sanchit-gandhi HF staff commited on
Commit
b0a9076
1 Parent(s): 91fd052

Training in progress, step 500

Browse files
Files changed (34) hide show
  1. .gitattributes +1 -0
  2. pytorch_model.bin +1 -1
  3. run_distributed.sh +36 -0
  4. run_speech_recognition_seq2seq.py +2 -1
  5. runs/Mar28_16-59-05_sanchit--v100/1648486774.395873/events.out.tfevents.1648486774.sanchit--v100.258712.1 +3 -0
  6. runs/Mar28_16-59-05_sanchit--v100/events.out.tfevents.1648486774.sanchit--v100.258712.0 +3 -0
  7. runs/Mar28_17-01-12_sanchit--v100/1648486901.737252/events.out.tfevents.1648486901.sanchit--v100.260352.1 +3 -0
  8. runs/Mar28_17-01-12_sanchit--v100/events.out.tfevents.1648486901.sanchit--v100.260352.0 +3 -0
  9. training_args.bin +1 -1
  10. wandb/debug-internal.log +1 -1
  11. wandb/debug.log +1 -1
  12. wandb/latest-run +1 -1
  13. wandb/run-20220327_210229-2wif55w7/files/config.yaml +7 -0
  14. wandb/run-20220327_210229-2wif55w7/files/output.log +17 -0
  15. wandb/run-20220327_210229-2wif55w7/files/wandb-summary.json +0 -0
  16. wandb/run-20220327_210229-2wif55w7/logs/debug-internal.log +2 -2
  17. wandb/run-20220327_210229-2wif55w7/logs/debug.log +106 -0
  18. wandb/run-20220327_210229-2wif55w7/run-2wif55w7.wandb +2 -2
  19. wandb/run-20220328_165934-10ki2qcy/files/config.yaml +716 -0
  20. wandb/run-20220328_165934-10ki2qcy/files/output.log +57 -0
  21. wandb/run-20220328_165934-10ki2qcy/files/requirements.txt +186 -0
  22. wandb/run-20220328_165934-10ki2qcy/files/wandb-metadata.json +58 -0
  23. wandb/run-20220328_165934-10ki2qcy/files/wandb-summary.json +1 -0
  24. wandb/run-20220328_165934-10ki2qcy/logs/debug-internal.log +76 -0
  25. wandb/run-20220328_165934-10ki2qcy/logs/debug.log +29 -0
  26. wandb/run-20220328_165934-10ki2qcy/run-10ki2qcy.wandb +0 -0
  27. wandb/run-20220328_170142-by95ehra/files/config.yaml +0 -0
  28. wandb/run-20220328_170142-by95ehra/files/output.log +0 -0
  29. wandb/run-20220328_170142-by95ehra/files/requirements.txt +186 -0
  30. wandb/run-20220328_170142-by95ehra/files/wandb-metadata.json +59 -0
  31. wandb/run-20220328_170142-by95ehra/files/wandb-summary.json +0 -0
  32. wandb/run-20220328_170142-by95ehra/logs/debug-internal.log +0 -0
  33. wandb/run-20220328_170142-by95ehra/logs/debug.log +27 -0
  34. wandb/run-20220328_170142-by95ehra/run-by95ehra.wandb +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ wandb/run-20220326_171130-bdf5nvyg/logs/debug-internal.log filter=lfs diff=lfs m
33
  wandb/run-20220327_194752-3s89mmo1/run-3s89mmo1.wandb filter=lfs diff=lfs merge=lfs -text
34
  wandb/run-20220327_210229-2wif55w7/run-2wif55w7.wandb filter=lfs diff=lfs merge=lfs -text
35
  wandb/run-20220327_210229-2wif55w7/logs/debug-internal.log filter=lfs diff=lfs merge=lfs -text
 
33
  wandb/run-20220327_194752-3s89mmo1/run-3s89mmo1.wandb filter=lfs diff=lfs merge=lfs -text
34
  wandb/run-20220327_210229-2wif55w7/run-2wif55w7.wandb filter=lfs diff=lfs merge=lfs -text
35
  wandb/run-20220327_210229-2wif55w7/logs/debug-internal.log filter=lfs diff=lfs merge=lfs -text
36
+ wandb/run-20220328_170142-by95ehra/run-by95ehra.wandb filter=lfs diff=lfs merge=lfs -text
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:47906ce99148d577f91691648d04ab6e595abb6d55afc91054f63ec4a29ec39d
3
  size 2353901617
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07fed569c095c8ad37ad608ff13f9e9ae4ca12f230b3c84e84108ebdd7f343cb
3
  size 2353901617
run_distributed.sh ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env bash
2
+ python -m torch.distributed.launch \
3
+ --nproc_per_node 2 run_speech_recognition_seq2seq.py \
4
+ --dataset_name="librispeech_asr" \
5
+ --model_name_or_path="./" \
6
+ --dataset_config_name="clean" \
7
+ --train_split_name="train.100" \
8
+ --eval_split_name="validation" \
9
+ --output_dir="./" \
10
+ --preprocessing_num_workers="1" \
11
+ --length_column_name="input_length" \
12
+ --overwrite_output_dir \
13
+ --num_train_epochs="10" \
14
+ --per_device_train_batch_size="8" \
15
+ --per_device_eval_batch_size="8" \
16
+ --gradient_accumulation_steps="16" \
17
+ --generation_max_length="40" \
18
+ --generation_num_beams="1" \
19
+ --learning_rate="3e-4" \
20
+ --warmup_steps="500" \
21
+ --evaluation_strategy="steps" \
22
+ --text_column_name="text" \
23
+ --save_steps="500" \
24
+ --eval_steps="500" \
25
+ --logging_steps="1" \
26
+ --save_total_limit="1" \
27
+ --freeze_feature_encoder \
28
+ --gradient_checkpointing \
29
+ --fp16 \
30
+ --group_by_length \
31
+ --predict_with_generate \
32
+ --do_lower_case \
33
+ --do_eval --do_train \
34
+ --push_to_hub \
35
+ --use_auth_token
36
+
run_speech_recognition_seq2seq.py CHANGED
@@ -468,7 +468,7 @@ def main():
468
  optimizers = (optimizer, None)
469
 
470
 
471
- #11. Initialize (Default) Trainer
472
 
473
  trainer = Seq2SeqTrainer(
474
  model=model,
@@ -478,6 +478,7 @@ def main():
478
  tokenizer=feature_extractor,
479
  data_collator=data_collator,
480
  compute_metrics=compute_metrics if training_args.predict_with_generate else None,
 
481
  )
482
 
483
  # 12. Training
468
  optimizers = (optimizer, None)
469
 
470
 
471
+ #11. Initialize Trainer with Adam8bit
472
 
473
  trainer = Seq2SeqTrainer(
474
  model=model,
478
  tokenizer=feature_extractor,
479
  data_collator=data_collator,
480
  compute_metrics=compute_metrics if training_args.predict_with_generate else None,
481
+ optimizers=optimizers,
482
  )
483
 
484
  # 12. Training
runs/Mar28_16-59-05_sanchit--v100/1648486774.395873/events.out.tfevents.1648486774.sanchit--v100.258712.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f53cbe4b17ca33997167d63b80cb9f34616eefe55e4169d2cd80ea1e213b164d
3
+ size 4973
runs/Mar28_16-59-05_sanchit--v100/events.out.tfevents.1648486774.sanchit--v100.258712.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a49a19480d025dd62340326421b1d0bc2bdcf4b2a526014bb4651460aed51a5b
3
+ size 9624
runs/Mar28_17-01-12_sanchit--v100/1648486901.737252/events.out.tfevents.1648486901.sanchit--v100.260352.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d75c131eccd4e3e5b06884413f9bbd6f1cf84bef6bfc9584b70c9c81042e95ad
3
+ size 4973
runs/Mar28_17-01-12_sanchit--v100/events.out.tfevents.1648486901.sanchit--v100.260352.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:086d1cdffa8cc1713d7330f9498692933a2059798816b9d8931c423c9cb55263
3
+ size 87907
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0947a271bdbd47be3b989768a5de1a09693c6228f10aae3ebef93f0a800fda6d
3
  size 3119
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:218e1610b384227b9486326571d5c071d07357c8b4fbe0925dc0186581ad7948
3
  size 3119
wandb/debug-internal.log CHANGED
@@ -1 +1 @@
1
- run-20220327_210229-2wif55w7/logs/debug-internal.log
1
+ run-20220328_170142-by95ehra/logs/debug-internal.log
wandb/debug.log CHANGED
@@ -1 +1 @@
1
- run-20220327_210229-2wif55w7/logs/debug.log
1
+ run-20220328_170142-by95ehra/logs/debug.log
wandb/latest-run CHANGED
@@ -1 +1 @@
1
- run-20220327_210229-2wif55w7
1
+ run-20220328_170142-by95ehra
wandb/run-20220327_210229-2wif55w7/files/config.yaml CHANGED
@@ -8669,7 +8669,14 @@ _wandb:
8669
  - 1
8670
  - 5
8671
  - 11
 
 
 
 
 
8672
  3:
 
 
8673
  - 13
8674
  4: 3.9.5
8675
  5: 0.12.10
8669
  - 1
8670
  - 5
8671
  - 11
8672
+ 2:
8673
+ - 1
8674
+ - 5
8675
+ - 11
8676
+ - 12
8677
  3:
8678
+ - 1
8679
+ - 7
8680
  - 13
8681
  4: 3.9.5
8682
  5: 0.12.10
wandb/run-20220327_210229-2wif55w7/files/output.log CHANGED
@@ -27823,3 +27823,20 @@ Upload file wandb/run-20220327_210229-2wif55w7/logs/debug-internal.log: 100%|█
27823
  eval_steps_per_second = 0.43
27824
  eval_wer = 1.5371
27825
  [INFO|trainer.py:2369] 2022-03-28 11:28:56,189 >> Batch size = 8llowing result as it does not have all the necessary fields:t operations will not be computed-28 11:13:17,895 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
27823
  eval_steps_per_second = 0.43
27824
  eval_wer = 1.5371
27825
  [INFO|trainer.py:2369] 2022-03-28 11:28:56,189 >> Batch size = 8llowing result as it does not have all the necessary fields:t operations will not be computed-28 11:13:17,895 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
27826
+ [INFO|trainer.py:2369] 2022-03-28 11:28:56,189 >> Batch size = 8llowing result as it does not have all the necessary fields:t operations will not be computed-28 11:13:17,895 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
27827
+ [INFO|trainer.py:2369] 2022-03-28 11:28:56,189 >> Batch size = 8llowing result as it does not have all the necessary fields:t operations will not be computed-28 11:13:17,895 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
27828
+ [INFO|trainer.py:2369] 2022-03-28 11:28:56,189 >> Batch size = 8llowing result as it does not have all the necessary fields:t operations will not be computed-28 11:13:17,895 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
27829
+ [INFO|trainer.py:2369] 2022-03-28 11:28:56,189 >> Batch size = 8llowing result as it does not have all the necessary fields:t operations will not be computed-28 11:13:17,895 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
27830
+ [INFO|trainer.py:2369] 2022-03-28 11:28:56,189 >> Batch size = 8llowing result as it does not have all the necessary fields:t operations will not be computed-28 11:13:17,895 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
27831
+ [INFO|trainer.py:2369] 2022-03-28 11:28:56,189 >> Batch size = 8llowing result as it does not have all the necessary fields:t operations will not be computed-28 11:13:17,895 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
27832
+ [INFO|trainer.py:2369] 2022-03-28 11:28:56,189 >> Batch size = 8llowing result as it does not have all the necessary fields:t operations will not be computed-28 11:13:17,895 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
27833
+ [INFO|trainer.py:2369] 2022-03-28 11:28:56,189 >> Batch size = 8llowing result as it does not have all the necessary fields:t operations will not be computed-28 11:13:17,895 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
27834
+ [INFO|trainer.py:2369] 2022-03-28 11:28:56,189 >> Batch size = 8llowing result as it does not have all the necessary fields:t operations will not be computed-28 11:13:17,895 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
27835
+ [INFO|trainer.py:2369] 2022-03-28 11:28:56,189 >> Batch size = 8llowing result as it does not have all the necessary fields:t operations will not be computed-28 11:13:17,895 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
27836
+ [INFO|trainer.py:2369] 2022-03-28 11:28:56,189 >> Batch size = 8llowing result as it does not have all the necessary fields:t operations will not be computed-28 11:13:17,895 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
27837
+ [INFO|trainer.py:2369] 2022-03-28 11:28:56,189 >> Batch size = 8llowing result as it does not have all the necessary fields:t operations will not be computed-28 11:13:17,895 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
27838
+ 03/28/2022 11:42:43 - WARNING - huggingface_hub.repository - To https://huggingface.co/sanchit-gandhi/wav2vec2-2-bart-large-cnn
27839
+ Upload file runs/Mar27_21-02-01_sanchit--v100/events.out.tfevents.1648467705.sanchit--v100.3678730.2: 100%|█| 358/358 [0ields:t operations will not be computed-28 11:13:17,895 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
27840
+ info = model_info(self.finetuned_from)formers/src/transformers/modelcard.py", line 611, in from_trainer, in <module>ields:t operations will not be computed-28 11:13:17,895 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
27841
+ info = model_info(self.finetuned_from)formers/src/transformers/modelcard.py", line 611, in from_trainer, in <module>ields:t operations will not be computed-28 11:13:17,895 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
27842
+ info = model_info(self.finetuned_from)formers/src/transformers/modelcard.py", line 611, in from_trainer, in <module>ields:t operations will not be computed-28 11:13:17,895 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
wandb/run-20220327_210229-2wif55w7/files/wandb-summary.json CHANGED
The diff for this file is too large to render. See raw diff
wandb/run-20220327_210229-2wif55w7/logs/debug-internal.log CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ddba4cd665207dacf7b237e7f4996b0c3cc8f003d7b6a7448b8edbbdfd7ad057
3
- size 10622676
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5bac2f9308ebfa88c90e9e3f64929bac3830ec4c4eeaf4d0a27a017e676e8aa
3
+ size 10639473
wandb/run-20220327_210229-2wif55w7/logs/debug.log CHANGED
@@ -25,3 +25,109 @@ config: {}
25
  2022-03-27 21:02:30,923 INFO MainThread:3678730 [wandb_init.py:init():651] run started, returning control to user process
26
  2022-03-27 21:02:30,925 INFO MainThread:3678730 [wandb_run.py:_config_callback():966] config_cb None None {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'torch.float32', 'use_bfloat16': False, 'pruned_heads': {}, 'tie_word_embeddings': False, 'is_encoder_decoder': True, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 40, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 5, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'architectures': ['SpeechEncoderDecoderModel'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': None, 'pad_token_id': 1, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': 0, 'task_specific_params': None, 'problem_type': None, '_name_or_path': './', 'transformers_version': None, 'decoder': {'vocab_size': 50264, 'max_position_embeddings': 1024, 'd_model': 1024, 'encoder_ffn_dim': 4096, 'encoder_layers': 12, 'encoder_attention_heads': 16, 'decoder_ffn_dim': 4096, 'decoder_layers': 12, 'decoder_attention_heads': 16, 'dropout': 0.1, 'attention_dropout': 0.0, 'activation_dropout': 0.0, 'activation_function': 'gelu', 'init_std': 0.02, 'encoder_layerdrop': 0.0, 'decoder_layerdrop': 0.0, 'classifier_dropout': 0.0, 'use_cache': True, 'num_hidden_layers': 12, 'scale_embedding': False, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'is_encoder_decoder': False, 'is_decoder': True, 'cross_attention_hidden_size': None, 'add_cross_attention': True, 'tie_encoder_decoder': False, 'max_length': 142, 'min_length': 56, 'do_sample': False, 'early_stopping': True, 'num_beams': 4, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 2.0, 'no_repeat_ngram_size': 3, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': 0, 'forced_eos_token_id': 2, 'remove_invalid_values': False, 'architectures': ['BartForConditionalGeneration'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1', 2: 'LABEL_2'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1, 'LABEL_2': 2}, 'tokenizer_class': None, 'prefix': ' ', 'bos_token_id': 0, 'pad_token_id': 1, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': 2, 'task_specific_params': {'summarization': {'early_stopping': True, 'length_penalty': 2.0, 'max_length': 142, 'min_length': 56, 'no_repeat_ngram_size': 3, 'num_beams': 4}}, 'problem_type': None, '_name_or_path': 'facebook/bart-large-cnn', 'transformers_version': '4.17.0.dev0', '_num_labels': 3, 'add_final_layer_norm': False, 'classif_dropout': 0.0, 'force_bos_token_to_be_generated': True, 'gradient_checkpointing': False, 'normalize_before': False, 'output_past': True, 'model_type': 'bart'}, 'encoder': {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'architectures': ['Wav2Vec2ForPreTraining'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': 0, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'facebook/wav2vec2-large-lv60', 'transformers_version': '4.17.0.dev0', 'feat_extract_dropout': 0.0, 'gradient_checkpointing': False, 'hidden_dropout_prob': 0.1, 'num_feat_extract_layers': 7, 'hidden_size': 1024, 'feat_extract_norm': 'layer', 'feat_extract_activation': 'gelu', 'conv_dim': [512, 512, 512, 512, 512, 512, 512], 'conv_stride': [5, 2, 2, 2, 2, 2, 2], 'conv_kernel': [10, 3, 3, 3, 3, 2, 2], 'conv_bias': True, 'num_conv_pos_embeddings': 128, 'num_conv_pos_embedding_groups': 16, 'num_hidden_layers': 24, 'intermediate_size': 4096, 'hidden_act': 'gelu', 'num_attention_heads': 16, 'hidden_dropout': 0.1, 'attention_dropout': 0.1, 'activation_dropout': 0.1, 'feat_proj_dropout': 0.0, 'final_dropout': 0.0, 'layerdrop': 0.0, 'layer_norm_eps': 1e-05, 'initializer_range': 0.02, 'vocab_size': 32, 'do_stable_layer_norm': True, 'use_weighted_layer_sum': False, 'apply_spec_augment': True, 'mask_time_prob': 0.1, 'mask_time_length': 10, 'mask_time_min_masks': 2, 'mask_feature_prob': 0.0, 'mask_feature_length': 10, 'mask_feature_min_masks': 0, 'num_codevectors_per_group': 320, 'num_codevector_groups': 2, 'contrastive_logits_temperature': 0.1, 'feat_quantizer_dropout': 0.0, 'num_negatives': 100, 'codevector_dim': 768, 'proj_codevector_dim': 768, 'diversity_loss_weight': 0.1, 'ctc_loss_reduction': 'sum', 'ctc_zero_infinity': False, 'add_adapter': True, 'adapter_kernel_size': 3, 'adapter_stride': 2, 'num_adapter_layers': 3, 'output_hidden_size': 1024, 'classifier_proj_size': 256, 'tdnn_dim': [512, 512, 512, 512, 1500], 'tdnn_kernel': [5, 3, 3, 1, 1], 'tdnn_dilation': [1, 2, 3, 1, 1], 'xvector_output_dim': 512, 'model_type': 'wav2vec2'}, 'model_type': 'speech-encoder-decoder', 'processor_class': 'Wav2Vec2Processor', 'use_cache': False, 'output_dir': './', 'overwrite_output_dir': True, 'do_train': True, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 8, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': 'None', 'per_gpu_eval_batch_size': 'None', 'gradient_accumulation_steps': 16, 'eval_accumulation_steps': 'None', 'learning_rate': 3e-05, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 10.0, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'warmup_ratio': 0.0, 'warmup_steps': 500, 'log_level': -1, 'log_level_replica': -1, 'log_on_each_node': True, 'logging_dir': './runs/Mar27_21-02-01_sanchit--v100', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 1, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': 1, 'save_on_each_node': False, 'no_cuda': False, 'seed': 42, 'bf16': False, 'fp16': True, 'fp16_opt_level': 'O1', 'half_precision_backend': 'amp', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': 'None', 'local_rank': -1, 'xpu_backend': 'None', 'tpu_num_cores': 'None', 'tpu_metrics_debug': False, 'debug': '[]', 'dataloader_drop_last': False, 'eval_steps': 500, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': './', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': 'None', 'load_best_model_at_end': False, 'metric_for_best_model': 'None', 'greater_is_better': 'None', 'ignore_data_skip': False, 'sharded_ddp': '[]', 'deepspeed': 'None', 'label_smoothing_factor': 0.0, 'optim': 'adamw_hf', 'adafactor': False, 'group_by_length': True, 'length_column_name': 'input_length', 'report_to': "['tensorboard', 'wandb']", 'ddp_find_unused_parameters': 'None', 'ddp_bucket_cap_mb': 'None', 'dataloader_pin_memory': True, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': 'None', 'hub_model_id': 'None', 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'gradient_checkpointing': True, 'fp16_backend': 'auto', 'push_to_hub_model_id': 'None', 'push_to_hub_organization': 'None', 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', '_n_gpu': 1, 'mp_parameters': '', 'sortish_sampler': False, 'predict_with_generate': True, 'generation_max_length': 40, 'generation_num_beams': 1, 'train_batch_size': 8, 'eval_batch_size': 8}
27
  2022-03-27 21:02:30,928 INFO MainThread:3678730 [wandb_watch.py:watch():43] Watching
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25
  2022-03-27 21:02:30,923 INFO MainThread:3678730 [wandb_init.py:init():651] run started, returning control to user process
26
  2022-03-27 21:02:30,925 INFO MainThread:3678730 [wandb_run.py:_config_callback():966] config_cb None None {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'torch.float32', 'use_bfloat16': False, 'pruned_heads': {}, 'tie_word_embeddings': False, 'is_encoder_decoder': True, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 40, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 5, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'architectures': ['SpeechEncoderDecoderModel'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': None, 'pad_token_id': 1, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': 0, 'task_specific_params': None, 'problem_type': None, '_name_or_path': './', 'transformers_version': None, 'decoder': {'vocab_size': 50264, 'max_position_embeddings': 1024, 'd_model': 1024, 'encoder_ffn_dim': 4096, 'encoder_layers': 12, 'encoder_attention_heads': 16, 'decoder_ffn_dim': 4096, 'decoder_layers': 12, 'decoder_attention_heads': 16, 'dropout': 0.1, 'attention_dropout': 0.0, 'activation_dropout': 0.0, 'activation_function': 'gelu', 'init_std': 0.02, 'encoder_layerdrop': 0.0, 'decoder_layerdrop': 0.0, 'classifier_dropout': 0.0, 'use_cache': True, 'num_hidden_layers': 12, 'scale_embedding': False, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'is_encoder_decoder': False, 'is_decoder': True, 'cross_attention_hidden_size': None, 'add_cross_attention': True, 'tie_encoder_decoder': False, 'max_length': 142, 'min_length': 56, 'do_sample': False, 'early_stopping': True, 'num_beams': 4, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 2.0, 'no_repeat_ngram_size': 3, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': 0, 'forced_eos_token_id': 2, 'remove_invalid_values': False, 'architectures': ['BartForConditionalGeneration'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1', 2: 'LABEL_2'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1, 'LABEL_2': 2}, 'tokenizer_class': None, 'prefix': ' ', 'bos_token_id': 0, 'pad_token_id': 1, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': 2, 'task_specific_params': {'summarization': {'early_stopping': True, 'length_penalty': 2.0, 'max_length': 142, 'min_length': 56, 'no_repeat_ngram_size': 3, 'num_beams': 4}}, 'problem_type': None, '_name_or_path': 'facebook/bart-large-cnn', 'transformers_version': '4.17.0.dev0', '_num_labels': 3, 'add_final_layer_norm': False, 'classif_dropout': 0.0, 'force_bos_token_to_be_generated': True, 'gradient_checkpointing': False, 'normalize_before': False, 'output_past': True, 'model_type': 'bart'}, 'encoder': {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'architectures': ['Wav2Vec2ForPreTraining'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': 0, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'facebook/wav2vec2-large-lv60', 'transformers_version': '4.17.0.dev0', 'feat_extract_dropout': 0.0, 'gradient_checkpointing': False, 'hidden_dropout_prob': 0.1, 'num_feat_extract_layers': 7, 'hidden_size': 1024, 'feat_extract_norm': 'layer', 'feat_extract_activation': 'gelu', 'conv_dim': [512, 512, 512, 512, 512, 512, 512], 'conv_stride': [5, 2, 2, 2, 2, 2, 2], 'conv_kernel': [10, 3, 3, 3, 3, 2, 2], 'conv_bias': True, 'num_conv_pos_embeddings': 128, 'num_conv_pos_embedding_groups': 16, 'num_hidden_layers': 24, 'intermediate_size': 4096, 'hidden_act': 'gelu', 'num_attention_heads': 16, 'hidden_dropout': 0.1, 'attention_dropout': 0.1, 'activation_dropout': 0.1, 'feat_proj_dropout': 0.0, 'final_dropout': 0.0, 'layerdrop': 0.0, 'layer_norm_eps': 1e-05, 'initializer_range': 0.02, 'vocab_size': 32, 'do_stable_layer_norm': True, 'use_weighted_layer_sum': False, 'apply_spec_augment': True, 'mask_time_prob': 0.1, 'mask_time_length': 10, 'mask_time_min_masks': 2, 'mask_feature_prob': 0.0, 'mask_feature_length': 10, 'mask_feature_min_masks': 0, 'num_codevectors_per_group': 320, 'num_codevector_groups': 2, 'contrastive_logits_temperature': 0.1, 'feat_quantizer_dropout': 0.0, 'num_negatives': 100, 'codevector_dim': 768, 'proj_codevector_dim': 768, 'diversity_loss_weight': 0.1, 'ctc_loss_reduction': 'sum', 'ctc_zero_infinity': False, 'add_adapter': True, 'adapter_kernel_size': 3, 'adapter_stride': 2, 'num_adapter_layers': 3, 'output_hidden_size': 1024, 'classifier_proj_size': 256, 'tdnn_dim': [512, 512, 512, 512, 1500], 'tdnn_kernel': [5, 3, 3, 1, 1], 'tdnn_dilation': [1, 2, 3, 1, 1], 'xvector_output_dim': 512, 'model_type': 'wav2vec2'}, 'model_type': 'speech-encoder-decoder', 'processor_class': 'Wav2Vec2Processor', 'use_cache': False, 'output_dir': './', 'overwrite_output_dir': True, 'do_train': True, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 8, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': 'None', 'per_gpu_eval_batch_size': 'None', 'gradient_accumulation_steps': 16, 'eval_accumulation_steps': 'None', 'learning_rate': 3e-05, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 10.0, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'warmup_ratio': 0.0, 'warmup_steps': 500, 'log_level': -1, 'log_level_replica': -1, 'log_on_each_node': True, 'logging_dir': './runs/Mar27_21-02-01_sanchit--v100', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 1, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': 1, 'save_on_each_node': False, 'no_cuda': False, 'seed': 42, 'bf16': False, 'fp16': True, 'fp16_opt_level': 'O1', 'half_precision_backend': 'amp', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': 'None', 'local_rank': -1, 'xpu_backend': 'None', 'tpu_num_cores': 'None', 'tpu_metrics_debug': False, 'debug': '[]', 'dataloader_drop_last': False, 'eval_steps': 500, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': './', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': 'None', 'load_best_model_at_end': False, 'metric_for_best_model': 'None', 'greater_is_better': 'None', 'ignore_data_skip': False, 'sharded_ddp': '[]', 'deepspeed': 'None', 'label_smoothing_factor': 0.0, 'optim': 'adamw_hf', 'adafactor': False, 'group_by_length': True, 'length_column_name': 'input_length', 'report_to': "['tensorboard', 'wandb']", 'ddp_find_unused_parameters': 'None', 'ddp_bucket_cap_mb': 'None', 'dataloader_pin_memory': True, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': 'None', 'hub_model_id': 'None', 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'gradient_checkpointing': True, 'fp16_backend': 'auto', 'push_to_hub_model_id': 'None', 'push_to_hub_organization': 'None', 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', '_n_gpu': 1, 'mp_parameters': '', 'sortish_sampler': False, 'predict_with_generate': True, 'generation_max_length': 40, 'generation_num_beams': 1, 'train_batch_size': 8, 'eval_batch_size': 8}
27
  2022-03-27 21:02:30,928 INFO MainThread:3678730 [wandb_watch.py:watch():43] Watching
28
+ 2022-03-28 11:42:47,792 INFO MainThread:3678730 [wandb_run.py:_atexit_cleanup():1797] got exitcode: 1
29
+ 2022-03-28 11:42:47,795 INFO MainThread:3678730 [wandb_run.py:_restore():1769] restore
30
+ 2022-03-28 11:42:50,478 INFO MainThread:3678730 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
31
+ wandb_count: 1
32
+ }
33
+ pusher_stats {
34
+ uploaded_bytes: 2017
35
+ total_bytes: 2017
36
+ }
37
+
38
+ 2022-03-28 11:42:50,581 INFO MainThread:3678730 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
39
+ wandb_count: 1
40
+ }
41
+ pusher_stats {
42
+ uploaded_bytes: 2017
43
+ total_bytes: 2017
44
+ }
45
+
46
+ 2022-03-28 11:42:50,774 INFO MainThread:3678730 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
47
+ wandb_count: 1
48
+ }
49
+ pusher_stats {
50
+ uploaded_bytes: 2017
51
+ total_bytes: 2017
52
+ }
53
+
54
+ 2022-03-28 11:42:51,873 INFO MainThread:3678730 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
55
+ wandb_count: 1
56
+ }
57
+ pusher_stats {
58
+ uploaded_bytes: 2017
59
+ total_bytes: 2017
60
+ }
61
+
62
+ 2022-03-28 11:42:52,242 INFO MainThread:3678730 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
63
+ wandb_count: 4
64
+ }
65
+ pusher_stats {
66
+ uploaded_bytes: 2017
67
+ total_bytes: 9118700
68
+ }
69
+
70
+ 2022-03-28 11:42:52,344 INFO MainThread:3678730 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
71
+ wandb_count: 5
72
+ }
73
+ pusher_stats {
74
+ uploaded_bytes: 1823250
75
+ total_bytes: 9375261
76
+ }
77
+
78
+ 2022-03-28 11:42:52,446 INFO MainThread:3678730 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
79
+ wandb_count: 5
80
+ }
81
+ pusher_stats {
82
+ uploaded_bytes: 9375261
83
+ total_bytes: 9375261
84
+ }
85
+
86
+ 2022-03-28 11:42:52,548 INFO MainThread:3678730 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
87
+ wandb_count: 5
88
+ }
89
+ pusher_stats {
90
+ uploaded_bytes: 9375261
91
+ total_bytes: 9375261
92
+ }
93
+
94
+ 2022-03-28 11:42:52,650 INFO MainThread:3678730 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
95
+ wandb_count: 5
96
+ }
97
+ pusher_stats {
98
+ uploaded_bytes: 9375261
99
+ total_bytes: 9375261
100
+ }
101
+
102
+ 2022-03-28 11:42:52,752 INFO MainThread:3678730 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
103
+ wandb_count: 5
104
+ }
105
+ pusher_stats {
106
+ uploaded_bytes: 9375261
107
+ total_bytes: 9375261
108
+ }
109
+
110
+ 2022-03-28 11:42:53,415 INFO MainThread:3678730 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
111
+ wandb_count: 5
112
+ }
113
+ pusher_stats {
114
+ uploaded_bytes: 9375261
115
+ total_bytes: 9375261
116
+ }
117
+
118
+ 2022-03-28 11:42:53,581 INFO MainThread:3678730 [wandb_run.py:_wait_for_finish():1929] got exit ret: done: true
119
+ exit_result {
120
+ }
121
+ file_counts {
122
+ wandb_count: 5
123
+ }
124
+ pusher_stats {
125
+ uploaded_bytes: 9375261
126
+ total_bytes: 9375261
127
+ }
128
+ local_info {
129
+ }
130
+
131
+ 2022-03-28 11:42:54,806 INFO MainThread:3678730 [wandb_run.py:_append_history():2144] rendering history
132
+ 2022-03-28 11:42:54,807 INFO MainThread:3678730 [wandb_run.py:_append_summary():2102] rendering summary
133
+ 2022-03-28 11:42:54,808 INFO MainThread:3678730 [wandb_run.py:_append_files():2194] logging synced files
wandb/run-20220327_210229-2wif55w7/run-2wif55w7.wandb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0bf45dfd9633a95ac1008847ad5ccda04c7ad13826143cbd3fc96d98bc6b736a
3
- size 456540236
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:009d377537cfce6101e2227e41e2a51f9d730d4116093b317837dc67f3a14e00
3
+ size 457790051
wandb/run-20220328_165934-10ki2qcy/files/config.yaml ADDED
@@ -0,0 +1,716 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ wandb_version: 1
2
+
3
+ _n_gpu:
4
+ desc: null
5
+ value: 1
6
+ _name_or_path:
7
+ desc: null
8
+ value: ./
9
+ _wandb:
10
+ desc: null
11
+ value:
12
+ cli_version: 0.12.10
13
+ framework: huggingface
14
+ huggingface_version: 4.17.0.dev0
15
+ is_jupyter_run: false
16
+ is_kaggle_kernel: false
17
+ m:
18
+ - 1: train/global_step
19
+ 6:
20
+ - 3
21
+ python_version: 3.9.5
22
+ start_time: 1648486774
23
+ t:
24
+ 1:
25
+ - 1
26
+ - 5
27
+ - 11
28
+ 3:
29
+ - 13
30
+ 4: 3.9.5
31
+ 5: 0.12.10
32
+ 6: 4.17.0.dev0
33
+ 8:
34
+ - 5
35
+ adafactor:
36
+ desc: null
37
+ value: false
38
+ adam_beta1:
39
+ desc: null
40
+ value: 0.9
41
+ adam_beta2:
42
+ desc: null
43
+ value: 0.999
44
+ adam_epsilon:
45
+ desc: null
46
+ value: 1.0e-08
47
+ add_cross_attention:
48
+ desc: null
49
+ value: false
50
+ architectures:
51
+ desc: null
52
+ value:
53
+ - SpeechEncoderDecoderModel
54
+ bad_words_ids:
55
+ desc: null
56
+ value: null
57
+ bf16:
58
+ desc: null
59
+ value: false
60
+ bf16_full_eval:
61
+ desc: null
62
+ value: false
63
+ bos_token_id:
64
+ desc: null
65
+ value: null
66
+ chunk_size_feed_forward:
67
+ desc: null
68
+ value: 0
69
+ cross_attention_hidden_size:
70
+ desc: null
71
+ value: null
72
+ dataloader_drop_last:
73
+ desc: null
74
+ value: false
75
+ dataloader_num_workers:
76
+ desc: null
77
+ value: 0
78
+ dataloader_pin_memory:
79
+ desc: null
80
+ value: true
81
+ ddp_bucket_cap_mb:
82
+ desc: null
83
+ value: None
84
+ ddp_find_unused_parameters:
85
+ desc: null
86
+ value: None
87
+ debug:
88
+ desc: null
89
+ value: '[]'
90
+ decoder:
91
+ desc: null
92
+ value:
93
+ _name_or_path: facebook/bart-large-cnn
94
+ _num_labels: 3
95
+ activation_dropout: 0.0
96
+ activation_function: gelu
97
+ add_cross_attention: true
98
+ add_final_layer_norm: false
99
+ architectures:
100
+ - BartForConditionalGeneration
101
+ attention_dropout: 0.0
102
+ bad_words_ids: null
103
+ bos_token_id: 0
104
+ chunk_size_feed_forward: 0
105
+ classif_dropout: 0.0
106
+ classifier_dropout: 0.0
107
+ cross_attention_hidden_size: null
108
+ d_model: 1024
109
+ decoder_attention_heads: 16
110
+ decoder_ffn_dim: 4096
111
+ decoder_layerdrop: 0.0
112
+ decoder_layers: 12
113
+ decoder_start_token_id: 2
114
+ diversity_penalty: 0.0
115
+ do_sample: false
116
+ dropout: 0.1
117
+ early_stopping: true
118
+ encoder_attention_heads: 16
119
+ encoder_ffn_dim: 4096
120
+ encoder_layerdrop: 0.0
121
+ encoder_layers: 12
122
+ encoder_no_repeat_ngram_size: 0
123
+ eos_token_id: 2
124
+ finetuning_task: null
125
+ force_bos_token_to_be_generated: true
126
+ forced_bos_token_id: 0
127
+ forced_eos_token_id: 2
128
+ gradient_checkpointing: false
129
+ id2label:
130
+ '0': LABEL_0
131
+ '1': LABEL_1
132
+ '2': LABEL_2
133
+ init_std: 0.02
134
+ is_decoder: true
135
+ is_encoder_decoder: false
136
+ label2id:
137
+ LABEL_0: 0
138
+ LABEL_1: 1
139
+ LABEL_2: 2
140
+ length_penalty: 2.0
141
+ max_length: 142
142
+ max_position_embeddings: 1024
143
+ min_length: 56
144
+ model_type: bart
145
+ no_repeat_ngram_size: 3
146
+ normalize_before: false
147
+ num_beam_groups: 1
148
+ num_beams: 4
149
+ num_hidden_layers: 12
150
+ num_return_sequences: 1
151
+ output_attentions: false
152
+ output_hidden_states: false
153
+ output_past: true
154
+ output_scores: false
155
+ pad_token_id: 1
156
+ prefix: ' '
157
+ problem_type: null
158
+ pruned_heads: {}
159
+ remove_invalid_values: false
160
+ repetition_penalty: 1.0
161
+ return_dict: true
162
+ return_dict_in_generate: false
163
+ scale_embedding: false
164
+ sep_token_id: null
165
+ task_specific_params:
166
+ summarization:
167
+ early_stopping: true
168
+ length_penalty: 2.0
169
+ max_length: 142
170
+ min_length: 56
171
+ no_repeat_ngram_size: 3
172
+ num_beams: 4
173
+ temperature: 1.0
174
+ tie_encoder_decoder: false
175
+ tie_word_embeddings: true
176
+ tokenizer_class: null
177
+ top_k: 50
178
+ top_p: 1.0
179
+ torch_dtype: null
180
+ torchscript: false
181
+ transformers_version: 4.17.0.dev0
182
+ use_bfloat16: false
183
+ use_cache: true
184
+ vocab_size: 50264
185
+ decoder_start_token_id:
186
+ desc: null
187
+ value: 0
188
+ deepspeed:
189
+ desc: null
190
+ value: None
191
+ disable_tqdm:
192
+ desc: null
193
+ value: false
194
+ diversity_penalty:
195
+ desc: null
196
+ value: 0.0
197
+ do_eval:
198
+ desc: null
199
+ value: true
200
+ do_predict:
201
+ desc: null
202
+ value: false
203
+ do_sample:
204
+ desc: null
205
+ value: false
206
+ do_train:
207
+ desc: null
208
+ value: true
209
+ early_stopping:
210
+ desc: null
211
+ value: false
212
+ encoder:
213
+ desc: null
214
+ value:
215
+ _name_or_path: facebook/wav2vec2-large-lv60
216
+ activation_dropout: 0.1
217
+ adapter_kernel_size: 3
218
+ adapter_stride: 2
219
+ add_adapter: true
220
+ add_cross_attention: false
221
+ apply_spec_augment: true
222
+ architectures:
223
+ - Wav2Vec2ForPreTraining
224
+ attention_dropout: 0.1
225
+ bad_words_ids: null
226
+ bos_token_id: 1
227
+ chunk_size_feed_forward: 0
228
+ classifier_proj_size: 256
229
+ codevector_dim: 768
230
+ contrastive_logits_temperature: 0.1
231
+ conv_bias: true
232
+ conv_dim:
233
+ - 512
234
+ - 512
235
+ - 512
236
+ - 512
237
+ - 512
238
+ - 512
239
+ - 512
240
+ conv_kernel:
241
+ - 10
242
+ - 3
243
+ - 3
244
+ - 3
245
+ - 3
246
+ - 2
247
+ - 2
248
+ conv_stride:
249
+ - 5
250
+ - 2
251
+ - 2
252
+ - 2
253
+ - 2
254
+ - 2
255
+ - 2
256
+ cross_attention_hidden_size: null
257
+ ctc_loss_reduction: sum
258
+ ctc_zero_infinity: false
259
+ decoder_start_token_id: null
260
+ diversity_loss_weight: 0.1
261
+ diversity_penalty: 0.0
262
+ do_sample: false
263
+ do_stable_layer_norm: true
264
+ early_stopping: false
265
+ encoder_no_repeat_ngram_size: 0
266
+ eos_token_id: 2
267
+ feat_extract_activation: gelu
268
+ feat_extract_dropout: 0.0
269
+ feat_extract_norm: layer
270
+ feat_proj_dropout: 0.0
271
+ feat_quantizer_dropout: 0.0
272
+ final_dropout: 0.0
273
+ finetuning_task: null
274
+ forced_bos_token_id: null
275
+ forced_eos_token_id: null
276
+ gradient_checkpointing: false
277
+ hidden_act: gelu
278
+ hidden_dropout: 0.1
279
+ hidden_dropout_prob: 0.1
280
+ hidden_size: 1024
281
+ id2label:
282
+ '0': LABEL_0
283
+ '1': LABEL_1
284
+ initializer_range: 0.02
285
+ intermediate_size: 4096
286
+ is_decoder: false
287
+ is_encoder_decoder: false
288
+ label2id:
289
+ LABEL_0: 0
290
+ LABEL_1: 1
291
+ layer_norm_eps: 1.0e-05
292
+ layerdrop: 0.0
293
+ length_penalty: 1.0
294
+ mask_feature_length: 10
295
+ mask_feature_min_masks: 0
296
+ mask_feature_prob: 0.0
297
+ mask_time_length: 10
298
+ mask_time_min_masks: 2
299
+ mask_time_prob: 0.1
300
+ max_length: 20
301
+ min_length: 0
302
+ model_type: wav2vec2
303
+ no_repeat_ngram_size: 0
304
+ num_adapter_layers: 3
305
+ num_attention_heads: 16
306
+ num_beam_groups: 1
307
+ num_beams: 1
308
+ num_codevector_groups: 2
309
+ num_codevectors_per_group: 320
310
+ num_conv_pos_embedding_groups: 16
311
+ num_conv_pos_embeddings: 128
312
+ num_feat_extract_layers: 7
313
+ num_hidden_layers: 24
314
+ num_negatives: 100
315
+ num_return_sequences: 1
316
+ output_attentions: false
317
+ output_hidden_size: 1024
318
+ output_hidden_states: false
319
+ output_scores: false
320
+ pad_token_id: 0
321
+ prefix: null
322
+ problem_type: null
323
+ proj_codevector_dim: 768
324
+ pruned_heads: {}
325
+ remove_invalid_values: false
326
+ repetition_penalty: 1.0
327
+ return_dict: true
328
+ return_dict_in_generate: false
329
+ sep_token_id: null
330
+ task_specific_params: null
331
+ tdnn_dilation:
332
+ - 1
333
+ - 2
334
+ - 3
335
+ - 1
336
+ - 1
337
+ tdnn_dim:
338
+ - 512
339
+ - 512
340
+ - 512
341
+ - 512
342
+ - 1500
343
+ tdnn_kernel:
344
+ - 5
345
+ - 3
346
+ - 3
347
+ - 1
348
+ - 1
349
+ temperature: 1.0
350
+ tie_encoder_decoder: false
351
+ tie_word_embeddings: true
352
+ tokenizer_class: null
353
+ top_k: 50
354
+ top_p: 1.0
355
+ torch_dtype: null
356
+ torchscript: false
357
+ transformers_version: 4.17.0.dev0
358
+ use_bfloat16: false
359
+ use_weighted_layer_sum: false
360
+ vocab_size: 32
361
+ xvector_output_dim: 512
362
+ encoder_no_repeat_ngram_size:
363
+ desc: null
364
+ value: 0
365
+ eos_token_id:
366
+ desc: null
367
+ value: 2
368
+ eval_accumulation_steps:
369
+ desc: null
370
+ value: None
371
+ eval_batch_size:
372
+ desc: null
373
+ value: 8
374
+ eval_steps:
375
+ desc: null
376
+ value: 500
377
+ evaluation_strategy:
378
+ desc: null
379
+ value: steps
380
+ finetuning_task:
381
+ desc: null
382
+ value: null
383
+ forced_bos_token_id:
384
+ desc: null
385
+ value: null
386
+ forced_eos_token_id:
387
+ desc: null
388
+ value: null
389
+ fp16:
390
+ desc: null
391
+ value: true
392
+ fp16_backend:
393
+ desc: null
394
+ value: auto
395
+ fp16_full_eval:
396
+ desc: null
397
+ value: false
398
+ fp16_opt_level:
399
+ desc: null
400
+ value: O1
401
+ generation_max_length:
402
+ desc: null
403
+ value: 40
404
+ generation_num_beams:
405
+ desc: null
406
+ value: 1
407
+ gradient_accumulation_steps:
408
+ desc: null
409
+ value: 16
410
+ gradient_checkpointing:
411
+ desc: null
412
+ value: true
413
+ greater_is_better:
414
+ desc: null
415
+ value: None
416
+ group_by_length:
417
+ desc: null
418
+ value: true
419
+ half_precision_backend:
420
+ desc: null
421
+ value: amp
422
+ hub_model_id:
423
+ desc: null
424
+ value: None
425
+ hub_strategy:
426
+ desc: null
427
+ value: every_save
428
+ hub_token:
429
+ desc: null
430
+ value: <HUB_TOKEN>
431
+ id2label:
432
+ desc: null
433
+ value:
434
+ '0': LABEL_0
435
+ '1': LABEL_1
436
+ ignore_data_skip:
437
+ desc: null
438
+ value: false
439
+ is_decoder:
440
+ desc: null
441
+ value: false
442
+ is_encoder_decoder:
443
+ desc: null
444
+ value: true
445
+ label2id:
446
+ desc: null
447
+ value:
448
+ LABEL_0: 0
449
+ LABEL_1: 1
450
+ label_names:
451
+ desc: null
452
+ value: None
453
+ label_smoothing_factor:
454
+ desc: null
455
+ value: 0.0
456
+ learning_rate:
457
+ desc: null
458
+ value: 3.0e-05
459
+ length_column_name:
460
+ desc: null
461
+ value: input_length
462
+ length_penalty:
463
+ desc: null
464
+ value: 1.0
465
+ load_best_model_at_end:
466
+ desc: null
467
+ value: false
468
+ local_rank:
469
+ desc: null
470
+ value: -1
471
+ log_level:
472
+ desc: null
473
+ value: -1
474
+ log_level_replica:
475
+ desc: null
476
+ value: -1
477
+ log_on_each_node:
478
+ desc: null
479
+ value: true
480
+ logging_dir:
481
+ desc: null
482
+ value: ./runs/Mar28_16-59-05_sanchit--v100
483
+ logging_first_step:
484
+ desc: null
485
+ value: false
486
+ logging_nan_inf_filter:
487
+ desc: null
488
+ value: true
489
+ logging_steps:
490
+ desc: null
491
+ value: 1
492
+ logging_strategy:
493
+ desc: null
494
+ value: steps
495
+ lr_scheduler_type:
496
+ desc: null
497
+ value: linear
498
+ max_grad_norm:
499
+ desc: null
500
+ value: 1.0
501
+ max_length:
502
+ desc: null
503
+ value: 40
504
+ max_steps:
505
+ desc: null
506
+ value: -1
507
+ metric_for_best_model:
508
+ desc: null
509
+ value: None
510
+ min_length:
511
+ desc: null
512
+ value: 0
513
+ model_type:
514
+ desc: null
515
+ value: speech-encoder-decoder
516
+ mp_parameters:
517
+ desc: null
518
+ value: ''
519
+ no_cuda:
520
+ desc: null
521
+ value: false
522
+ no_repeat_ngram_size:
523
+ desc: null
524
+ value: 0
525
+ num_beam_groups:
526
+ desc: null
527
+ value: 1
528
+ num_beams:
529
+ desc: null
530
+ value: 5
531
+ num_return_sequences:
532
+ desc: null
533
+ value: 1
534
+ num_train_epochs:
535
+ desc: null
536
+ value: 10.0
537
+ optim:
538
+ desc: null
539
+ value: adamw_hf
540
+ output_attentions:
541
+ desc: null
542
+ value: false
543
+ output_dir:
544
+ desc: null
545
+ value: ./
546
+ output_hidden_states:
547
+ desc: null
548
+ value: false
549
+ output_scores:
550
+ desc: null
551
+ value: false
552
+ overwrite_output_dir:
553
+ desc: null
554
+ value: true
555
+ pad_token_id:
556
+ desc: null
557
+ value: 1
558
+ past_index:
559
+ desc: null
560
+ value: -1
561
+ per_device_eval_batch_size:
562
+ desc: null
563
+ value: 8
564
+ per_device_train_batch_size:
565
+ desc: null
566
+ value: 8
567
+ per_gpu_eval_batch_size:
568
+ desc: null
569
+ value: None
570
+ per_gpu_train_batch_size:
571
+ desc: null
572
+ value: None
573
+ predict_with_generate:
574
+ desc: null
575
+ value: true
576
+ prediction_loss_only:
577
+ desc: null
578
+ value: false
579
+ prefix:
580
+ desc: null
581
+ value: null
582
+ problem_type:
583
+ desc: null
584
+ value: null
585
+ processor_class:
586
+ desc: null
587
+ value: Wav2Vec2Processor
588
+ pruned_heads:
589
+ desc: null
590
+ value: {}
591
+ push_to_hub:
592
+ desc: null
593
+ value: true
594
+ push_to_hub_model_id:
595
+ desc: null
596
+ value: None
597
+ push_to_hub_organization:
598
+ desc: null
599
+ value: None
600
+ push_to_hub_token:
601
+ desc: null
602
+ value: <PUSH_TO_HUB_TOKEN>
603
+ remove_invalid_values:
604
+ desc: null
605
+ value: false
606
+ remove_unused_columns:
607
+ desc: null
608
+ value: true
609
+ repetition_penalty:
610
+ desc: null
611
+ value: 1.0
612
+ report_to:
613
+ desc: null
614
+ value: '[''tensorboard'', ''wandb'']'
615
+ resume_from_checkpoint:
616
+ desc: null
617
+ value: None
618
+ return_dict:
619
+ desc: null
620
+ value: true
621
+ return_dict_in_generate:
622
+ desc: null
623
+ value: false
624
+ run_name:
625
+ desc: null
626
+ value: ./
627
+ save_on_each_node:
628
+ desc: null
629
+ value: false
630
+ save_steps:
631
+ desc: null
632
+ value: 500
633
+ save_strategy:
634
+ desc: null
635
+ value: steps
636
+ save_total_limit:
637
+ desc: null
638
+ value: 1
639
+ seed:
640
+ desc: null
641
+ value: 42
642
+ sep_token_id:
643
+ desc: null
644
+ value: null
645
+ sharded_ddp:
646
+ desc: null
647
+ value: '[]'
648
+ skip_memory_metrics:
649
+ desc: null
650
+ value: true
651
+ sortish_sampler:
652
+ desc: null
653
+ value: false
654
+ task_specific_params:
655
+ desc: null
656
+ value: null
657
+ temperature:
658
+ desc: null
659
+ value: 1.0
660
+ tf32:
661
+ desc: null
662
+ value: None
663
+ tie_encoder_decoder:
664
+ desc: null
665
+ value: false
666
+ tie_word_embeddings:
667
+ desc: null
668
+ value: false
669
+ tokenizer_class:
670
+ desc: null
671
+ value: null
672
+ top_k:
673
+ desc: null
674
+ value: 50
675
+ top_p:
676
+ desc: null
677
+ value: 1.0
678
+ torch_dtype:
679
+ desc: null
680
+ value: torch.float32
681
+ torchscript:
682
+ desc: null
683
+ value: false
684
+ tpu_metrics_debug:
685
+ desc: null
686
+ value: false
687
+ tpu_num_cores:
688
+ desc: null
689
+ value: None
690
+ train_batch_size:
691
+ desc: null
692
+ value: 8
693
+ transformers_version:
694
+ desc: null
695
+ value: null
696
+ use_bfloat16:
697
+ desc: null
698
+ value: false
699
+ use_cache:
700
+ desc: null
701
+ value: false
702
+ use_legacy_prediction_loop:
703
+ desc: null
704
+ value: false
705
+ warmup_ratio:
706
+ desc: null
707
+ value: 0.0
708
+ warmup_steps:
709
+ desc: null
710
+ value: 500
711
+ weight_decay:
712
+ desc: null
713
+ value: 0.0
714
+ xpu_backend:
715
+ desc: null
716
+ value: None
wandb/run-20220328_165934-10ki2qcy/files/output.log ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ 0%| | 0/2230 [00:00<?, ?it/s][WARNING|modeling_bart.py:1051] 2022-03-28 16:59:37,626 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
3
+ [WARNING|modeling_utils.py:388] 2022-03-28 16:59:38,446 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
4
+ [WARNING|modeling_bart.py:1051] 2022-03-28 16:59:39,671 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
5
+ [WARNING|modeling_utils.py:388] 2022-03-28 16:59:40,344 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
6
+ [WARNING|modeling_bart.py:1051] 2022-03-28 16:59:41,567 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
7
+ [WARNING|modeling_utils.py:388] 2022-03-28 16:59:42,214 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
8
+ [WARNING|modeling_bart.py:1051] 2022-03-28 16:59:43,414 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
9
+ [WARNING|modeling_utils.py:388] 2022-03-28 16:59:44,083 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
10
+ [WARNING|modeling_bart.py:1051] 2022-03-28 16:59:45,285 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
11
+ [WARNING|modeling_utils.py:388] 2022-03-28 16:59:45,922 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
12
+ [WARNING|modeling_bart.py:1051] 2022-03-28 16:59:47,142 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
13
+ [WARNING|modeling_utils.py:388] 2022-03-28 16:59:47,775 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
14
+ [WARNING|modeling_bart.py:1051] 2022-03-28 16:59:48,976 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
15
+ [WARNING|modeling_utils.py:388] 2022-03-28 16:59:49,640 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
16
+ [WARNING|modeling_bart.py:1051] 2022-03-28 16:59:50,844 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
17
+ [WARNING|modeling_utils.py:388] 2022-03-28 16:59:51,509 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
18
+ [WARNING|modeling_bart.py:1051] 2022-03-28 16:59:52,710 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
19
+ [WARNING|modeling_utils.py:388] 2022-03-28 16:59:53,428 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
20
+ [WARNING|modeling_bart.py:1051] 2022-03-28 16:59:54,614 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
21
+ [WARNING|modeling_utils.py:388] 2022-03-28 16:59:55,274 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
22
+ [WARNING|modeling_bart.py:1051] 2022-03-28 16:59:56,459 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
23
+ [WARNING|modeling_utils.py:388] 2022-03-28 16:59:57,112 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
24
+ [WARNING|modeling_bart.py:1051] 2022-03-28 16:59:58,292 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
25
+ [WARNING|modeling_utils.py:388] 2022-03-28 16:59:58,921 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
26
+ [WARNING|modeling_bart.py:1051] 2022-03-28 17:00:00,093 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
27
+ [WARNING|modeling_utils.py:388] 2022-03-28 17:00:00,757 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
28
+ [WARNING|modeling_bart.py:1051] 2022-03-28 17:00:01,927 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
29
+ [WARNING|modeling_utils.py:388] 2022-03-28 17:00:02,553 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
30
+ [WARNING|modeling_bart.py:1051] 2022-03-28 17:00:03,722 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
31
+ [WARNING|modeling_utils.py:388] 2022-03-28 17:00:04,347 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
32
+ [WARNING|modeling_bart.py:1051] 2022-03-28 17:00:05,548 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
33
+ [WARNING|modeling_utils.py:388] 2022-03-28 17:00:06,195 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
34
+ 0%| | 1/2230 [00:30<18:42:06, 30.20s/it]
35
+ 0%| | 1/2230 [00:30<18:42:06, 30.20s/it][WARNING|modeling_bart.py:1051] 2022-03-28 17:00:07,403 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
36
+ [WARNING|modeling_utils.py:388] 2022-03-28 17:00:08,017 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
37
+ [WARNING|modeling_bart.py:1051] 2022-03-28 17:00:09,176 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
38
+ [WARNING|modeling_utils.py:388] 2022-03-28 17:00:09,804 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
39
+ [WARNING|modeling_bart.py:1051] 2022-03-28 17:00:10,962 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
40
+ [WARNING|modeling_utils.py:388] 2022-03-28 17:00:11,609 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
41
+ [WARNING|modeling_bart.py:1051] 2022-03-28 17:00:12,778 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
42
+ [WARNING|modeling_utils.py:388] 2022-03-28 17:00:13,401 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
43
+ [WARNING|modeling_bart.py:1051] 2022-03-28 17:00:14,595 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
44
+ [WARNING|modeling_utils.py:388] 2022-03-28 17:00:15,240 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
45
+ [WARNING|modeling_bart.py:1051] 2022-03-28 17:00:16,385 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
46
+ [WARNING|modeling_utils.py:388] 2022-03-28 17:00:17,008 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
47
+ [WARNING|modeling_bart.py:1051] 2022-03-28 17:00:18,180 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
48
+ [WARNING|modeling_utils.py:388] 2022-03-28 17:00:18,824 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
49
+ [WARNING|modeling_bart.py:1051] 2022-03-28 17:00:20,031 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
50
+ [WARNING|modeling_utils.py:388] 2022-03-28 17:00:20,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
51
+ [WARNING|modeling_bart.py:1051] 2022-03-28 17:00:21,831 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
52
+ [WARNING|modeling_utils.py:388] 2022-03-28 17:00:22,439 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
53
+ [WARNING|modeling_bart.py:1051] 2022-03-28 17:00:23,608 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
54
+ [WARNING|modeling_utils.py:388] 2022-03-28 17:00:24,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
55
+ [WARNING|modeling_bart.py:1051] 2022-03-28 17:00:25,417 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
56
+ [WARNING|modeling_utils.py:388] 2022-03-28 17:00:26,038 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
57
+ [WARNING|modeling_bart.py:1051] 2022-03-28 17:00:27,176 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
wandb/run-20220328_165934-10ki2qcy/files/requirements.txt ADDED
@@ -0,0 +1,186 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ absl-py==1.0.0
2
+ aiohttp==3.8.1
3
+ aiosignal==1.2.0
4
+ anyio==3.5.0
5
+ appdirs==1.4.4
6
+ argon2-cffi-bindings==21.2.0
7
+ argon2-cffi==21.3.0
8
+ asttokens==2.0.5
9
+ async-timeout==4.0.2
10
+ attrs==21.4.0
11
+ audioread==2.1.9
12
+ babel==2.9.1
13
+ backcall==0.2.0
14
+ bitsandbytes-cuda113==0.26.0
15
+ black==22.1.0
16
+ bleach==4.1.0
17
+ cachetools==5.0.0
18
+ certifi==2021.10.8
19
+ cffi==1.15.0
20
+ charset-normalizer==2.0.11
21
+ chex==0.1.0
22
+ click==8.0.3
23
+ clldutils==3.10.1
24
+ colorlog==6.6.0
25
+ csvw==1.11.0
26
+ cycler==0.11.0
27
+ datasets==1.18.3
28
+ debugpy==1.5.1
29
+ decorator==5.1.1
30
+ defusedxml==0.7.1
31
+ dill==0.3.4
32
+ dlinfo==1.2.1
33
+ dm-tree==0.1.6
34
+ docker-pycreds==0.4.0
35
+ entrypoints==0.4
36
+ executing==0.8.2
37
+ filelock==3.4.2
38
+ flatbuffers==2.0
39
+ flax==0.4.0
40
+ fonttools==4.29.1
41
+ frozenlist==1.3.0
42
+ fsspec==2022.1.0
43
+ gitdb==4.0.9
44
+ gitpython==3.1.27
45
+ google-auth-oauthlib==0.4.6
46
+ google-auth==2.6.0
47
+ grpcio==1.43.0
48
+ huggingface-hub==0.4.0
49
+ hypothesis==6.36.1
50
+ idna==3.3
51
+ importlib-metadata==4.10.1
52
+ ipdb==0.13.9
53
+ ipykernel==6.8.0
54
+ ipython-genutils==0.2.0
55
+ ipython==8.0.1
56
+ ipywidgets==7.6.5
57
+ isodate==0.6.1
58
+ jax==0.2.28
59
+ jaxlib==0.1.76+cuda11.cudnn82
60
+ jedi==0.18.1
61
+ jinja2==3.0.3
62
+ jiwer==2.3.0
63
+ joblib==1.1.0
64
+ json5==0.9.6
65
+ jsonschema==4.4.0
66
+ jupyter-client==7.1.2
67
+ jupyter-console==6.4.0
68
+ jupyter-core==4.9.1
69
+ jupyter-server==1.13.5
70
+ jupyter==1.0.0
71
+ jupyterlab-pygments==0.1.2
72
+ jupyterlab-server==2.10.3
73
+ jupyterlab-widgets==1.0.2
74
+ jupyterlab==3.2.9
75
+ kiwisolver==1.3.2
76
+ librosa==0.8.1
77
+ llvmlite==0.38.0
78
+ markdown==3.3.6
79
+ markupsafe==2.0.1
80
+ matplotlib-inline==0.1.3
81
+ matplotlib==3.5.1
82
+ mistune==0.8.4
83
+ msgpack==1.0.3
84
+ multidict==6.0.2
85
+ multiprocess==0.70.12.2
86
+ mypy-extensions==0.4.3
87
+ nbclassic==0.3.5
88
+ nbclient==0.5.10
89
+ nbconvert==6.4.1
90
+ nbformat==5.1.3
91
+ nest-asyncio==1.5.4
92
+ notebook==6.4.8
93
+ numba==0.55.1
94
+ numpy==1.21.5
95
+ oauthlib==3.2.0
96
+ opt-einsum==3.3.0
97
+ optax==0.1.0
98
+ packaging==21.3
99
+ pandas==1.4.0
100
+ pandocfilters==1.5.0
101
+ parso==0.8.3
102
+ pathspec==0.9.0
103
+ pathtools==0.1.2
104
+ pexpect==4.8.0
105
+ phonemizer==3.0.1
106
+ pickleshare==0.7.5
107
+ pillow==9.0.0
108
+ pip==22.0.2
109
+ pkg-resources==0.0.0
110
+ platformdirs==2.4.1
111
+ pooch==1.6.0
112
+ prometheus-client==0.13.1
113
+ promise==2.3
114
+ prompt-toolkit==3.0.26
115
+ protobuf==3.19.4
116
+ psutil==5.9.0
117
+ ptyprocess==0.7.0
118
+ pure-eval==0.2.2
119
+ pyarrow==6.0.1
120
+ pyasn1-modules==0.2.8
121
+ pyasn1==0.4.8
122
+ pycparser==2.21
123
+ pyctcdecode==0.3.0
124
+ pygments==2.11.2
125
+ pygtrie==2.4.2
126
+ pyparsing==3.0.7
127
+ pyrsistent==0.18.1
128
+ python-dateutil==2.8.2
129
+ python-levenshtein==0.12.2
130
+ pytz==2021.3
131
+ pyyaml==6.0
132
+ pyzmq==22.3.0
133
+ qtconsole==5.2.2
134
+ qtpy==2.0.1
135
+ regex==2022.1.18
136
+ requests-oauthlib==1.3.1
137
+ requests==2.27.1
138
+ resampy==0.2.2
139
+ rfc3986==2.0.0
140
+ rsa==4.8
141
+ sacremoses==0.0.47
142
+ scikit-learn==1.0.2
143
+ scipy==1.7.3
144
+ segments==2.2.0
145
+ send2trash==1.8.0
146
+ sentry-sdk==1.5.6
147
+ setuptools==44.1.1
148
+ shortuuid==1.0.8
149
+ six==1.16.0
150
+ smmap==5.0.0
151
+ sniffio==1.2.0
152
+ sortedcontainers==2.4.0
153
+ soundfile==0.10.3.post1
154
+ stack-data==0.1.4
155
+ tabulate==0.8.9
156
+ tensorboard-data-server==0.6.1
157
+ tensorboard-plugin-wit==1.8.1
158
+ tensorboard==2.8.0
159
+ termcolor==1.1.0
160
+ terminado==0.13.1
161
+ testpath==0.5.0
162
+ threadpoolctl==3.1.0
163
+ tokenizers==0.11.4
164
+ toml==0.10.2
165
+ tomli==2.0.0
166
+ toolz==0.11.2
167
+ torch==1.10.2+cu113
168
+ torchaudio==0.10.2+cu113
169
+ tornado==6.1
170
+ tqdm==4.62.3
171
+ traitlets==5.1.1
172
+ transformers==4.17.0.dev0
173
+ typing-extensions==3.10.0.2
174
+ uritemplate==4.1.1
175
+ urllib3==1.26.8
176
+ wandb==0.12.10
177
+ wcwidth==0.2.5
178
+ webencodings==0.5.1
179
+ websocket-client==1.2.3
180
+ werkzeug==2.0.2
181
+ wheel==0.37.1
182
+ widgetsnbextension==3.5.2
183
+ xxhash==2.0.2
184
+ yarl==1.7.2
185
+ yaspin==2.1.0
186
+ zipp==3.7.0
wandb/run-20220328_165934-10ki2qcy/files/wandb-metadata.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "os": "Linux-5.11.0-1028-gcp-x86_64-with-glibc2.33",
3
+ "python": "3.9.5",
4
+ "heartbeatAt": "2022-03-28T16:59:35.909514",
5
+ "startedAt": "2022-03-28T16:59:34.735552",
6
+ "docker": null,
7
+ "gpu": "Tesla V100-SXM2-16GB",
8
+ "gpu_count": 2,
9
+ "cpu_count": 16,
10
+ "cuda": null,
11
+ "args": [
12
+ "--dataset_name=librispeech_asr",
13
+ "--model_name_or_path=./",
14
+ "--dataset_config_name=clean",
15
+ "--train_split_name=train.100",
16
+ "--eval_split_name=validation",
17
+ "--output_dir=./",
18
+ "--preprocessing_num_workers=1",
19
+ "--length_column_name=input_length",
20
+ "--overwrite_output_dir",
21
+ "--num_train_epochs=10",
22
+ "--per_device_train_batch_size=8",
23
+ "--per_device_eval_batch_size=8",
24
+ "--gradient_accumulation_steps=16",
25
+ "--generation_max_length=40",
26
+ "--generation_num_beams=1",
27
+ "--learning_rate=3e-5",
28
+ "--warmup_steps=500",
29
+ "--evaluation_strategy=steps",
30
+ "--text_column_name=text",
31
+ "--save_steps=500",
32
+ "--eval_steps=500",
33
+ "--logging_steps=1",
34
+ "--save_total_limit=1",
35
+ "--freeze_feature_encoder",
36
+ "--gradient_checkpointing",
37
+ "--fp16",
38
+ "--group_by_length",
39
+ "--predict_with_generate",
40
+ "--do_lower_case",
41
+ "--do_eval",
42
+ "--do_train",
43
+ "--push_to_hub",
44
+ "--use_auth_token"
45
+ ],
46
+ "state": "running",
47
+ "program": "/home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/run_speech_recognition_seq2seq.py",
48
+ "codePath": "run_speech_recognition_seq2seq.py",
49
+ "git": {
50
+ "remote": "https://huggingface.co/sanchit-gandhi/wav2vec2-2-bart-large-cnn",
51
+ "commit": "91fd052a291010848498467796c4dbcaa5f0935b"
52
+ },
53
+ "email": "sanchit@huggingface.co",
54
+ "root": "/home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn",
55
+ "host": "sanchit--v100",
56
+ "username": "sanchit_huggingface_co",
57
+ "executable": "/home/sanchit_huggingface_co/gcp/bin/python"
58
+ }
wandb/run-20220328_165934-10ki2qcy/files/wandb-summary.json ADDED
@@ -0,0 +1 @@
 
1
+ {"train/loss": 8.3195, "train/learning_rate": 0.0, "train/epoch": 0.0, "train/global_step": 1, "_runtime": 32, "_timestamp": 1648486806, "_step": 0}
wandb/run-20220328_165934-10ki2qcy/logs/debug-internal.log ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2022-03-28 16:59:35,636 INFO MainThread:259155 [internal.py:wandb_internal():89] W&B internal server running at pid: 259155, started at: 2022-03-28 16:59:35.636382
2
+ 2022-03-28 16:59:35,639 DEBUG HandlerThread:259155 [handler.py:handle_request():131] handle_request: check_version
3
+ 2022-03-28 16:59:35,639 INFO WriterThread:259155 [datastore.py:open_for_write():77] open: /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220328_165934-10ki2qcy/run-10ki2qcy.wandb
4
+ 2022-03-28 16:59:35,640 DEBUG SenderThread:259155 [sender.py:send():235] send: header
5
+ 2022-03-28 16:59:35,640 DEBUG SenderThread:259155 [sender.py:send_request():249] send_request: check_version
6
+ 2022-03-28 16:59:35,708 DEBUG SenderThread:259155 [sender.py:send():235] send: run
7
+ 2022-03-28 16:59:35,817 INFO SenderThread:259155 [dir_watcher.py:__init__():169] watching files in: /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220328_165934-10ki2qcy/files
8
+ 2022-03-28 16:59:35,817 INFO SenderThread:259155 [sender.py:_start_run_threads():809] run started: 10ki2qcy with start time 1648486774
9
+ 2022-03-28 16:59:35,817 DEBUG SenderThread:259155 [sender.py:send():235] send: summary
10
+ 2022-03-28 16:59:35,817 INFO SenderThread:259155 [sender.py:_save_file():944] saving file wandb-summary.json with policy end
11
+ 2022-03-28 16:59:35,818 DEBUG HandlerThread:259155 [handler.py:handle_request():131] handle_request: run_start
12
+ 2022-03-28 16:59:35,909 DEBUG HandlerThread:259155 [meta.py:__init__():36] meta init
13
+ 2022-03-28 16:59:35,909 DEBUG HandlerThread:259155 [meta.py:__init__():50] meta init done
14
+ 2022-03-28 16:59:35,909 DEBUG HandlerThread:259155 [meta.py:probe():210] probe
15
+ 2022-03-28 16:59:35,915 DEBUG HandlerThread:259155 [meta.py:_setup_git():200] setup git
16
+ 2022-03-28 16:59:35,930 DEBUG HandlerThread:259155 [meta.py:_setup_git():207] setup git done
17
+ 2022-03-28 16:59:35,930 DEBUG HandlerThread:259155 [meta.py:_save_pip():54] save pip
18
+ 2022-03-28 16:59:35,931 DEBUG HandlerThread:259155 [meta.py:_save_pip():68] save pip done
19
+ 2022-03-28 16:59:35,931 DEBUG HandlerThread:259155 [meta.py:probe():248] probe done
20
+ 2022-03-28 16:59:36,010 DEBUG SenderThread:259155 [sender.py:send():235] send: files
21
+ 2022-03-28 16:59:36,010 INFO SenderThread:259155 [sender.py:_save_file():944] saving file wandb-metadata.json with policy now
22
+ 2022-03-28 16:59:36,015 DEBUG HandlerThread:259155 [handler.py:handle_request():131] handle_request: stop_status
23
+ 2022-03-28 16:59:36,015 DEBUG SenderThread:259155 [sender.py:send_request():249] send_request: stop_status
24
+ 2022-03-28 16:59:36,048 DEBUG SenderThread:259155 [sender.py:send():235] send: config
25
+ 2022-03-28 16:59:36,049 DEBUG SenderThread:259155 [sender.py:send():235] send: metric
26
+ 2022-03-28 16:59:36,049 DEBUG SenderThread:259155 [sender.py:send():235] send: metric
27
+ 2022-03-28 16:59:36,049 WARNING SenderThread:259155 [sender.py:send_metric():902] Seen metric with glob (shouldnt happen)
28
+ 2022-03-28 16:59:36,279 INFO Thread-11 :259155 [upload_job.py:push():137] Uploaded file /tmp/tmprchn9a1qwandb/vemwlqdn-wandb-metadata.json
29
+ 2022-03-28 16:59:36,819 INFO Thread-8 :259155 [dir_watcher.py:_on_file_created():217] file/dir created: /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220328_165934-10ki2qcy/files/wandb-metadata.json
30
+ 2022-03-28 16:59:36,819 INFO Thread-8 :259155 [dir_watcher.py:_on_file_created():217] file/dir created: /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220328_165934-10ki2qcy/files/wandb-summary.json
31
+ 2022-03-28 16:59:36,819 INFO Thread-8 :259155 [dir_watcher.py:_on_file_created():217] file/dir created: /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220328_165934-10ki2qcy/files/requirements.txt
32
+ 2022-03-28 16:59:36,819 INFO Thread-8 :259155 [dir_watcher.py:_on_file_created():217] file/dir created: /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220328_165934-10ki2qcy/files/output.log
33
+ 2022-03-28 16:59:38,818 INFO Thread-8 :259155 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220328_165934-10ki2qcy/files/output.log
34
+ 2022-03-28 16:59:40,819 INFO Thread-8 :259155 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220328_165934-10ki2qcy/files/output.log
35
+ 2022-03-28 16:59:42,820 INFO Thread-8 :259155 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220328_165934-10ki2qcy/files/output.log
36
+ 2022-03-28 16:59:44,820 INFO Thread-8 :259155 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220328_165934-10ki2qcy/files/output.log
37
+ 2022-03-28 16:59:46,821 INFO Thread-8 :259155 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220328_165934-10ki2qcy/files/output.log
38
+ 2022-03-28 16:59:48,822 INFO Thread-8 :259155 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220328_165934-10ki2qcy/files/output.log
39
+ 2022-03-28 16:59:50,823 INFO Thread-8 :259155 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220328_165934-10ki2qcy/files/output.log
40
+ 2022-03-28 16:59:51,253 DEBUG HandlerThread:259155 [handler.py:handle_request():131] handle_request: stop_status
41
+ 2022-03-28 16:59:51,254 DEBUG SenderThread:259155 [sender.py:send_request():249] send_request: stop_status
42
+ 2022-03-28 16:59:52,823 INFO Thread-8 :259155 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220328_165934-10ki2qcy/files/output.log
43
+ 2022-03-28 16:59:54,824 INFO Thread-8 :259155 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220328_165934-10ki2qcy/files/output.log
44
+ 2022-03-28 16:59:56,825 INFO Thread-8 :259155 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220328_165934-10ki2qcy/files/output.log
45
+ 2022-03-28 16:59:58,825 INFO Thread-8 :259155 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220328_165934-10ki2qcy/files/output.log
46
+ 2022-03-28 17:00:00,826 INFO Thread-8 :259155 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220328_165934-10ki2qcy/files/output.log
47
+ 2022-03-28 17:00:02,827 INFO Thread-8 :259155 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220328_165934-10ki2qcy/files/output.log
48
+ 2022-03-28 17:00:04,785 DEBUG SenderThread:259155 [sender.py:send():235] send: stats
49
+ 2022-03-28 17:00:04,828 INFO Thread-8 :259155 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220328_165934-10ki2qcy/files/output.log
50
+ 2022-03-28 17:00:06,243 DEBUG SenderThread:259155 [sender.py:send():235] send: metric
51
+ 2022-03-28 17:00:06,243 DEBUG SenderThread:259155 [sender.py:send():235] send: metric
52
+ 2022-03-28 17:00:06,243 DEBUG SenderThread:259155 [sender.py:send():235] send: metric
53
+ 2022-03-28 17:00:06,243 DEBUG SenderThread:259155 [sender.py:send():235] send: history
54
+ 2022-03-28 17:00:06,243 DEBUG SenderThread:259155 [sender.py:send():235] send: summary
55
+ 2022-03-28 17:00:06,244 INFO SenderThread:259155 [sender.py:_save_file():944] saving file wandb-summary.json with policy end
56
+ 2022-03-28 17:00:06,601 DEBUG HandlerThread:259155 [handler.py:handle_request():131] handle_request: stop_status
57
+ 2022-03-28 17:00:06,601 DEBUG SenderThread:259155 [sender.py:send_request():249] send_request: stop_status
58
+ 2022-03-28 17:00:06,829 INFO Thread-8 :259155 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220328_165934-10ki2qcy/files/wandb-summary.json
59
+ 2022-03-28 17:00:06,829 INFO Thread-8 :259155 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220328_165934-10ki2qcy/files/config.yaml
60
+ 2022-03-28 17:00:06,829 INFO Thread-8 :259155 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220328_165934-10ki2qcy/files/output.log
61
+ 2022-03-28 17:00:08,829 INFO Thread-8 :259155 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220328_165934-10ki2qcy/files/output.log
62
+ 2022-03-28 17:00:10,830 INFO Thread-8 :259155 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220328_165934-10ki2qcy/files/output.log
63
+ 2022-03-28 17:00:12,831 INFO Thread-8 :259155 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220328_165934-10ki2qcy/files/output.log
64
+ 2022-03-28 17:00:14,832 INFO Thread-8 :259155 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220328_165934-10ki2qcy/files/output.log
65
+ 2022-03-28 17:00:16,832 INFO Thread-8 :259155 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220328_165934-10ki2qcy/files/output.log
66
+ 2022-03-28 17:00:18,833 INFO Thread-8 :259155 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220328_165934-10ki2qcy/files/output.log
67
+ 2022-03-28 17:00:21,776 DEBUG HandlerThread:259155 [handler.py:handle_request():131] handle_request: stop_status
68
+ 2022-03-28 17:00:21,776 DEBUG SenderThread:259155 [sender.py:send_request():249] send_request: stop_status
69
+ 2022-03-28 17:00:21,834 INFO Thread-8 :259155 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220328_165934-10ki2qcy/files/output.log
70
+ 2022-03-28 17:00:23,835 INFO Thread-8 :259155 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220328_165934-10ki2qcy/files/output.log
71
+ 2022-03-28 17:00:25,836 INFO Thread-8 :259155 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220328_165934-10ki2qcy/files/output.log
72
+ 2022-03-28 17:00:27,836 INFO Thread-8 :259155 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220328_165934-10ki2qcy/files/output.log
73
+ 2022-03-28 17:00:29,137 WARNING MainThread:259155 [internal.py:wandb_internal():152] Internal process interrupt: 1
74
+ 2022-03-28 17:00:29,317 WARNING MainThread:259155 [internal.py:wandb_internal():152] Internal process interrupt: 2
75
+ 2022-03-28 17:00:29,317 ERROR MainThread:259155 [internal.py:wandb_internal():155] Internal process interrupted.
76
+ 2022-03-28 17:00:29,660 INFO MainThread:259155 [internal.py:handle_exit():79] Internal process exited
wandb/run-20220328_165934-10ki2qcy/logs/debug.log ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2022-03-28 16:59:34,737 INFO MainThread:258712 [wandb_setup.py:_flush():75] Loading settings from /home/sanchit_huggingface_co/.config/wandb/settings
2
+ 2022-03-28 16:59:34,737 INFO MainThread:258712 [wandb_setup.py:_flush():75] Loading settings from /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/settings
3
+ 2022-03-28 16:59:34,737 INFO MainThread:258712 [wandb_setup.py:_flush():75] Loading settings from environment variables: {}
4
+ 2022-03-28 16:59:34,737 INFO MainThread:258712 [wandb_setup.py:_flush():75] Inferring run settings from compute environment: {'program_relpath': 'run_speech_recognition_seq2seq.py', 'program': '/home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/run_speech_recognition_seq2seq.py'}
5
+ 2022-03-28 16:59:34,737 INFO MainThread:258712 [wandb_init.py:_log_setup():386] Logging user logs to /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220328_165934-10ki2qcy/logs/debug.log
6
+ 2022-03-28 16:59:34,737 INFO MainThread:258712 [wandb_init.py:_log_setup():387] Logging internal logs to /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220328_165934-10ki2qcy/logs/debug-internal.log
7
+ 2022-03-28 16:59:34,737 INFO MainThread:258712 [wandb_init.py:init():420] calling init triggers
8
+ 2022-03-28 16:59:34,737 INFO MainThread:258712 [wandb_init.py:init():425] wandb.init called with sweep_config: {}
9
+ config: {}
10
+ 2022-03-28 16:59:34,737 INFO MainThread:258712 [wandb_init.py:init():471] starting backend
11
+ 2022-03-28 16:59:34,737 INFO MainThread:258712 [backend.py:_multiprocessing_setup():99] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
12
+ 2022-03-28 16:59:34,794 INFO MainThread:258712 [backend.py:ensure_launched():219] starting backend process...
13
+ 2022-03-28 16:59:34,851 INFO MainThread:258712 [backend.py:ensure_launched():224] started backend process with pid: 259155
14
+ 2022-03-28 16:59:34,853 INFO MainThread:258712 [wandb_init.py:init():480] backend started and connected
15
+ 2022-03-28 16:59:34,864 INFO MainThread:258712 [wandb_init.py:init():550] updated telemetry
16
+ 2022-03-28 16:59:34,999 INFO MainThread:258712 [wandb_init.py:init():581] communicating current version
17
+ 2022-03-28 16:59:35,706 INFO MainThread:258712 [wandb_init.py:init():586] got version response upgrade_message: "wandb version 0.12.11 is available! To upgrade, please run:\n $ pip install wandb --upgrade"
18
+
19
+ 2022-03-28 16:59:35,707 INFO MainThread:258712 [wandb_init.py:init():596] communicating run to backend with 30 second timeout
20
+ 2022-03-28 16:59:35,817 INFO MainThread:258712 [wandb_init.py:init():624] starting run threads in backend
21
+ 2022-03-28 16:59:36,015 INFO MainThread:258712 [wandb_run.py:_console_start():1827] atexit reg
22
+ 2022-03-28 16:59:36,015 INFO MainThread:258712 [wandb_run.py:_redirect():1701] redirect: SettingsConsole.REDIRECT
23
+ 2022-03-28 16:59:36,016 INFO MainThread:258712 [wandb_run.py:_redirect():1706] Redirecting console.
24
+ 2022-03-28 16:59:36,017 INFO MainThread:258712 [wandb_run.py:_redirect():1762] Redirects installed.
25
+ 2022-03-28 16:59:36,017 INFO MainThread:258712 [wandb_init.py:init():651] run started, returning control to user process
26
+ 2022-03-28 16:59:36,020 INFO MainThread:258712 [wandb_run.py:_config_callback():966] config_cb None None {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'torch.float32', 'use_bfloat16': False, 'pruned_heads': {}, 'tie_word_embeddings': False, 'is_encoder_decoder': True, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 40, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 5, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'architectures': ['SpeechEncoderDecoderModel'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': None, 'pad_token_id': 1, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': 0, 'task_specific_params': None, 'problem_type': None, '_name_or_path': './', 'transformers_version': None, 'decoder': {'vocab_size': 50264, 'max_position_embeddings': 1024, 'd_model': 1024, 'encoder_ffn_dim': 4096, 'encoder_layers': 12, 'encoder_attention_heads': 16, 'decoder_ffn_dim': 4096, 'decoder_layers': 12, 'decoder_attention_heads': 16, 'dropout': 0.1, 'attention_dropout': 0.0, 'activation_dropout': 0.0, 'activation_function': 'gelu', 'init_std': 0.02, 'encoder_layerdrop': 0.0, 'decoder_layerdrop': 0.0, 'classifier_dropout': 0.0, 'use_cache': True, 'num_hidden_layers': 12, 'scale_embedding': False, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'is_encoder_decoder': False, 'is_decoder': True, 'cross_attention_hidden_size': None, 'add_cross_attention': True, 'tie_encoder_decoder': False, 'max_length': 142, 'min_length': 56, 'do_sample': False, 'early_stopping': True, 'num_beams': 4, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 2.0, 'no_repeat_ngram_size': 3, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': 0, 'forced_eos_token_id': 2, 'remove_invalid_values': False, 'architectures': ['BartForConditionalGeneration'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1', 2: 'LABEL_2'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1, 'LABEL_2': 2}, 'tokenizer_class': None, 'prefix': ' ', 'bos_token_id': 0, 'pad_token_id': 1, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': 2, 'task_specific_params': {'summarization': {'early_stopping': True, 'length_penalty': 2.0, 'max_length': 142, 'min_length': 56, 'no_repeat_ngram_size': 3, 'num_beams': 4}}, 'problem_type': None, '_name_or_path': 'facebook/bart-large-cnn', 'transformers_version': '4.17.0.dev0', '_num_labels': 3, 'add_final_layer_norm': False, 'classif_dropout': 0.0, 'force_bos_token_to_be_generated': True, 'gradient_checkpointing': False, 'normalize_before': False, 'output_past': True, 'model_type': 'bart'}, 'encoder': {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'architectures': ['Wav2Vec2ForPreTraining'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': 0, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'facebook/wav2vec2-large-lv60', 'transformers_version': '4.17.0.dev0', 'feat_extract_dropout': 0.0, 'gradient_checkpointing': False, 'hidden_dropout_prob': 0.1, 'num_feat_extract_layers': 7, 'hidden_size': 1024, 'feat_extract_norm': 'layer', 'feat_extract_activation': 'gelu', 'conv_dim': [512, 512, 512, 512, 512, 512, 512], 'conv_stride': [5, 2, 2, 2, 2, 2, 2], 'conv_kernel': [10, 3, 3, 3, 3, 2, 2], 'conv_bias': True, 'num_conv_pos_embeddings': 128, 'num_conv_pos_embedding_groups': 16, 'num_hidden_layers': 24, 'intermediate_size': 4096, 'hidden_act': 'gelu', 'num_attention_heads': 16, 'hidden_dropout': 0.1, 'attention_dropout': 0.1, 'activation_dropout': 0.1, 'feat_proj_dropout': 0.0, 'final_dropout': 0.0, 'layerdrop': 0.0, 'layer_norm_eps': 1e-05, 'initializer_range': 0.02, 'vocab_size': 32, 'do_stable_layer_norm': True, 'use_weighted_layer_sum': False, 'apply_spec_augment': True, 'mask_time_prob': 0.1, 'mask_time_length': 10, 'mask_time_min_masks': 2, 'mask_feature_prob': 0.0, 'mask_feature_length': 10, 'mask_feature_min_masks': 0, 'num_codevectors_per_group': 320, 'num_codevector_groups': 2, 'contrastive_logits_temperature': 0.1, 'feat_quantizer_dropout': 0.0, 'num_negatives': 100, 'codevector_dim': 768, 'proj_codevector_dim': 768, 'diversity_loss_weight': 0.1, 'ctc_loss_reduction': 'sum', 'ctc_zero_infinity': False, 'add_adapter': True, 'adapter_kernel_size': 3, 'adapter_stride': 2, 'num_adapter_layers': 3, 'output_hidden_size': 1024, 'classifier_proj_size': 256, 'tdnn_dim': [512, 512, 512, 512, 1500], 'tdnn_kernel': [5, 3, 3, 1, 1], 'tdnn_dilation': [1, 2, 3, 1, 1], 'xvector_output_dim': 512, 'model_type': 'wav2vec2'}, 'model_type': 'speech-encoder-decoder', 'processor_class': 'Wav2Vec2Processor', 'use_cache': False, 'output_dir': './', 'overwrite_output_dir': True, 'do_train': True, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 8, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': 'None', 'per_gpu_eval_batch_size': 'None', 'gradient_accumulation_steps': 16, 'eval_accumulation_steps': 'None', 'learning_rate': 3e-05, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 10.0, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'warmup_ratio': 0.0, 'warmup_steps': 500, 'log_level': -1, 'log_level_replica': -1, 'log_on_each_node': True, 'logging_dir': './runs/Mar28_16-59-05_sanchit--v100', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 1, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': 1, 'save_on_each_node': False, 'no_cuda': False, 'seed': 42, 'bf16': False, 'fp16': True, 'fp16_opt_level': 'O1', 'half_precision_backend': 'amp', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': 'None', 'local_rank': -1, 'xpu_backend': 'None', 'tpu_num_cores': 'None', 'tpu_metrics_debug': False, 'debug': '[]', 'dataloader_drop_last': False, 'eval_steps': 500, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': './', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': 'None', 'load_best_model_at_end': False, 'metric_for_best_model': 'None', 'greater_is_better': 'None', 'ignore_data_skip': False, 'sharded_ddp': '[]', 'deepspeed': 'None', 'label_smoothing_factor': 0.0, 'optim': 'adamw_hf', 'adafactor': False, 'group_by_length': True, 'length_column_name': 'input_length', 'report_to': "['tensorboard', 'wandb']", 'ddp_find_unused_parameters': 'None', 'ddp_bucket_cap_mb': 'None', 'dataloader_pin_memory': True, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': 'None', 'hub_model_id': 'None', 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'gradient_checkpointing': True, 'fp16_backend': 'auto', 'push_to_hub_model_id': 'None', 'push_to_hub_organization': 'None', 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', '_n_gpu': 1, 'mp_parameters': '', 'sortish_sampler': False, 'predict_with_generate': True, 'generation_max_length': 40, 'generation_num_beams': 1, 'train_batch_size': 8, 'eval_batch_size': 8}
27
+ 2022-03-28 16:59:36,023 INFO MainThread:258712 [wandb_watch.py:watch():43] Watching
28
+ 2022-03-28 17:00:29,590 INFO MainThread:258712 [wandb_run.py:_atexit_cleanup():1797] got exitcode: 255
29
+ 2022-03-28 17:00:29,591 INFO MainThread:258712 [wandb_run.py:_restore():1769] restore
wandb/run-20220328_165934-10ki2qcy/run-10ki2qcy.wandb ADDED
Binary file (17.3 kB). View file
wandb/run-20220328_170142-by95ehra/files/config.yaml ADDED
The diff for this file is too large to render. See raw diff
wandb/run-20220328_170142-by95ehra/files/output.log ADDED
The diff for this file is too large to render. See raw diff
wandb/run-20220328_170142-by95ehra/files/requirements.txt ADDED
@@ -0,0 +1,186 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ absl-py==1.0.0
2
+ aiohttp==3.8.1
3
+ aiosignal==1.2.0
4
+ anyio==3.5.0
5
+ appdirs==1.4.4
6
+ argon2-cffi-bindings==21.2.0
7
+ argon2-cffi==21.3.0
8
+ asttokens==2.0.5
9
+ async-timeout==4.0.2
10
+ attrs==21.4.0
11
+ audioread==2.1.9
12
+ babel==2.9.1
13
+ backcall==0.2.0
14
+ bitsandbytes-cuda113==0.26.0
15
+ black==22.1.0
16
+ bleach==4.1.0
17
+ cachetools==5.0.0
18
+ certifi==2021.10.8
19
+ cffi==1.15.0
20
+ charset-normalizer==2.0.11
21
+ chex==0.1.0
22
+ click==8.0.3
23
+ clldutils==3.10.1
24
+ colorlog==6.6.0
25
+ csvw==1.11.0
26
+ cycler==0.11.0
27
+ datasets==1.18.3
28
+ debugpy==1.5.1
29
+ decorator==5.1.1
30
+ defusedxml==0.7.1
31
+ dill==0.3.4
32
+ dlinfo==1.2.1
33
+ dm-tree==0.1.6
34
+ docker-pycreds==0.4.0
35
+ entrypoints==0.4
36
+ executing==0.8.2
37
+ filelock==3.4.2
38
+ flatbuffers==2.0
39
+ flax==0.4.0
40
+ fonttools==4.29.1
41
+ frozenlist==1.3.0
42
+ fsspec==2022.1.0
43
+ gitdb==4.0.9
44
+ gitpython==3.1.27
45
+ google-auth-oauthlib==0.4.6
46
+ google-auth==2.6.0
47
+ grpcio==1.43.0
48
+ huggingface-hub==0.4.0
49
+ hypothesis==6.36.1
50
+ idna==3.3
51
+ importlib-metadata==4.10.1
52
+ ipdb==0.13.9
53
+ ipykernel==6.8.0
54
+ ipython-genutils==0.2.0
55
+ ipython==8.0.1
56
+ ipywidgets==7.6.5
57
+ isodate==0.6.1
58
+ jax==0.2.28
59
+ jaxlib==0.1.76+cuda11.cudnn82
60
+ jedi==0.18.1
61
+ jinja2==3.0.3
62
+ jiwer==2.3.0
63
+ joblib==1.1.0
64
+ json5==0.9.6
65
+ jsonschema==4.4.0
66
+ jupyter-client==7.1.2
67
+ jupyter-console==6.4.0
68
+ jupyter-core==4.9.1
69
+ jupyter-server==1.13.5
70
+ jupyter==1.0.0
71
+ jupyterlab-pygments==0.1.2
72
+ jupyterlab-server==2.10.3
73
+ jupyterlab-widgets==1.0.2
74
+ jupyterlab==3.2.9
75
+ kiwisolver==1.3.2
76
+ librosa==0.8.1
77
+ llvmlite==0.38.0
78
+ markdown==3.3.6
79
+ markupsafe==2.0.1
80
+ matplotlib-inline==0.1.3
81
+ matplotlib==3.5.1
82
+ mistune==0.8.4
83
+ msgpack==1.0.3
84
+ multidict==6.0.2
85
+ multiprocess==0.70.12.2
86
+ mypy-extensions==0.4.3
87
+ nbclassic==0.3.5
88
+ nbclient==0.5.10
89
+ nbconvert==6.4.1
90
+ nbformat==5.1.3
91
+ nest-asyncio==1.5.4
92
+ notebook==6.4.8
93
+ numba==0.55.1
94
+ numpy==1.21.5
95
+ oauthlib==3.2.0
96
+ opt-einsum==3.3.0
97
+ optax==0.1.0
98
+ packaging==21.3
99
+ pandas==1.4.0
100
+ pandocfilters==1.5.0
101
+ parso==0.8.3
102
+ pathspec==0.9.0
103
+ pathtools==0.1.2
104
+ pexpect==4.8.0
105
+ phonemizer==3.0.1
106
+ pickleshare==0.7.5
107
+ pillow==9.0.0
108
+ pip==22.0.2
109
+ pkg-resources==0.0.0
110
+ platformdirs==2.4.1
111
+ pooch==1.6.0
112
+ prometheus-client==0.13.1
113
+ promise==2.3
114
+ prompt-toolkit==3.0.26
115
+ protobuf==3.19.4
116
+ psutil==5.9.0
117
+ ptyprocess==0.7.0
118
+ pure-eval==0.2.2
119
+ pyarrow==6.0.1
120
+ pyasn1-modules==0.2.8
121
+ pyasn1==0.4.8
122
+ pycparser==2.21
123
+ pyctcdecode==0.3.0
124
+ pygments==2.11.2
125
+ pygtrie==2.4.2
126
+ pyparsing==3.0.7
127
+ pyrsistent==0.18.1
128
+ python-dateutil==2.8.2
129
+ python-levenshtein==0.12.2
130
+ pytz==2021.3
131
+ pyyaml==6.0
132
+ pyzmq==22.3.0
133
+ qtconsole==5.2.2
134
+ qtpy==2.0.1
135
+ regex==2022.1.18
136
+ requests-oauthlib==1.3.1
137
+ requests==2.27.1
138
+ resampy==0.2.2
139
+ rfc3986==2.0.0
140
+ rsa==4.8
141
+ sacremoses==0.0.47
142
+ scikit-learn==1.0.2
143
+ scipy==1.7.3
144
+ segments==2.2.0
145
+ send2trash==1.8.0
146
+ sentry-sdk==1.5.6
147
+ setuptools==44.1.1
148
+ shortuuid==1.0.8
149
+ six==1.16.0
150
+ smmap==5.0.0
151
+ sniffio==1.2.0
152
+ sortedcontainers==2.4.0
153
+ soundfile==0.10.3.post1
154
+ stack-data==0.1.4
155
+ tabulate==0.8.9
156
+ tensorboard-data-server==0.6.1
157
+ tensorboard-plugin-wit==1.8.1
158
+ tensorboard==2.8.0
159
+ termcolor==1.1.0
160
+ terminado==0.13.1
161
+ testpath==0.5.0
162
+ threadpoolctl==3.1.0
163
+ tokenizers==0.11.4
164
+ toml==0.10.2
165
+ tomli==2.0.0
166
+ toolz==0.11.2
167
+ torch==1.10.2+cu113
168
+ torchaudio==0.10.2+cu113
169
+ tornado==6.1
170
+ tqdm==4.62.3
171
+ traitlets==5.1.1
172
+ transformers==4.17.0.dev0
173
+ typing-extensions==3.10.0.2
174
+ uritemplate==4.1.1
175
+ urllib3==1.26.8
176
+ wandb==0.12.10
177
+ wcwidth==0.2.5
178
+ webencodings==0.5.1
179
+ websocket-client==1.2.3
180
+ werkzeug==2.0.2
181
+ wheel==0.37.1
182
+ widgetsnbextension==3.5.2
183
+ xxhash==2.0.2
184
+ yarl==1.7.2
185
+ yaspin==2.1.0
186
+ zipp==3.7.0
wandb/run-20220328_170142-by95ehra/files/wandb-metadata.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "os": "Linux-5.11.0-1028-gcp-x86_64-with-glibc2.33",
3
+ "python": "3.9.5",
4
+ "heartbeatAt": "2022-03-28T17:01:43.328132",
5
+ "startedAt": "2022-03-28T17:01:42.187826",
6
+ "docker": null,
7
+ "gpu": "Tesla V100-SXM2-16GB",
8
+ "gpu_count": 2,
9
+ "cpu_count": 16,
10
+ "cuda": null,
11
+ "args": [
12
+ "--local_rank=0",
13
+ "--dataset_name=librispeech_asr",
14
+ "--model_name_or_path=./",
15
+ "--dataset_config_name=clean",
16
+ "--train_split_name=train.100",
17
+ "--eval_split_name=validation",
18
+ "--output_dir=./",
19
+ "--preprocessing_num_workers=1",
20
+ "--length_column_name=input_length",
21
+ "--overwrite_output_dir",
22
+ "--num_train_epochs=10",
23
+ "--per_device_train_batch_size=8",
24
+ "--per_device_eval_batch_size=8",
25
+ "--gradient_accumulation_steps=16",
26
+ "--generation_max_length=40",
27
+ "--generation_num_beams=1",
28
+ "--learning_rate=3e-4",
29
+ "--warmup_steps=500",
30
+ "--evaluation_strategy=steps",
31
+ "--text_column_name=text",
32
+ "--save_steps=500",
33
+ "--eval_steps=500",
34
+ "--logging_steps=1",
35
+ "--save_total_limit=1",
36
+ "--freeze_feature_encoder",
37
+ "--gradient_checkpointing",
38
+ "--fp16",
39
+ "--group_by_length",
40
+ "--predict_with_generate",
41
+ "--do_lower_case",
42
+ "--do_eval",
43
+ "--do_train",
44
+ "--push_to_hub",
45
+ "--use_auth_token"
46
+ ],
47
+ "state": "running",
48
+ "program": "/home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/run_speech_recognition_seq2seq.py",
49
+ "codePath": "run_speech_recognition_seq2seq.py",
50
+ "git": {
51
+ "remote": "https://huggingface.co/sanchit-gandhi/wav2vec2-2-bart-large-cnn",
52
+ "commit": "91fd052a291010848498467796c4dbcaa5f0935b"
53
+ },
54
+ "email": "sanchit@huggingface.co",
55
+ "root": "/home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn",
56
+ "host": "sanchit--v100",
57
+ "username": "sanchit_huggingface_co",
58
+ "executable": "/home/sanchit_huggingface_co/gcp/bin/python"
59
+ }
wandb/run-20220328_170142-by95ehra/files/wandb-summary.json ADDED
The diff for this file is too large to render. See raw diff
wandb/run-20220328_170142-by95ehra/logs/debug-internal.log ADDED
The diff for this file is too large to render. See raw diff
wandb/run-20220328_170142-by95ehra/logs/debug.log ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2022-03-28 17:01:42,189 INFO MainThread:260352 [wandb_setup.py:_flush():75] Loading settings from /home/sanchit_huggingface_co/.config/wandb/settings
2
+ 2022-03-28 17:01:42,189 INFO MainThread:260352 [wandb_setup.py:_flush():75] Loading settings from /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/settings
3
+ 2022-03-28 17:01:42,189 INFO MainThread:260352 [wandb_setup.py:_flush():75] Loading settings from environment variables: {}
4
+ 2022-03-28 17:01:42,189 INFO MainThread:260352 [wandb_setup.py:_flush():75] Inferring run settings from compute environment: {'program_relpath': 'run_speech_recognition_seq2seq.py', 'program': '/home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/run_speech_recognition_seq2seq.py'}
5
+ 2022-03-28 17:01:42,189 INFO MainThread:260352 [wandb_init.py:_log_setup():386] Logging user logs to /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220328_170142-by95ehra/logs/debug.log
6
+ 2022-03-28 17:01:42,190 INFO MainThread:260352 [wandb_init.py:_log_setup():387] Logging internal logs to /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220328_170142-by95ehra/logs/debug-internal.log
7
+ 2022-03-28 17:01:42,190 INFO MainThread:260352 [wandb_init.py:init():420] calling init triggers
8
+ 2022-03-28 17:01:42,190 INFO MainThread:260352 [wandb_init.py:init():425] wandb.init called with sweep_config: {}
9
+ config: {}
10
+ 2022-03-28 17:01:42,190 INFO MainThread:260352 [wandb_init.py:init():471] starting backend
11
+ 2022-03-28 17:01:42,190 INFO MainThread:260352 [backend.py:_multiprocessing_setup():99] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
12
+ 2022-03-28 17:01:42,252 INFO MainThread:260352 [backend.py:ensure_launched():219] starting backend process...
13
+ 2022-03-28 17:01:42,312 INFO MainThread:260352 [backend.py:ensure_launched():224] started backend process with pid: 260770
14
+ 2022-03-28 17:01:42,314 INFO MainThread:260352 [wandb_init.py:init():480] backend started and connected
15
+ 2022-03-28 17:01:42,325 INFO MainThread:260352 [wandb_init.py:init():550] updated telemetry
16
+ 2022-03-28 17:01:42,472 INFO MainThread:260352 [wandb_init.py:init():581] communicating current version
17
+ 2022-03-28 17:01:43,113 INFO MainThread:260352 [wandb_init.py:init():586] got version response upgrade_message: "wandb version 0.12.11 is available! To upgrade, please run:\n $ pip install wandb --upgrade"
18
+
19
+ 2022-03-28 17:01:43,113 INFO MainThread:260352 [wandb_init.py:init():596] communicating run to backend with 30 second timeout
20
+ 2022-03-28 17:01:43,217 INFO MainThread:260352 [wandb_init.py:init():624] starting run threads in backend
21
+ 2022-03-28 17:01:43,429 INFO MainThread:260352 [wandb_run.py:_console_start():1827] atexit reg
22
+ 2022-03-28 17:01:43,429 INFO MainThread:260352 [wandb_run.py:_redirect():1701] redirect: SettingsConsole.REDIRECT
23
+ 2022-03-28 17:01:43,429 INFO MainThread:260352 [wandb_run.py:_redirect():1706] Redirecting console.
24
+ 2022-03-28 17:01:43,431 INFO MainThread:260352 [wandb_run.py:_redirect():1762] Redirects installed.
25
+ 2022-03-28 17:01:43,431 INFO MainThread:260352 [wandb_init.py:init():651] run started, returning control to user process
26
+ 2022-03-28 17:01:43,433 INFO MainThread:260352 [wandb_run.py:_config_callback():966] config_cb None None {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'torch.float32', 'use_bfloat16': False, 'pruned_heads': {}, 'tie_word_embeddings': False, 'is_encoder_decoder': True, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 40, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 5, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'architectures': ['SpeechEncoderDecoderModel'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': None, 'pad_token_id': 1, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': 0, 'task_specific_params': None, 'problem_type': None, '_name_or_path': './', 'transformers_version': None, 'decoder': {'vocab_size': 50264, 'max_position_embeddings': 1024, 'd_model': 1024, 'encoder_ffn_dim': 4096, 'encoder_layers': 12, 'encoder_attention_heads': 16, 'decoder_ffn_dim': 4096, 'decoder_layers': 12, 'decoder_attention_heads': 16, 'dropout': 0.1, 'attention_dropout': 0.0, 'activation_dropout': 0.0, 'activation_function': 'gelu', 'init_std': 0.02, 'encoder_layerdrop': 0.0, 'decoder_layerdrop': 0.0, 'classifier_dropout': 0.0, 'use_cache': True, 'num_hidden_layers': 12, 'scale_embedding': False, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'is_encoder_decoder': False, 'is_decoder': True, 'cross_attention_hidden_size': None, 'add_cross_attention': True, 'tie_encoder_decoder': False, 'max_length': 142, 'min_length': 56, 'do_sample': False, 'early_stopping': True, 'num_beams': 4, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 2.0, 'no_repeat_ngram_size': 3, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': 0, 'forced_eos_token_id': 2, 'remove_invalid_values': False, 'architectures': ['BartForConditionalGeneration'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1', 2: 'LABEL_2'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1, 'LABEL_2': 2}, 'tokenizer_class': None, 'prefix': ' ', 'bos_token_id': 0, 'pad_token_id': 1, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': 2, 'task_specific_params': {'summarization': {'early_stopping': True, 'length_penalty': 2.0, 'max_length': 142, 'min_length': 56, 'no_repeat_ngram_size': 3, 'num_beams': 4}}, 'problem_type': None, '_name_or_path': 'facebook/bart-large-cnn', 'transformers_version': '4.17.0.dev0', '_num_labels': 3, 'add_final_layer_norm': False, 'classif_dropout': 0.0, 'force_bos_token_to_be_generated': True, 'gradient_checkpointing': False, 'normalize_before': False, 'output_past': True, 'model_type': 'bart'}, 'encoder': {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'architectures': ['Wav2Vec2ForPreTraining'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': 0, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'facebook/wav2vec2-large-lv60', 'transformers_version': '4.17.0.dev0', 'feat_extract_dropout': 0.0, 'gradient_checkpointing': False, 'hidden_dropout_prob': 0.1, 'num_feat_extract_layers': 7, 'hidden_size': 1024, 'feat_extract_norm': 'layer', 'feat_extract_activation': 'gelu', 'conv_dim': [512, 512, 512, 512, 512, 512, 512], 'conv_stride': [5, 2, 2, 2, 2, 2, 2], 'conv_kernel': [10, 3, 3, 3, 3, 2, 2], 'conv_bias': True, 'num_conv_pos_embeddings': 128, 'num_conv_pos_embedding_groups': 16, 'num_hidden_layers': 24, 'intermediate_size': 4096, 'hidden_act': 'gelu', 'num_attention_heads': 16, 'hidden_dropout': 0.1, 'attention_dropout': 0.1, 'activation_dropout': 0.1, 'feat_proj_dropout': 0.0, 'final_dropout': 0.0, 'layerdrop': 0.0, 'layer_norm_eps': 1e-05, 'initializer_range': 0.02, 'vocab_size': 32, 'do_stable_layer_norm': True, 'use_weighted_layer_sum': False, 'apply_spec_augment': True, 'mask_time_prob': 0.1, 'mask_time_length': 10, 'mask_time_min_masks': 2, 'mask_feature_prob': 0.0, 'mask_feature_length': 10, 'mask_feature_min_masks': 0, 'num_codevectors_per_group': 320, 'num_codevector_groups': 2, 'contrastive_logits_temperature': 0.1, 'feat_quantizer_dropout': 0.0, 'num_negatives': 100, 'codevector_dim': 768, 'proj_codevector_dim': 768, 'diversity_loss_weight': 0.1, 'ctc_loss_reduction': 'sum', 'ctc_zero_infinity': False, 'add_adapter': True, 'adapter_kernel_size': 3, 'adapter_stride': 2, 'num_adapter_layers': 3, 'output_hidden_size': 1024, 'classifier_proj_size': 256, 'tdnn_dim': [512, 512, 512, 512, 1500], 'tdnn_kernel': [5, 3, 3, 1, 1], 'tdnn_dilation': [1, 2, 3, 1, 1], 'xvector_output_dim': 512, 'model_type': 'wav2vec2'}, 'model_type': 'speech-encoder-decoder', 'processor_class': 'Wav2Vec2Processor', 'use_cache': False, 'output_dir': './', 'overwrite_output_dir': True, 'do_train': True, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 8, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': 'None', 'per_gpu_eval_batch_size': 'None', 'gradient_accumulation_steps': 16, 'eval_accumulation_steps': 'None', 'learning_rate': 0.0003, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 10.0, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'warmup_ratio': 0.0, 'warmup_steps': 500, 'log_level': -1, 'log_level_replica': -1, 'log_on_each_node': True, 'logging_dir': './runs/Mar28_17-01-12_sanchit--v100', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 1, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': 1, 'save_on_each_node': False, 'no_cuda': False, 'seed': 42, 'bf16': False, 'fp16': True, 'fp16_opt_level': 'O1', 'half_precision_backend': 'amp', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': 'None', 'local_rank': 0, 'xpu_backend': 'None', 'tpu_num_cores': 'None', 'tpu_metrics_debug': False, 'debug': '[]', 'dataloader_drop_last': False, 'eval_steps': 500, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': './', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': 'None', 'load_best_model_at_end': False, 'metric_for_best_model': 'None', 'greater_is_better': 'None', 'ignore_data_skip': False, 'sharded_ddp': '[]', 'deepspeed': 'None', 'label_smoothing_factor': 0.0, 'optim': 'adamw_hf', 'adafactor': False, 'group_by_length': True, 'length_column_name': 'input_length', 'report_to': "['tensorboard', 'wandb']", 'ddp_find_unused_parameters': 'None', 'ddp_bucket_cap_mb': 'None', 'dataloader_pin_memory': True, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': 'None', 'hub_model_id': 'None', 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'gradient_checkpointing': True, 'fp16_backend': 'auto', 'push_to_hub_model_id': 'None', 'push_to_hub_organization': 'None', 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', '_n_gpu': 1, 'mp_parameters': '', 'sortish_sampler': False, 'predict_with_generate': True, 'generation_max_length': 40, 'generation_num_beams': 1, 'train_batch_size': 8, 'eval_batch_size': 8}
27
+ 2022-03-28 17:01:43,436 INFO MainThread:260352 [wandb_watch.py:watch():43] Watching
wandb/run-20220328_170142-by95ehra/run-by95ehra.wandb ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5effea33220015452961f352885a0ad0ed4979c1445231492a2520205d77479
3
+ size 98697243