0
120
+ learning_rate:
121
+ desc: null
122
+ value: 5.0e-05
123
+ length_column_name:
124
+ desc: null
125
+ value: length
126
+ line_by_line:
127
+ desc: null
128
+ value: false
129
+ load_best_model_at_end:
130
+ desc: null
131
+ value: false
132
+ local_rank:
133
+ desc: null
134
+ value: -1
135
+ log_level:
136
+ desc: null
137
+ value: -1
138
+ log_level_replica:
139
+ desc: null
140
+ value: -1
141
+ log_on_each_node:
142
+ desc: null
143
+ value: true
144
+ logging_dir:
145
+ desc: null
146
+ value: ./runs/Jul14_23-26-56_t1v-n-f5c06ea1-w-0
147
+ logging_first_step:
148
+ desc: null
149
+ value: false
150
+ logging_steps:
151
+ desc: null
152
+ value: 500
153
+ logging_strategy:
154
+ desc: null
155
+ value: IntervalStrategy.STEPS
156
+ lr_scheduler_type:
157
+ desc: null
158
+ value: SchedulerType.LINEAR
159
+ max_eval_samples:
160
+ desc: null
161
+ value: 2000
162
+ max_grad_norm:
163
+ desc: null
164
+ value: 1.0
165
+ max_seq_length:
166
+ desc: null
167
+ value: 4096
168
+ max_steps:
169
+ desc: null
170
+ value: -1
171
+ metric_for_best_model:
172
+ desc: null
173
+ value: null
174
+ mlm_probability:
175
+ desc: null
176
+ value: 0.15
177
+ model_name_or_path:
178
+ desc: null
179
+ value: null
180
+ model_type:
181
+ desc: null
182
+ value: big_bird
183
+ mp_parameters:
184
+ desc: null
185
+ value: ''
186
+ no_cuda:
187
+ desc: null
188
+ value: false
189
+ num_train_epochs:
190
+ desc: null
191
+ value: 5.0
192
+ output_dir:
193
+ desc: null
194
+ value: ./
195
+ overwrite_cache:
196
+ desc: null
197
+ value: false
198
+ overwrite_output_dir:
199
+ desc: null
200
+ value: true
201
+ pad_to_max_length:
202
+ desc: null
203
+ value: false
204
+ past_index:
205
+ desc: null
206
+ value: -1
207
+ per_device_eval_batch_size:
208
+ desc: null
209
+ value: 1
210
+ per_device_train_batch_size:
211
+ desc: null
212
+ value: 1
213
+ per_gpu_eval_batch_size:
214
+ desc: null
215
+ value: null
216
+ per_gpu_train_batch_size:
217
+ desc: null
218
+ value: null
219
+ prediction_loss_only:
220
+ desc: null
221
+ value: false
222
+ preprocessing_num_workers:
223
+ desc: null
224
+ value: 96
225
+ push_to_hub:
226
+ desc: null
227
+ value: true
228
+ push_to_hub_model_id:
229
+ desc: null
230
+ value: ''
231
+ push_to_hub_organization:
232
+ desc: null
233
+ value: null
234
+ push_to_hub_token:
235
+ desc: null
236
+ value: null
237
+ remove_unused_columns:
238
+ desc: null
239
+ value: true
240
+ report_to:
241
+ desc: null
242
+ value:
243
+ - tensorboard
244
+ - wandb
245
+ resume_from_checkpoint:
246
+ desc: null
247
+ value: null
248
+ run_name:
249
+ desc: null
250
+ value: ./
251
+ save_on_each_node:
252
+ desc: null
253
+ value: false
254
+ save_optimizer:
255
+ desc: null
256
+ value: true
257
+ save_steps:
258
+ desc: null
259
+ value: 20000
260
+ save_strategy:
261
+ desc: null
262
+ value: IntervalStrategy.STEPS
263
+ save_total_limit:
264
+ desc: null
265
+ value: 5
266
+ seed:
267
+ desc: null
268
+ value: 42
269
+ sharded_ddp:
270
+ desc: null
271
+ value: []
272
+ skip_memory_metrics:
273
+ desc: null
274
+ value: true
275
+ tokenizer_name:
276
+ desc: null
277
+ value: ./
278
+ tpu_metrics_debug:
279
+ desc: null
280
+ value: false
281
+ tpu_num_cores:
282
+ desc: null
283
+ value: null
284
+ train_ref_file:
285
+ desc: null
286
+ value: null
287
+ use_fast_tokenizer:
288
+ desc: null
289
+ value: true
290
+ use_legacy_prediction_loop:
291
+ desc: null
292
+ value: false
293
+ validation_ref_file:
294
+ desc: null
295
+ value: null
296
+ validation_split_percentage:
297
+ desc: null
298
+ value: 5
299
+ warmup_ratio:
300
+ desc: null
301
+ value: 0.0
302
+ warmup_steps:
303
+ desc: null
304
+ value: 10000
305
+ weight_decay:
306
+ desc: null
307
+ value: 0.0095
wandb/run-20210714_232703-1jijl27o/files/output.log ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ /home/dat/pino/lib/python3.8/site-packages/jax/_src/numpy/lax_numpy.py:3132: UserWarning: Explicitly requested dtype <class 'jax._src.numpy.lax_numpy.int64'> requested in zeros is not available, and will be truncated to dtype int32. To enable more dtypes, set the jax_enable_x64 configuration option or the JAX_ENABLE_X64 shell environment variable. See https://github.com/google/jax#current-gotchas for more.
2
+ lax._check_user_dtype_supported(dtype, "zeros")
3
+ /home/dat/pino/lib/python3.8/site-packages/jax/lib/xla_bridge.py:386: 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/dat/pino/lib/python3.8/site-packages/jax/lib/xla_bridge.py:373: 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 ... (1/5): 0%| | 0/5 [00:00<?, ?it/s]2021-07-14 23:40:46.044618: E external/org_tensorflow/tensorflow/compiler/xla/pjrt/pjrt_stream_executor_client.cc:2036] Execution of replica 0 failed: Resource exhausted: Attempting to allocate 17.0K. That was not possible. There are 48.0K free. Due to fragmentation, the largest contiguous region of free memory is 16.0K.; (0x0x0_HBM0)
8
+ Epoch ... (1/5): 0%| | 0/5 [13:26<?, ?it/s]
9
+ Traceback (most recent call last):
10
+ File "./run_mlm_flax.py", line 806, in <module>
11
+ train_batch_idx = generate_batch_splits(train_samples_idx, train_batch_size // grad_accum_steps)
12
+ File "./run_mlm_flax.py", line 263, in generate_batch_splits
13
+ batch_idx = np.split(samples_idx, sections_split)
14
+ File "<__array_function__ internals>", line 5, in split
15
+ File "/home/dat/pino/lib/python3.8/site-packages/numpy/lib/shape_base.py", line 874, in split
16
+ return array_split(ary, indices_or_sections, axis)
17
+ File "<__array_function__ internals>", line 5, in array_split
18
+ File "/home/dat/pino/lib/python3.8/site-packages/numpy/lib/shape_base.py", line 790, in array_split
19
+ sub_arys.append(_nx.swapaxes(sary[st:end], axis, 0))
20
+ File "/home/dat/pino/lib/python3.8/site-packages/jax/_src/numpy/lax_numpy.py", line 5009, in _rewriting_take
21
+ return _gather(arr, treedef, static_idx, dynamic_idx, indices_are_sorted,
22
+ File "/home/dat/pino/lib/python3.8/site-packages/jax/_src/numpy/lax_numpy.py", line 5028, in _gather
23
+ y = lax.gather(
24
+ File "/home/dat/pino/lib/python3.8/site-packages/jax/_src/lax/lax.py", line 984, in gather
25
+ return gather_p.bind(
26
+ File "/home/dat/pino/lib/python3.8/site-packages/jax/core.py", line 264, in bind
27
+ out = top_trace.process_primitive(self, tracers, params)
28
+ File "/home/dat/pino/lib/python3.8/site-packages/jax/core.py", line 603, in process_primitive
29
+ return primitive.impl(*tracers, **params)
30
+ File "/home/dat/pino/lib/python3.8/site-packages/jax/interpreters/xla.py", line 249, in apply_primitive
31
+ return compiled_fun(*args)
32
+ File "/home/dat/pino/lib/python3.8/site-packages/jax/interpreters/xla.py", line 365, in _execute_compiled_primitive
33
+ out_bufs = compiled.execute(input_bufs)
34
+ RuntimeError: Resource exhausted: Attempting to allocate 17.0K. That was not possible. There are 48.0K free. Due to fragmentation, the largest contiguous region of free memory is 16.0K.; (0x0x0_HBM0)
wandb/run-20210714_232703-1jijl27o/files/requirements.txt ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ absl-py==0.13.0
2
+ aiohttp==3.7.4.post0
3
+ astunparse==1.6.3
4
+ async-timeout==3.0.1
5
+ attrs==21.2.0
6
+ cachetools==4.2.2
7
+ certifi==2021.5.30
8
+ chardet==4.0.0
9
+ charset-normalizer==2.0.1
10
+ chex==0.0.8
11
+ click==8.0.1
12
+ configparser==5.0.2
13
+ cycler==0.10.0
14
+ datasets==1.9.1.dev0
15
+ dill==0.3.4
16
+ dm-tree==0.1.6
17
+ docker-pycreds==0.4.0
18
+ filelock==3.0.12
19
+ flatbuffers==1.12
20
+ flax==0.3.4
21
+ fsspec==2021.7.0
22
+ gast==0.4.0
23
+ gitdb==4.0.7
24
+ gitpython==3.1.18
25
+ google-auth-oauthlib==0.4.4
26
+ google-auth==1.32.1
27
+ google-pasta==0.2.0
28
+ grpcio==1.34.1
29
+ h5py==3.1.0
30
+ huggingface-hub==0.0.12
31
+ idna==3.2
32
+ install==1.3.4
33
+ jax==0.2.17
34
+ jaxlib==0.1.68
35
+ joblib==1.0.1
36
+ keras-nightly==2.5.0.dev2021032900
37
+ keras-preprocessing==1.1.2
38
+ kiwisolver==1.3.1
39
+ libtpu-nightly==0.1.dev20210615
40
+ markdown==3.3.4
41
+ matplotlib==3.4.2
42
+ msgpack==1.0.2
43
+ multidict==5.1.0
44
+ multiprocess==0.70.12.2
45
+ numpy==1.19.5
46
+ oauthlib==3.1.1
47
+ opt-einsum==3.3.0
48
+ optax==0.0.9
49
+ packaging==21.0
50
+ pandas==1.3.0
51
+ pathtools==0.1.2
52
+ pillow==8.3.1
53
+ pip==20.0.2
54
+ pkg-resources==0.0.0
55
+ promise==2.3
56
+ protobuf==3.17.3
57
+ psutil==5.8.0
58
+ pyarrow==4.0.1
59
+ pyasn1-modules==0.2.8
60
+ pyasn1==0.4.8
61
+ pyparsing==2.4.7
62
+ python-dateutil==2.8.1
63
+ pytz==2021.1
64
+ pyyaml==5.4.1
65
+ regex==2021.7.6
66
+ requests-oauthlib==1.3.0
67
+ requests==2.26.0
68
+ rsa==4.7.2
69
+ sacremoses==0.0.45
70
+ scipy==1.7.0
71
+ sentry-sdk==1.3.0
72
+ setuptools==44.0.0
73
+ shortuuid==1.0.1
74
+ six==1.15.0
75
+ smmap==4.0.0
76
+ subprocess32==3.5.4
77
+ tensorboard-data-server==0.6.1
78
+ tensorboard-plugin-wit==1.8.0
79
+ tensorboard==2.5.0
80
+ tensorflow-estimator==2.5.0
81
+ tensorflow==2.5.0
82
+ termcolor==1.1.0
83
+ tokenizers==0.10.3
84
+ toolz==0.11.1
85
+ tqdm==4.61.2
86
+ transformers==4.9.0.dev0
87
+ typing-extensions==3.7.4.3
88
+ urllib3==1.26.6
89
+ wandb==0.10.33
90
+ werkzeug==2.0.1
91
+ wheel==0.36.2
92
+ wrapt==1.12.1
93
+ xxhash==2.0.2
94
+ yarl==1.6.3
wandb/run-20210714_232703-1jijl27o/files/wandb-metadata.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "os": "Linux-5.4.0-1043-gcp-x86_64-with-glibc2.29",
3
+ "python": "3.8.10",
4
+ "heartbeatAt": "2021-07-14T23:27:05.989594",
5
+ "startedAt": "2021-07-14T23:27:03.993085",
6
+ "docker": null,
7
+ "cpu_count": 96,
8
+ "cuda": null,
9
+ "args": [
10
+ "--push_to_hub",
11
+ "--output_dir=./",
12
+ "--model_type=big_bird",
13
+ "--config_name=./",
14
+ "--tokenizer_name=./",
15
+ "--max_seq_length=4096",
16
+ "--weight_decay=0.0095",
17
+ "--warmup_steps=10000",
18
+ "--overwrite_output_dir",
19
+ "--adam_beta1=0.9",
20
+ "--adam_beta2=0.98",
21
+ "--logging_steps=500",
22
+ "--eval_steps=20000",
23
+ "--num_train_epochs=5",
24
+ "--preprocessing_num_workers=96",
25
+ "--save_steps=20000",
26
+ "--learning_rate=5e-5",
27
+ "--per_device_train_batch_size=1",
28
+ "--per_device_eval_batch_size=1",
29
+ "--save_total_limit=5",
30
+ "--max_eval_samples=2000",
31
+ "--overwrite_cache",
32
+ "False",
33
+ "--gradient_accumulation_steps=4"
34
+ ],
35
+ "state": "running",
36
+ "program": "./run_mlm_flax.py",
37
+ "codePath": "run_mlm_flax.py",
38
+ "git": {
39
+ "remote": "https://huggingface.co/flax-community/pino-roberta-base",
40
+ "commit": "9915204ae8501d6ae8425aa8f0b4b290cbc7e5b6"
41
+ },
42
+ "email": null,
43
+ "root": "/home/dat/pino-roberta-base",
44
+ "host": "t1v-n-f5c06ea1-w-0",
45
+ "username": "dat",
46
+ "executable": "/home/dat/pino/bin/python"
47
+ }
wandb/run-20210714_232703-1jijl27o/files/wandb-summary.json ADDED
@@ -0,0 +1 @@
 
1
+ {}
wandb/run-20210714_232703-1jijl27o/logs/debug-internal.log ADDED
@@ -0,0 +1,275 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2021-07-14 23:27:04,669 INFO MainThread:606786 [internal.py:wandb_internal():88] W&B internal server running at pid: 606786, started at: 2021-07-14 23:27:04.669257
2
+ 2021-07-14 23:27:04,671 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: check_version
3
+ 2021-07-14 23:27:04,671 INFO WriterThread:606786 [datastore.py:open_for_write():80] open: /home/dat/pino-roberta-base/wandb/run-20210714_232703-1jijl27o/run-1jijl27o.wandb
4
+ 2021-07-14 23:27:04,672 DEBUG SenderThread:606786 [sender.py:send():179] send: header
5
+ 2021-07-14 23:27:04,672 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: check_version
6
+ 2021-07-14 23:27:04,709 DEBUG SenderThread:606786 [sender.py:send():179] send: run
7
+ 2021-07-14 23:27:04,879 INFO SenderThread:606786 [dir_watcher.py:__init__():168] watching files in: /home/dat/pino-roberta-base/wandb/run-20210714_232703-1jijl27o/files
8
+ 2021-07-14 23:27:04,880 INFO SenderThread:606786 [sender.py:_start_run_threads():716] run started: 1jijl27o with start time 1626305224
9
+ 2021-07-14 23:27:04,880 DEBUG SenderThread:606786 [sender.py:send():179] send: summary
10
+ 2021-07-14 23:27:04,880 INFO SenderThread:606786 [sender.py:_save_file():841] saving file wandb-summary.json with policy end
11
+ 2021-07-14 23:27:04,880 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: run_start
12
+ 2021-07-14 23:27:05,883 INFO Thread-8 :606786 [dir_watcher.py:_on_file_created():216] file/dir created: /home/dat/pino-roberta-base/wandb/run-20210714_232703-1jijl27o/files/wandb-summary.json
13
+ 2021-07-14 23:27:05,989 DEBUG HandlerThread:606786 [meta.py:__init__():39] meta init
14
+ 2021-07-14 23:27:05,989 DEBUG HandlerThread:606786 [meta.py:__init__():53] meta init done
15
+ 2021-07-14 23:27:05,989 DEBUG HandlerThread:606786 [meta.py:probe():210] probe
16
+ 2021-07-14 23:27:05,990 DEBUG HandlerThread:606786 [meta.py:_setup_git():200] setup git
17
+ 2021-07-14 23:27:06,020 DEBUG HandlerThread:606786 [meta.py:_setup_git():207] setup git done
18
+ 2021-07-14 23:27:06,020 DEBUG HandlerThread:606786 [meta.py:_save_pip():57] save pip
19
+ 2021-07-14 23:27:06,021 DEBUG HandlerThread:606786 [meta.py:_save_pip():71] save pip done
20
+ 2021-07-14 23:27:06,021 DEBUG HandlerThread:606786 [meta.py:probe():252] probe done
21
+ 2021-07-14 23:27:06,024 DEBUG SenderThread:606786 [sender.py:send():179] send: files
22
+ 2021-07-14 23:27:06,024 INFO SenderThread:606786 [sender.py:_save_file():841] saving file wandb-metadata.json with policy now
23
+ 2021-07-14 23:27:06,032 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
24
+ 2021-07-14 23:27:06,033 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
25
+ 2021-07-14 23:27:06,166 DEBUG SenderThread:606786 [sender.py:send():179] send: config
26
+ 2021-07-14 23:27:06,166 DEBUG SenderThread:606786 [sender.py:send():179] send: config
27
+ 2021-07-14 23:27:06,166 DEBUG SenderThread:606786 [sender.py:send():179] send: config
28
+ 2021-07-14 23:27:06,504 INFO Thread-11 :606786 [upload_job.py:push():137] Uploaded file /tmp/tmpf02i07o_wandb/gludn8x0-wandb-metadata.json
29
+ 2021-07-14 23:27:06,881 INFO Thread-8 :606786 [dir_watcher.py:_on_file_created():216] file/dir created: /home/dat/pino-roberta-base/wandb/run-20210714_232703-1jijl27o/files/requirements.txt
30
+ 2021-07-14 23:27:06,881 INFO Thread-8 :606786 [dir_watcher.py:_on_file_created():216] file/dir created: /home/dat/pino-roberta-base/wandb/run-20210714_232703-1jijl27o/files/wandb-metadata.json
31
+ 2021-07-14 23:27:06,881 INFO Thread-8 :606786 [dir_watcher.py:_on_file_created():216] file/dir created: /home/dat/pino-roberta-base/wandb/run-20210714_232703-1jijl27o/files/output.log
32
+ 2021-07-14 23:27:20,887 INFO Thread-8 :606786 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210714_232703-1jijl27o/files/output.log
33
+ 2021-07-14 23:27:21,168 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
34
+ 2021-07-14 23:27:21,168 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
35
+ 2021-07-14 23:27:22,888 INFO Thread-8 :606786 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210714_232703-1jijl27o/files/output.log
36
+ 2021-07-14 23:27:34,069 DEBUG SenderThread:606786 [sender.py:send():179] send: stats
37
+ 2021-07-14 23:27:35,894 INFO Thread-8 :606786 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210714_232703-1jijl27o/files/config.yaml
38
+ 2021-07-14 23:27:36,301 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
39
+ 2021-07-14 23:27:36,302 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
40
+ 2021-07-14 23:27:51,435 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
41
+ 2021-07-14 23:27:51,435 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
42
+ 2021-07-14 23:28:04,145 DEBUG SenderThread:606786 [sender.py:send():179] send: stats
43
+ 2021-07-14 23:28:06,571 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
44
+ 2021-07-14 23:28:06,571 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
45
+ 2021-07-14 23:28:21,704 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
46
+ 2021-07-14 23:28:21,704 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
47
+ 2021-07-14 23:28:34,210 DEBUG SenderThread:606786 [sender.py:send():179] send: stats
48
+ 2021-07-14 23:28:36,838 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
49
+ 2021-07-14 23:28:36,838 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
50
+ 2021-07-14 23:28:51,969 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
51
+ 2021-07-14 23:28:51,970 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
52
+ 2021-07-14 23:29:04,276 DEBUG SenderThread:606786 [sender.py:send():179] send: stats
53
+ 2021-07-14 23:29:11,606 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
54
+ 2021-07-14 23:29:11,606 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
55
+ 2021-07-14 23:29:26,738 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
56
+ 2021-07-14 23:29:26,739 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
57
+ 2021-07-14 23:29:34,341 DEBUG SenderThread:606786 [sender.py:send():179] send: stats
58
+ 2021-07-14 23:29:41,875 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
59
+ 2021-07-14 23:29:41,875 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
60
+ 2021-07-14 23:29:57,008 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
61
+ 2021-07-14 23:29:57,009 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
62
+ 2021-07-14 23:30:04,407 DEBUG SenderThread:606786 [sender.py:send():179] send: stats
63
+ 2021-07-14 23:30:12,141 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
64
+ 2021-07-14 23:30:12,142 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
65
+ 2021-07-14 23:30:27,275 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
66
+ 2021-07-14 23:30:27,276 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
67
+ 2021-07-14 23:30:34,475 DEBUG SenderThread:606786 [sender.py:send():179] send: stats
68
+ 2021-07-14 23:30:42,407 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
69
+ 2021-07-14 23:30:42,407 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
70
+ 2021-07-14 23:30:57,540 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
71
+ 2021-07-14 23:30:57,541 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
72
+ 2021-07-14 23:31:04,540 DEBUG SenderThread:606786 [sender.py:send():179] send: stats
73
+ 2021-07-14 23:31:12,674 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
74
+ 2021-07-14 23:31:12,674 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
75
+ 2021-07-14 23:31:27,806 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
76
+ 2021-07-14 23:31:27,807 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
77
+ 2021-07-14 23:31:34,612 DEBUG SenderThread:606786 [sender.py:send():179] send: stats
78
+ 2021-07-14 23:31:42,940 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
79
+ 2021-07-14 23:31:42,940 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
80
+ 2021-07-14 23:31:58,074 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
81
+ 2021-07-14 23:31:58,075 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
82
+ 2021-07-14 23:32:04,688 DEBUG SenderThread:606786 [sender.py:send():179] send: stats
83
+ 2021-07-14 23:32:13,208 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
84
+ 2021-07-14 23:32:13,208 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
85
+ 2021-07-14 23:32:28,339 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
86
+ 2021-07-14 23:32:28,340 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
87
+ 2021-07-14 23:32:34,767 DEBUG SenderThread:606786 [sender.py:send():179] send: stats
88
+ 2021-07-14 23:32:43,471 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
89
+ 2021-07-14 23:32:43,472 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
90
+ 2021-07-14 23:32:58,604 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
91
+ 2021-07-14 23:32:58,604 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
92
+ 2021-07-14 23:33:04,843 DEBUG SenderThread:606786 [sender.py:send():179] send: stats
93
+ 2021-07-14 23:33:13,739 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
94
+ 2021-07-14 23:33:13,739 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
95
+ 2021-07-14 23:33:28,873 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
96
+ 2021-07-14 23:33:28,874 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
97
+ 2021-07-14 23:33:34,917 DEBUG SenderThread:606786 [sender.py:send():179] send: stats
98
+ 2021-07-14 23:33:44,007 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
99
+ 2021-07-14 23:33:44,007 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
100
+ 2021-07-14 23:33:59,140 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
101
+ 2021-07-14 23:33:59,141 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
102
+ 2021-07-14 23:34:04,989 DEBUG SenderThread:606786 [sender.py:send():179] send: stats
103
+ 2021-07-14 23:34:14,274 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
104
+ 2021-07-14 23:34:14,275 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
105
+ 2021-07-14 23:34:29,406 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
106
+ 2021-07-14 23:34:29,406 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
107
+ 2021-07-14 23:34:35,063 DEBUG SenderThread:606786 [sender.py:send():179] send: stats
108
+ 2021-07-14 23:34:44,538 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
109
+ 2021-07-14 23:34:44,538 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
110
+ 2021-07-14 23:34:59,670 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
111
+ 2021-07-14 23:34:59,671 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
112
+ 2021-07-14 23:35:05,136 DEBUG SenderThread:606786 [sender.py:send():179] send: stats
113
+ 2021-07-14 23:35:14,806 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
114
+ 2021-07-14 23:35:14,806 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
115
+ 2021-07-14 23:35:29,937 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
116
+ 2021-07-14 23:35:29,938 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
117
+ 2021-07-14 23:35:35,212 DEBUG SenderThread:606786 [sender.py:send():179] send: stats
118
+ 2021-07-14 23:35:45,083 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
119
+ 2021-07-14 23:35:45,084 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
120
+ 2021-07-14 23:36:00,215 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
121
+ 2021-07-14 23:36:00,215 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
122
+ 2021-07-14 23:36:05,289 DEBUG SenderThread:606786 [sender.py:send():179] send: stats
123
+ 2021-07-14 23:36:15,359 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
124
+ 2021-07-14 23:36:15,359 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
125
+ 2021-07-14 23:36:30,491 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
126
+ 2021-07-14 23:36:30,492 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
127
+ 2021-07-14 23:36:35,354 DEBUG SenderThread:606786 [sender.py:send():179] send: stats
128
+ 2021-07-14 23:36:45,626 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
129
+ 2021-07-14 23:36:45,626 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
130
+ 2021-07-14 23:37:00,758 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
131
+ 2021-07-14 23:37:00,758 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
132
+ 2021-07-14 23:37:05,418 DEBUG SenderThread:606786 [sender.py:send():179] send: stats
133
+ 2021-07-14 23:37:15,896 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
134
+ 2021-07-14 23:37:15,896 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
135
+ 2021-07-14 23:37:31,030 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
136
+ 2021-07-14 23:37:31,031 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
137
+ 2021-07-14 23:37:35,484 DEBUG SenderThread:606786 [sender.py:send():179] send: stats
138
+ 2021-07-14 23:37:46,162 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
139
+ 2021-07-14 23:37:46,162 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
140
+ 2021-07-14 23:38:01,293 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
141
+ 2021-07-14 23:38:01,294 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
142
+ 2021-07-14 23:38:05,552 DEBUG SenderThread:606786 [sender.py:send():179] send: stats
143
+ 2021-07-14 23:38:16,425 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
144
+ 2021-07-14 23:38:16,425 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
145
+ 2021-07-14 23:38:31,557 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
146
+ 2021-07-14 23:38:31,557 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
147
+ 2021-07-14 23:38:35,624 DEBUG SenderThread:606786 [sender.py:send():179] send: stats
148
+ 2021-07-14 23:38:46,691 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
149
+ 2021-07-14 23:38:46,691 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
150
+ 2021-07-14 23:39:01,823 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
151
+ 2021-07-14 23:39:01,824 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
152
+ 2021-07-14 23:39:05,695 DEBUG SenderThread:606786 [sender.py:send():179] send: stats
153
+ 2021-07-14 23:39:16,955 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
154
+ 2021-07-14 23:39:16,955 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
155
+ 2021-07-14 23:39:32,087 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
156
+ 2021-07-14 23:39:32,088 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
157
+ 2021-07-14 23:39:35,769 DEBUG SenderThread:606786 [sender.py:send():179] send: stats
158
+ 2021-07-14 23:39:47,220 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
159
+ 2021-07-14 23:39:47,221 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
160
+ 2021-07-14 23:40:02,350 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
161
+ 2021-07-14 23:40:02,351 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
162
+ 2021-07-14 23:40:05,843 DEBUG SenderThread:606786 [sender.py:send():179] send: stats
163
+ 2021-07-14 23:40:17,481 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
164
+ 2021-07-14 23:40:17,482 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
165
+ 2021-07-14 23:40:32,615 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: stop_status
166
+ 2021-07-14 23:40:32,616 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: stop_status
167
+ 2021-07-14 23:40:35,918 DEBUG SenderThread:606786 [sender.py:send():179] send: stats
168
+ 2021-07-14 23:40:47,205 INFO Thread-8 :606786 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210714_232703-1jijl27o/files/output.log
169
+ 2021-07-14 23:40:48,363 DEBUG SenderThread:606786 [sender.py:send():179] send: telemetry
170
+ 2021-07-14 23:40:48,364 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: poll_exit
171
+ 2021-07-14 23:40:48,364 DEBUG SenderThread:606786 [sender.py:send():179] send: exit
172
+ 2021-07-14 23:40:48,364 INFO SenderThread:606786 [sender.py:send_exit():287] handling exit code: 1
173
+ 2021-07-14 23:40:48,366 INFO SenderThread:606786 [sender.py:send_exit():295] send defer
174
+ 2021-07-14 23:40:48,366 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: poll_exit
175
+ 2021-07-14 23:40:48,367 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: defer
176
+ 2021-07-14 23:40:48,367 INFO HandlerThread:606786 [handler.py:handle_request_defer():141] handle defer: 0
177
+ 2021-07-14 23:40:48,367 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: defer
178
+ 2021-07-14 23:40:48,367 INFO SenderThread:606786 [sender.py:send_request_defer():304] handle sender defer: 0
179
+ 2021-07-14 23:40:48,367 INFO SenderThread:606786 [sender.py:transition_state():308] send defer: 1
180
+ 2021-07-14 23:40:48,368 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: defer
181
+ 2021-07-14 23:40:48,368 INFO HandlerThread:606786 [handler.py:handle_request_defer():141] handle defer: 1
182
+ 2021-07-14 23:40:48,446 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: defer
183
+ 2021-07-14 23:40:48,446 INFO SenderThread:606786 [sender.py:send_request_defer():304] handle sender defer: 1
184
+ 2021-07-14 23:40:48,446 INFO SenderThread:606786 [sender.py:transition_state():308] send defer: 2
185
+ 2021-07-14 23:40:48,446 DEBUG SenderThread:606786 [sender.py:send():179] send: stats
186
+ 2021-07-14 23:40:48,447 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: defer
187
+ 2021-07-14 23:40:48,447 INFO HandlerThread:606786 [handler.py:handle_request_defer():141] handle defer: 2
188
+ 2021-07-14 23:40:48,447 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: defer
189
+ 2021-07-14 23:40:48,447 INFO SenderThread:606786 [sender.py:send_request_defer():304] handle sender defer: 2
190
+ 2021-07-14 23:40:48,447 INFO SenderThread:606786 [sender.py:transition_state():308] send defer: 3
191
+ 2021-07-14 23:40:48,447 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: defer
192
+ 2021-07-14 23:40:48,448 INFO HandlerThread:606786 [handler.py:handle_request_defer():141] handle defer: 3
193
+ 2021-07-14 23:40:48,448 DEBUG SenderThread:606786 [sender.py:send():179] send: summary
194
+ 2021-07-14 23:40:48,448 INFO SenderThread:606786 [sender.py:_save_file():841] saving file wandb-summary.json with policy end
195
+ 2021-07-14 23:40:48,449 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: defer
196
+ 2021-07-14 23:40:48,449 INFO SenderThread:606786 [sender.py:send_request_defer():304] handle sender defer: 3
197
+ 2021-07-14 23:40:48,449 INFO SenderThread:606786 [sender.py:transition_state():308] send defer: 4
198
+ 2021-07-14 23:40:48,449 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: defer
199
+ 2021-07-14 23:40:48,449 INFO HandlerThread:606786 [handler.py:handle_request_defer():141] handle defer: 4
200
+ 2021-07-14 23:40:48,449 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: defer
201
+ 2021-07-14 23:40:48,449 INFO SenderThread:606786 [sender.py:send_request_defer():304] handle sender defer: 4
202
+ 2021-07-14 23:40:48,469 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: poll_exit
203
+ 2021-07-14 23:40:48,629 INFO SenderThread:606786 [sender.py:transition_state():308] send defer: 5
204
+ 2021-07-14 23:40:48,629 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: poll_exit
205
+ 2021-07-14 23:40:48,630 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: defer
206
+ 2021-07-14 23:40:48,630 INFO HandlerThread:606786 [handler.py:handle_request_defer():141] handle defer: 5
207
+ 2021-07-14 23:40:48,630 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: defer
208
+ 2021-07-14 23:40:48,630 INFO SenderThread:606786 [sender.py:send_request_defer():304] handle sender defer: 5
209
+ 2021-07-14 23:40:48,630 INFO SenderThread:606786 [dir_watcher.py:finish():282] shutting down directory watcher
210
+ 2021-07-14 23:40:48,732 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: poll_exit
211
+ 2021-07-14 23:40:49,206 INFO Thread-8 :606786 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210714_232703-1jijl27o/files/config.yaml
212
+ 2021-07-14 23:40:49,207 INFO SenderThread:606786 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210714_232703-1jijl27o/files/output.log
213
+ 2021-07-14 23:40:49,207 INFO SenderThread:606786 [dir_watcher.py:_on_file_modified():229] file/dir modified: /home/dat/pino-roberta-base/wandb/run-20210714_232703-1jijl27o/files/wandb-summary.json
214
+ 2021-07-14 23:40:49,207 INFO SenderThread:606786 [dir_watcher.py:finish():312] scan: /home/dat/pino-roberta-base/wandb/run-20210714_232703-1jijl27o/files
215
+ 2021-07-14 23:40:49,207 INFO SenderThread:606786 [dir_watcher.py:finish():318] scan save: /home/dat/pino-roberta-base/wandb/run-20210714_232703-1jijl27o/files/requirements.txt requirements.txt
216
+ 2021-07-14 23:40:49,208 INFO SenderThread:606786 [dir_watcher.py:finish():318] scan save: /home/dat/pino-roberta-base/wandb/run-20210714_232703-1jijl27o/files/output.log output.log
217
+ 2021-07-14 23:40:49,208 INFO SenderThread:606786 [dir_watcher.py:finish():318] scan save: /home/dat/pino-roberta-base/wandb/run-20210714_232703-1jijl27o/files/wandb-metadata.json wandb-metadata.json
218
+ 2021-07-14 23:40:49,208 INFO SenderThread:606786 [dir_watcher.py:finish():318] scan save: /home/dat/pino-roberta-base/wandb/run-20210714_232703-1jijl27o/files/config.yaml config.yaml
219
+ 2021-07-14 23:40:49,208 INFO SenderThread:606786 [dir_watcher.py:finish():318] scan save: /home/dat/pino-roberta-base/wandb/run-20210714_232703-1jijl27o/files/wandb-summary.json wandb-summary.json
220
+ 2021-07-14 23:40:49,209 INFO SenderThread:606786 [sender.py:transition_state():308] send defer: 6
221
+ 2021-07-14 23:40:49,209 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: poll_exit
222
+ 2021-07-14 23:40:49,210 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: defer
223
+ 2021-07-14 23:40:49,210 INFO HandlerThread:606786 [handler.py:handle_request_defer():141] handle defer: 6
224
+ 2021-07-14 23:40:49,215 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: defer
225
+ 2021-07-14 23:40:49,216 INFO SenderThread:606786 [sender.py:send_request_defer():304] handle sender defer: 6
226
+ 2021-07-14 23:40:49,216 INFO SenderThread:606786 [file_pusher.py:finish():177] shutting down file pusher
227
+ 2021-07-14 23:40:49,311 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: poll_exit
228
+ 2021-07-14 23:40:49,311 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: poll_exit
229
+ 2021-07-14 23:40:49,413 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: poll_exit
230
+ 2021-07-14 23:40:49,413 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: poll_exit
231
+ 2021-07-14 23:40:49,515 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: poll_exit
232
+ 2021-07-14 23:40:49,515 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: poll_exit
233
+ 2021-07-14 23:40:49,617 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: poll_exit
234
+ 2021-07-14 23:40:49,618 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: poll_exit
235
+ 2021-07-14 23:40:49,652 INFO Thread-12 :606786 [upload_job.py:push():137] Uploaded file /home/dat/pino-roberta-base/wandb/run-20210714_232703-1jijl27o/files/requirements.txt
236
+ 2021-07-14 23:40:49,653 INFO Thread-14 :606786 [upload_job.py:push():137] Uploaded file /home/dat/pino-roberta-base/wandb/run-20210714_232703-1jijl27o/files/config.yaml
237
+ 2021-07-14 23:40:49,698 INFO Thread-15 :606786 [upload_job.py:push():137] Uploaded file /home/dat/pino-roberta-base/wandb/run-20210714_232703-1jijl27o/files/wandb-summary.json
238
+ 2021-07-14 23:40:49,719 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: poll_exit
239
+ 2021-07-14 23:40:49,720 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: poll_exit
240
+ 2021-07-14 23:40:49,739 INFO Thread-13 :606786 [upload_job.py:push():137] Uploaded file /home/dat/pino-roberta-base/wandb/run-20210714_232703-1jijl27o/files/output.log
241
+ 2021-07-14 23:40:49,821 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: poll_exit
242
+ 2021-07-14 23:40:49,822 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: poll_exit
243
+ 2021-07-14 23:40:49,923 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: poll_exit
244
+ 2021-07-14 23:40:49,923 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: poll_exit
245
+ 2021-07-14 23:40:49,940 INFO Thread-7 :606786 [sender.py:transition_state():308] send defer: 7
246
+ 2021-07-14 23:40:49,940 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: defer
247
+ 2021-07-14 23:40:49,940 INFO HandlerThread:606786 [handler.py:handle_request_defer():141] handle defer: 7
248
+ 2021-07-14 23:40:49,940 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: defer
249
+ 2021-07-14 23:40:49,940 INFO SenderThread:606786 [sender.py:send_request_defer():304] handle sender defer: 7
250
+ 2021-07-14 23:40:50,025 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: poll_exit
251
+ 2021-07-14 23:40:50,227 INFO SenderThread:606786 [sender.py:transition_state():308] send defer: 8
252
+ 2021-07-14 23:40:50,228 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: poll_exit
253
+ 2021-07-14 23:40:50,228 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: defer
254
+ 2021-07-14 23:40:50,228 INFO HandlerThread:606786 [handler.py:handle_request_defer():141] handle defer: 8
255
+ 2021-07-14 23:40:50,229 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: defer
256
+ 2021-07-14 23:40:50,229 INFO SenderThread:606786 [sender.py:send_request_defer():304] handle sender defer: 8
257
+ 2021-07-14 23:40:50,229 INFO SenderThread:606786 [sender.py:transition_state():308] send defer: 9
258
+ 2021-07-14 23:40:50,229 DEBUG SenderThread:606786 [sender.py:send():179] send: final
259
+ 2021-07-14 23:40:50,229 DEBUG SenderThread:606786 [sender.py:send():179] send: footer
260
+ 2021-07-14 23:40:50,230 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: defer
261
+ 2021-07-14 23:40:50,230 INFO HandlerThread:606786 [handler.py:handle_request_defer():141] handle defer: 9
262
+ 2021-07-14 23:40:50,230 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: defer
263
+ 2021-07-14 23:40:50,230 INFO SenderThread:606786 [sender.py:send_request_defer():304] handle sender defer: 9
264
+ 2021-07-14 23:40:50,330 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: poll_exit
265
+ 2021-07-14 23:40:50,330 DEBUG SenderThread:606786 [sender.py:send_request():193] send_request: poll_exit
266
+ 2021-07-14 23:40:50,330 INFO SenderThread:606786 [file_pusher.py:join():182] waiting for file pusher
267
+ 2021-07-14 23:40:50,332 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: get_summary
268
+ 2021-07-14 23:40:50,332 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: sampled_history
269
+ 2021-07-14 23:40:50,333 DEBUG HandlerThread:606786 [handler.py:handle_request():124] handle_request: shutdown
270
+ 2021-07-14 23:40:50,333 INFO HandlerThread:606786 [handler.py:finish():638] shutting down handler
271
+ 2021-07-14 23:40:51,230 INFO WriterThread:606786 [datastore.py:close():288] close: /home/dat/pino-roberta-base/wandb/run-20210714_232703-1jijl27o/run-1jijl27o.wandb
272
+ 2021-07-14 23:40:51,330 INFO SenderThread:606786 [sender.py:finish():945] shutting down sender
273
+ 2021-07-14 23:40:51,331 INFO SenderThread:606786 [file_pusher.py:finish():177] shutting down file pusher
274
+ 2021-07-14 23:40:51,331 INFO SenderThread:606786 [file_pusher.py:join():182] waiting for file pusher
275
+ 2021-07-14 23:40:51,334 INFO MainThread:606786 [internal.py:handle_exit():78] Internal process exited
wandb/run-20210714_232703-1jijl27o/logs/debug.log ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2021-07-14 23:27:03,994 INFO MainThread:605532 [wandb_setup.py:_flush():69] setting env: {}
2
+ 2021-07-14 23:27:03,994 INFO MainThread:605532 [wandb_setup.py:_flush():69] setting login settings: {}
3
+ 2021-07-14 23:27:03,994 INFO MainThread:605532 [wandb_init.py:_log_setup():337] Logging user logs to /home/dat/pino-roberta-base/wandb/run-20210714_232703-1jijl27o/logs/debug.log
4
+ 2021-07-14 23:27:03,994 INFO MainThread:605532 [wandb_init.py:_log_setup():338] Logging internal logs to /home/dat/pino-roberta-base/wandb/run-20210714_232703-1jijl27o/logs/debug-internal.log
5
+ 2021-07-14 23:27:03,995 INFO MainThread:605532 [wandb_init.py:init():370] calling init triggers
6
+ 2021-07-14 23:27:03,995 INFO MainThread:605532 [wandb_init.py:init():375] wandb.init called with sweep_config: {}
7
+ config: {}
8
+ 2021-07-14 23:27:03,995 INFO MainThread:605532 [wandb_init.py:init():419] starting backend
9
+ 2021-07-14 23:27:03,995 INFO MainThread:605532 [backend.py:_multiprocessing_setup():70] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
10
+ 2021-07-14 23:27:04,041 INFO MainThread:605532 [backend.py:ensure_launched():135] starting backend process...
11
+ 2021-07-14 23:27:04,085 INFO MainThread:605532 [backend.py:ensure_launched():139] started backend process with pid: 606786
12
+ 2021-07-14 23:27:04,087 INFO MainThread:605532 [wandb_init.py:init():424] backend started and connected
13
+ 2021-07-14 23:27:04,090 INFO MainThread:605532 [wandb_init.py:init():472] updated telemetry
14
+ 2021-07-14 23:27:04,091 INFO MainThread:605532 [wandb_init.py:init():491] communicating current version
15
+ 2021-07-14 23:27:04,708 INFO MainThread:605532 [wandb_init.py:init():496] got version response
16
+ 2021-07-14 23:27:04,708 INFO MainThread:605532 [wandb_init.py:init():504] communicating run to backend with 30 second timeout
17
+ 2021-07-14 23:27:04,879 INFO MainThread:605532 [wandb_init.py:init():529] starting run threads in backend
18
+ 2021-07-14 23:27:06,027 INFO MainThread:605532 [wandb_run.py:_console_start():1623] atexit reg
19
+ 2021-07-14 23:27:06,028 INFO MainThread:605532 [wandb_run.py:_redirect():1497] redirect: SettingsConsole.REDIRECT
20
+ 2021-07-14 23:27:06,028 INFO MainThread:605532 [wandb_run.py:_redirect():1502] Redirecting console.
21
+ 2021-07-14 23:27:06,030 INFO MainThread:605532 [wandb_run.py:_redirect():1558] Redirects installed.
22
+ 2021-07-14 23:27:06,030 INFO MainThread:605532 [wandb_init.py:init():554] run started, returning control to user process
23
+ 2021-07-14 23:27:06,038 INFO MainThread:605532 [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': 1, 'per_device_eval_batch_size': 1, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 4, 'eval_accumulation_steps': None, 'learning_rate': 5e-05, 'weight_decay': 0.0095, 'adam_beta1': 0.9, 'adam_beta2': 0.98, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 5.0, 'max_steps': -1, 'lr_scheduler_type': 'SchedulerType.LINEAR', 'warmup_ratio': 0.0, 'warmup_steps': 10000, 'log_level': -1, 'log_level_replica': -1, 'log_on_each_node': True, 'logging_dir': './runs/Jul14_23-26-56_t1v-n-f5c06ea1-w-0', 'logging_strategy': 'IntervalStrategy.STEPS', 'logging_first_step': False, 'logging_steps': 500, 'save_strategy': 'IntervalStrategy.STEPS', 'save_steps': 20000, 'save_total_limit': 5, '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': 20000, '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': True, 'resume_from_checkpoint': None, 'push_to_hub_model_id': '', 'push_to_hub_organization': None, 'push_to_hub_token': None, 'mp_parameters': ''}
24
+ 2021-07-14 23:27:06,040 INFO MainThread:605532 [wandb_run.py:_config_callback():872] config_cb None None {'model_name_or_path': None, 'model_type': 'big_bird', 'config_name': './', 'tokenizer_name': './', 'cache_dir': None, 'use_fast_tokenizer': True, 'dtype': 'float32', 'save_optimizer': True}
25
+ 2021-07-14 23:27:06,041 INFO MainThread:605532 [wandb_run.py:_config_callback():872] config_cb None None {'dataset_name': None, 'dataset_config_name': None, 'train_ref_file': None, 'validation_ref_file': None, 'overwrite_cache': False, 'validation_split_percentage': 5, 'max_seq_length': 4096, 'preprocessing_num_workers': 96, 'mlm_probability': 0.15, 'pad_to_max_length': False, 'line_by_line': False, 'max_eval_samples': 2000}
26
+ 2021-07-14 23:40:46,049 INFO MainThread:605532 [wandb_run.py:_atexit_cleanup():1593] got exitcode: 1
27
+ 2021-07-14 23:40:46,050 INFO MainThread:605532 [wandb_run.py:_restore():1565] restore
28
+ 2021-07-14 23:40:48,367 INFO MainThread:605532 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
29
+ wandb_count: 1
30
+ }
31
+ pusher_stats {
32
+ uploaded_bytes: 1448
33
+ total_bytes: 1448
34
+ }
35
+
36
+ 2021-07-14 23:40:48,630 INFO MainThread:605532 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
37
+ wandb_count: 1
38
+ }
39
+ pusher_stats {
40
+ uploaded_bytes: 1448
41
+ total_bytes: 1448
42
+ }
43
+
44
+ 2021-07-14 23:40:49,210 INFO MainThread:605532 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
45
+ wandb_count: 4
46
+ }
47
+ pusher_stats {
48
+ uploaded_bytes: 1448
49
+ total_bytes: 11299
50
+ }
51
+
52
+ 2021-07-14 23:40:49,312 INFO MainThread:605532 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
53
+ wandb_count: 5
54
+ }
55
+ pusher_stats {
56
+ uploaded_bytes: 1448
57
+ total_bytes: 11301
58
+ }
59
+
60
+ 2021-07-14 23:40:49,414 INFO MainThread:605532 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
61
+ wandb_count: 5
62
+ }
63
+ pusher_stats {
64
+ uploaded_bytes: 11301
65
+ total_bytes: 11301
66
+ }
67
+
68
+ 2021-07-14 23:40:49,516 INFO MainThread:605532 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
69
+ wandb_count: 5
70
+ }
71
+ pusher_stats {
72
+ uploaded_bytes: 11301
73
+ total_bytes: 11301
74
+ }
75
+
76
+ 2021-07-14 23:40:49,618 INFO MainThread:605532 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
77
+ wandb_count: 5
78
+ }
79
+ pusher_stats {
80
+ uploaded_bytes: 11301
81
+ total_bytes: 11301
82
+ }
83
+
84
+ 2021-07-14 23:40:49,720 INFO MainThread:605532 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
85
+ wandb_count: 5
86
+ }
87
+ pusher_stats {
88
+ uploaded_bytes: 11301
89
+ total_bytes: 11301
90
+ }
91
+
92
+ 2021-07-14 23:40:49,822 INFO MainThread:605532 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
93
+ wandb_count: 5
94
+ }
95
+ pusher_stats {
96
+ uploaded_bytes: 11301
97
+ total_bytes: 11301
98
+ }
99
+
100
+ 2021-07-14 23:40:49,924 INFO MainThread:605532 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
101
+ wandb_count: 5
102
+ }
103
+ pusher_stats {
104
+ uploaded_bytes: 11301
105
+ total_bytes: 11301
106
+ }
107
+
108
+ 2021-07-14 23:40:50,228 INFO MainThread:605532 [wandb_run.py:_wait_for_finish():1715] got exit ret: file_counts {
109
+ wandb_count: 5
110
+ }
111
+ pusher_stats {
112
+ uploaded_bytes: 11301
113
+ total_bytes: 11301
114
+ }
115
+
116
+ 2021-07-14 23:40:50,331 INFO MainThread:605532 [wandb_run.py:_wait_for_finish():1715] got exit ret: done: true
117
+ exit_result {
118
+ }
119
+ file_counts {
120
+ wandb_count: 5
121
+ }
122
+ pusher_stats {
123
+ uploaded_bytes: 11301
124
+ total_bytes: 11301
125
+ }
126
+
127
+ 2021-07-14 23:40:51,653 INFO MainThread:605532 [wandb_run.py:_show_files():1937] logging synced files
wandb/run-20210714_232703-1jijl27o/run-1jijl27o.wandb ADDED
Binary file (13.6 kB). View file
wandb/run-20210714_234615-3p6vlfc3/files/config.yaml ADDED
@@ -0,0 +1,304 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ - 3
15
+ - 11
16
+ 4: 3.8.10
17
+ 5: 0.10.33
18
+ 6: 4.9.0.dev0
19
+ 8:
20
+ - 5
21
+ adafactor:
22
+ desc: null
23
+ value: false
24
+ adam_beta1:
25
+ desc: null
26
+ value: 0.9
27
+ adam_beta2:
28
+ desc: null
29
+ value: 0.98
30
+ adam_epsilon:
31
+ desc: null
32
+ value: 1.0e-08
33
+ cache_dir:
34
+ desc: null
35
+ value: null
36
+ config_name:
37
+ desc: null
38
+ value: ./
39
+ dataloader_drop_last:
40
+ desc: null
41
+ value: false
42
+ dataloader_num_workers:
43
+ desc: null
44
+ value: 0
45
+ dataloader_pin_memory:
46
+ desc: null
47
+ value: true
48
+ dataset_config_name:
49
+ desc: null
50
+ value: null
51
+ dataset_name:
52
+ desc: null
53
+ value: null
54
+ ddp_find_unused_parameters:
55
+ desc: null
56
+ value: null
57
+ debug:
58
+ desc: null
59
+ value: []
60
+ deepspeed:
61
+ desc: null
62
+ value: null
63
+ disable_tqdm:
64
+ desc: null
65
+ value: false
66
+ do_eval:
67
+ desc: null
68
+ value: false
69
+ do_predict:
70
+ desc: null
71
+ value: false
72
+ do_train:
73
+ desc: null
74
+ value: false
75
+ dtype:
76
+ desc: null
77
+ value: float32
78
+ eval_accumulation_steps:
79
+ desc: null
80
+ value: null
81
+ eval_steps:
82
+ desc: null
83
+ value: 20000
84
+ evaluation_strategy:
85
+ desc: null
86
+ value: IntervalStrategy.NO
87
+ fp16:
88
+ desc: null
89
+ value: false
90
+ fp16_backend:
91
+ desc: null
92
+ value: auto
93
+ fp16_full_eval:
94
+ desc: null
95
+ value: false
96
+ fp16_opt_level:
97
+ desc: null
98
+ value: O1
99
+ gradient_accumulation_steps:
100
+ desc: null
101
+ value: 4
102
+ greater_is_better:
103
+ desc: null
104
+ value: null
105
+ group_by_length:
106
+ desc: null
107
+ value: false
108
+ ignore_data_skip:
109
+ desc: null
110
+ value: false
111
+ label_names:
112
+ desc: null
113
+ value: null
114
+ label_smoothing_factor:
115
+ desc: null
116
+ value: 0.0
117
+ learning_rate:
118
+ desc: null
119
+ value: 5.0e-05
120
+ length_column_name:
121
+ desc: null
122
+ value: length
123
+ line_by_line:
124
+ desc: null
125
+ value: false
126
+ load_best_model_at_end:
127
+ desc: null
128
+ value: false
129
+ local_rank:
130
+ desc: null
131
+ value: -1
132
+ log_level:
133
+ desc: null
134
+ value: -1
135
+ log_level_replica:
136
+ desc: null
137
+ value: -1
138
+ log_on_each_node:
139
+ desc: null
140
+ value: true
141
+ logging_dir:
142
+ desc: null
143
+ value: ./runs/Jul14_23-46-07_t1v-n-f5c06ea1-w-0
144
+ logging_first_step:
145
+ desc: null
146
+ value: false
147
+ logging_steps:
148
+ desc: null
149
+ value: 250
150
+ logging_strategy:
151
+ desc: null
152
+ value: IntervalStrategy.STEPS
153
+ lr_scheduler_type:
154
+ desc: null
155
+ value: SchedulerType.LINEAR
156
+ max_eval_samples:
157
+ desc: null
158
+ value: 2000
159
+ max_grad_norm:
160
+ desc: null
161
+ value: 1.0
162
+ max_seq_length:
163
+ desc: null
164
+ value: 4096
165
+ max_steps:
166
+ desc: null
167
+ value: -1
168
+ metric_for_best_model:
169
+ desc: null
170
+ value: null
171
+ mlm_probability:
172
+ desc: null
173
+ value: 0.15
174
+ model_name_or_path:
175
+ desc: null
176
+ value: null
177
+ model_type:
178
+ desc: null
179
+ value: big_bird
180
+ mp_parameters:
181
+ desc: null
182
+ value: ''
183
+ no_cuda:
184
+ desc: null
185
+ value: false
186
+ num_train_epochs:
187
+ desc: null
188
+ value: 5.0
189
+ output_dir:
190
+ desc: null
191
+ value: ./
192
+ overwrite_cache:
193
+ desc: null
194
+ value: false
195
+ overwrite_output_dir:
196
+ desc: null
197
+ value: true
198
+ pad_to_max_length:
199
+ desc: null
200
+ value: false
201
+ past_index:
202
+ desc: null
203
+ value: -1
204
+ per_device_eval_batch_size:
205
+ desc: null
206
+ value: 2
207
+ per_device_train_batch_size:
208
+ desc: null
209
+ value: 2
210
+ per_gpu_eval_batch_size:
211
+ desc: null
212
+ value: null
213
+ per_gpu_train_batch_size:
214
+ desc: null
215
+ value: null
216
+ prediction_loss_only:
217
+ desc: null
218
+ value: false
219
+ preprocessing_num_workers:
220
+ desc: null
221
+ value: 96
222
+ push_to_hub:
223
+ desc: null
224
+ value: true
225
+ push_to_hub_model_id:
226
+ desc: null
227
+ value: ''
228
+ push_to_hub_organization:
229
+ desc: null
230
+ value: null
231
+ push_to_hub_token:
232
+ desc: null
233
+ value: null
234
+ remove_unused_columns:
235
+ desc: null
236
+ value: true
237
+ report_to:
238
+ desc: null
239
+ value:
240
+ - tensorboard
241
+ - wandb
242
+ resume_from_checkpoint:
243
+ desc: null
244
+ value: null
245
+ run_name:
246
+ desc: null
247
+ value: ./
248
+ save_on_each_node:
249
+ desc: null
250
+ value: false
251
+ save_optimizer:
252
+ desc: null
253
+ value: true
254
+ save_steps:
255
+ desc: null
256
+ value: 20000
257
+ save_strategy:
258
+ desc: null
259
+ value: IntervalStrategy.STEPS
260
+ save_total_limit:
261
+ desc: null
262
+ value: 5
263
+ seed:
264
+ desc: null
265
+ value: 42
266
+ sharded_ddp:
267
+ desc: null
268
+ value: []
269
+ skip_memory_metrics:
270
+ desc: null
271
+ value: true
272
+ tokenizer_name:
273
+ desc: null
274
+ value: ./
275
+ tpu_metrics_debug:
276
+ desc: null
277
+ value: false
278
+ tpu_num_cores:
279
+ desc: null
280
+ value: null
281
+ train_ref_file:
282
+ desc: null
283
+ value: null
284
+ use_fast_tokenizer:
285
+ desc: null
286
+ value: true
287
+ use_legacy_prediction_loop:
288
+ desc: null
289
+ value: false
290
+ validation_ref_file:
291
+ desc: null
292
+ value: null
293
+ validation_split_percentage:
294
+ desc: null
295
+ value: 5
296
+ warmup_ratio:
297
+ desc: null
298
+ value: 0.0
299
+ warmup_steps:
300
+ desc: null
301
+ value: 10000
302
+ weight_decay:
303
+ desc: null
304
+ value: 0.0095
wandb/run-20210714_234615-3p6vlfc3/files/output.log ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
1
+ /home/dat/pino/lib/python3.8/site-packages/jax/_src/numpy/lax_numpy.py:3132: UserWarning: Explicitly requested dtype <class 'jax._src.numpy.lax_numpy.int64'> requested in zeros is not available, and will be truncated to dtype int32. To enable more dtypes, set the jax_enable_x64 configuration option or the JAX_ENABLE_X64 shell environment variable. See https://github.com/google/jax#current-gotchas for more.
2
+ lax._check_user_dtype_supported(dtype, "zeros")
3
+ /home/dat/pino/lib/python3.8/site-packages/jax/lib/xla_bridge.py:386: 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/dat/pino/lib/python3.8/site-packages/jax/lib/xla_bridge.py:373: UserWarning: jax.host_id has been renamed to jax.process_index. This alias will eventually be removed; please update your code.
6
+ warnings.warn(
wandb/run-20210714_234615-3p6vlfc3/files/requirements.txt ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ absl-py==0.13.0
2
+ aiohttp==3.7.4.post0
3
+ astunparse==1.6.3
4
+ async-timeout==3.0.1
5
+ attrs==21.2.0
6
+ cachetools==4.2.2
7
+ certifi==2021.5.30
8
+ chardet==4.0.0
9
+ charset-normalizer==2.0.1
10
+ chex==0.0.8
11
+ click==8.0.1
12
+ configparser==5.0.2
13
+ cycler==0.10.0
14
+ datasets==1.9.1.dev0
15
+ dill==0.3.4
16
+ dm-tree==0.1.6
17
+ docker-pycreds==0.4.0
18
+ filelock==3.0.12
19
+ flatbuffers==1.12
20
+ flax==0.3.4
21
+ fsspec==2021.7.0
22
+ gast==0.4.0
23
+ gitdb==4.0.7
24
+ gitpython==3.1.18
25
+ google-auth-oauthlib==0.4.4
26
+ google-auth==1.32.1
27
+ google-pasta==0.2.0
28
+ grpcio==1.34.1
29
+ h5py==3.1.0
30
+ huggingface-hub==0.0.12
31
+ idna==3.2
32
+ install==1.3.4
33
+ jax==0.2.17
34
+ jaxlib==0.1.68
35
+ joblib==1.0.1
36
+ keras-nightly==2.5.0.dev2021032900
37
+ keras-preprocessing==1.1.2
38
+ kiwisolver==1.3.1
39
+ libtpu-nightly==0.1.dev20210615
40
+ markdown==3.3.4
41
+ matplotlib==3.4.2
42
+ msgpack==1.0.2
43
+ multidict==5.1.0
44
+ multiprocess==0.70.12.2
45
+ numpy==1.19.5
46
+ oauthlib==3.1.1
47
+ opt-einsum==3.3.0
48
+ optax==0.0.9
49
+ packaging==21.0
50
+ pandas==1.3.0
51
+ pathtools==0.1.2
52
+ pillow==8.3.1
53
+ pip==20.0.2
54
+ pkg-resources==0.0.0
55
+ promise==2.3
56
+ protobuf==3.17.3
57
+ psutil==5.8.0
58
+ pyarrow==4.0.1
59
+ pyasn1-modules==0.2.8
60
+ pyasn1==0.4.8
61
+ pyparsing==2.4.7
62
+ python-dateutil==2.8.1
63
+ pytz==2021.1
64
+ pyyaml==5.4.1
65
+ regex==2021.7.6
66
+ requests-oauthlib==1.3.0
67
+ requests==2.26.0
68
+ rsa==4.7.2
69
+ sacremoses==0.0.45
70
+ scipy==1.7.0
71
+ sentry-sdk==1.3.0
72
+ setuptools==44.0.0
73
+ shortuuid==1.0.1
74
+ six==1.15.0
75
+ smmap==4.0.0
76
+ subprocess32==3.5.4
77
+ tensorboard-data-server==0.6.1
78
+ tensorboard-plugin-wit==1.8.0
79
+ tensorboard==2.5.0
80
+ tensorflow-estimator==2.5.0
81
+ tensorflow==2.5.0
82
+ termcolor==1.1.0
83
+ tokenizers==0.10.3
84
+ toolz==0.11.1
85
+ tqdm==4.61.2
86
+ transformers==4.9.0.dev0
87
+ typing-extensions==3.7.4.3
88
+ urllib3==1.26.6
89
+ wandb==0.10.33
90
+ werkzeug==2.0.1
91
+ wheel==0.36.2
92
+ wrapt==1.12.1
93
+ xxhash==2.0.2
94
+ yarl==1.6.3