sanchit-gandhi HF staff commited on
Commit
251aa59
1 Parent(s): 0e7d81d

Training in progress, step 500

Browse files
Files changed (33) hide show
  1. .gitattributes +2 -0
  2. pytorch_model.bin +1 -1
  3. run_librispeech.sh +1 -1
  4. runs/Mar27_19-47-24_sanchit--v100/1648410471.8274474/events.out.tfevents.1648410471.sanchit--v100.3630555.1 +3 -0
  5. runs/Mar27_19-47-24_sanchit--v100/events.out.tfevents.1648410471.sanchit--v100.3630555.0 +3 -0
  6. runs/Mar27_21-02-01_sanchit--v100/1648414949.4091816/events.out.tfevents.1648414949.sanchit--v100.3678730.1 +3 -0
  7. runs/Mar27_21-02-01_sanchit--v100/events.out.tfevents.1648414949.sanchit--v100.3678730.0 +3 -0
  8. training_args.bin +1 -1
  9. wandb/debug-internal.log +1 -1
  10. wandb/debug.log +1 -1
  11. wandb/latest-run +1 -1
  12. wandb/run-20220326_171130-bdf5nvyg/files/config.yaml +7 -0
  13. wandb/run-20220326_171130-bdf5nvyg/files/output.log +17 -0
  14. wandb/run-20220326_171130-bdf5nvyg/files/wandb-summary.json +0 -0
  15. wandb/run-20220326_171130-bdf5nvyg/logs/debug-internal.log +2 -2
  16. wandb/run-20220326_171130-bdf5nvyg/logs/debug.log +290 -0
  17. wandb/run-20220326_171130-bdf5nvyg/run-bdf5nvyg.wandb +2 -2
  18. wandb/run-20220327_194752-3s89mmo1/files/config.yaml +0 -0
  19. wandb/run-20220327_194752-3s89mmo1/files/output.log +0 -0
  20. wandb/run-20220327_194752-3s89mmo1/files/requirements.txt +186 -0
  21. wandb/run-20220327_194752-3s89mmo1/files/wandb-metadata.json +58 -0
  22. wandb/run-20220327_194752-3s89mmo1/files/wandb-summary.json +0 -0
  23. wandb/run-20220327_194752-3s89mmo1/logs/debug-internal.log +0 -0
  24. wandb/run-20220327_194752-3s89mmo1/logs/debug.log +29 -0
  25. wandb/run-20220327_194752-3s89mmo1/run-3s89mmo1.wandb +3 -0
  26. wandb/run-20220327_210229-2wif55w7/files/config.yaml +0 -0
  27. wandb/run-20220327_210229-2wif55w7/files/output.log +0 -0
  28. wandb/run-20220327_210229-2wif55w7/files/requirements.txt +186 -0
  29. wandb/run-20220327_210229-2wif55w7/files/wandb-metadata.json +58 -0
  30. wandb/run-20220327_210229-2wif55w7/files/wandb-summary.json +0 -0
  31. wandb/run-20220327_210229-2wif55w7/logs/debug-internal.log +0 -0
  32. wandb/run-20220327_210229-2wif55w7/logs/debug.log +27 -0
  33. wandb/run-20220327_210229-2wif55w7/run-2wif55w7.wandb +3 -0
.gitattributes CHANGED
@@ -30,3 +30,5 @@ wandb/run-20220323_165914-1vl16ira/run-1vl16ira.wandb filter=lfs diff=lfs merge=
30
  wandb/run-20220325_193848-1sz5964i/run-1sz5964i.wandb filter=lfs diff=lfs merge=lfs -text
31
  wandb/run-20220326_171130-bdf5nvyg/run-bdf5nvyg.wandb filter=lfs diff=lfs merge=lfs -text
32
  wandb/run-20220326_171130-bdf5nvyg/logs/debug-internal.log filter=lfs diff=lfs merge=lfs -text
 
 
30
  wandb/run-20220325_193848-1sz5964i/run-1sz5964i.wandb filter=lfs diff=lfs merge=lfs -text
31
  wandb/run-20220326_171130-bdf5nvyg/run-bdf5nvyg.wandb filter=lfs diff=lfs merge=lfs -text
32
  wandb/run-20220326_171130-bdf5nvyg/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
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ddaa26f887e29edc2c64015855a5fb38106c12ec0be59f5429df3474a159feb1
3
  size 2353901617
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77a381f0c47b893843988d9fc66a16094b50bfcd37bfc391ef847db3f7d7d32d
3
  size 2353901617
run_librispeech.sh CHANGED
@@ -15,7 +15,7 @@ CUDA_VISIBLE_DEVICES=1 python run_speech_recognition_seq2seq.py \
15
  --gradient_accumulation_steps="16" \
16
  --generation_max_length="40" \
17
  --generation_num_beams="1" \
18
- --learning_rate="3e-4" \
19
  --warmup_steps="500" \
20
  --evaluation_strategy="steps" \
21
  --text_column_name="text" \
15
  --gradient_accumulation_steps="16" \
16
  --generation_max_length="40" \
17
  --generation_num_beams="1" \
18
+ --learning_rate="3e-5" \
19
  --warmup_steps="500" \
20
  --evaluation_strategy="steps" \
21
  --text_column_name="text" \
runs/Mar27_19-47-24_sanchit--v100/1648410471.8274474/events.out.tfevents.1648410471.sanchit--v100.3630555.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6160d9d1c49077f5deac1fc1ec271e5ddfb817b2afb19cffc12c4969e3288f5f
3
+ size 4973
runs/Mar27_19-47-24_sanchit--v100/events.out.tfevents.1648410471.sanchit--v100.3630555.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef647ac2992901f563a647717c4c098053a5da7135fbf4c90932212da877b26a
3
+ size 39547
runs/Mar27_21-02-01_sanchit--v100/1648414949.4091816/events.out.tfevents.1648414949.sanchit--v100.3678730.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13ee4930dc4ec202396be7ddf035b7b953563b1c487b7b69bd83952c9943fbf0
3
+ size 4973
runs/Mar27_21-02-01_sanchit--v100/events.out.tfevents.1648414949.sanchit--v100.3678730.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b40e1d7d88f0cefa879e164acf12eda24622bce323f3756edbc9872f026c9310
3
+ size 87907
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:373a971610037857c0c2fecfa1530d1f657b799234ceaf5ef4178168edce4e5b
3
  size 3119
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0947a271bdbd47be3b989768a5de1a09693c6228f10aae3ebef93f0a800fda6d
3
  size 3119
wandb/debug-internal.log CHANGED
@@ -1 +1 @@
1
- run-20220326_171130-bdf5nvyg/logs/debug-internal.log
1
+ run-20220327_210229-2wif55w7/logs/debug-internal.log
wandb/debug.log CHANGED
@@ -1 +1 @@
1
- run-20220326_171130-bdf5nvyg/logs/debug.log
1
+ run-20220327_210229-2wif55w7/logs/debug.log
wandb/latest-run CHANGED
@@ -1 +1 @@
1
- run-20220326_171130-bdf5nvyg
1
+ run-20220327_210229-2wif55w7
wandb/run-20220326_171130-bdf5nvyg/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-20220326_171130-bdf5nvyg/files/output.log CHANGED
@@ -27765,3 +27765,20 @@ Upload file wandb/run-20220326_171130-bdf5nvyg/run-bdf5nvyg.wandb: 100%|██
27765
  eval_steps_per_second = 0.458
27766
  eval_wer = 0.0932
27767
  [INFO|trainer.py:2366] 2022-03-27 07:38:54,563 >> Num examples = 2642|█████████████| 434M/434M [00:25<00:00, 18.1MB/s]ields:t operations will not be computed-27 07:27:04,529 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
27765
  eval_steps_per_second = 0.458
27766
  eval_wer = 0.0932
27767
  [INFO|trainer.py:2366] 2022-03-27 07:38:54,563 >> Num examples = 2642|█████████████| 434M/434M [00:25<00:00, 18.1MB/s]ields:t operations will not be computed-27 07:27:04,529 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
27768
+ [INFO|trainer.py:2366] 2022-03-27 07:38:54,563 >> Num examples = 2642|█████████████| 434M/434M [00:25<00:00, 18.1MB/s]ields:t operations will not be computed-27 07:27:04,529 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
27769
+ [INFO|trainer.py:2366] 2022-03-27 07:38:54,563 >> Num examples = 2642|█████████████| 434M/434M [00:25<00:00, 18.1MB/s]ields:t operations will not be computed-27 07:27:04,529 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
27770
+ [INFO|trainer.py:2366] 2022-03-27 07:38:54,563 >> Num examples = 2642|█████████████| 434M/434M [00:25<00:00, 18.1MB/s]ields:t operations will not be computed-27 07:27:04,529 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
27771
+ [INFO|trainer.py:2366] 2022-03-27 07:38:54,563 >> Num examples = 2642|█████████████| 434M/434M [00:25<00:00, 18.1MB/s]ields:t operations will not be computed-27 07:27:04,529 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
27772
+ [INFO|trainer.py:2366] 2022-03-27 07:38:54,563 >> Num examples = 2642|█████████████| 434M/434M [00:25<00:00, 18.1MB/s]ields:t operations will not be computed-27 07:27:04,529 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
27773
+ [INFO|trainer.py:2366] 2022-03-27 07:38:54,563 >> Num examples = 2642|█████████████| 434M/434M [00:25<00:00, 18.1MB/s]ields:t operations will not be computed-27 07:27:04,529 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
27774
+ [INFO|trainer.py:2366] 2022-03-27 07:38:54,563 >> Num examples = 2642|█████████████| 434M/434M [00:25<00:00, 18.1MB/s]ields:t operations will not be computed-27 07:27:04,529 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
27775
+ [INFO|trainer.py:2366] 2022-03-27 07:38:54,563 >> Num examples = 2642|█████████████| 434M/434M [00:25<00:00, 18.1MB/s]ields:t operations will not be computed-27 07:27:04,529 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
27776
+ [INFO|trainer.py:2366] 2022-03-27 07:38:54,563 >> Num examples = 2642|█████████████| 434M/434M [00:25<00:00, 18.1MB/s]ields:t operations will not be computed-27 07:27:04,529 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
27777
+ [INFO|trainer.py:2366] 2022-03-27 07:38:54,563 >> Num examples = 2642|█████████████| 434M/434M [00:25<00:00, 18.1MB/s]ields:t operations will not be computed-27 07:27:04,529 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
27778
+ [INFO|trainer.py:2366] 2022-03-27 07:38:54,563 >> Num examples = 2642|█████████████| 434M/434M [00:25<00:00, 18.1MB/s]ields:t operations will not be computed-27 07:27:04,529 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
27779
+ [INFO|trainer.py:2366] 2022-03-27 07:38:54,563 >> Num examples = 2642|█████████████| 434M/434M [00:25<00:00, 18.1MB/s]ields:t operations will not be computed-27 07:27:04,529 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
27780
+ 03/27/2022 07:51:54 - WARNING - huggingface_hub.repository - To https://huggingface.co/sanchit-gandhi/wav2vec2-2-bart-large-cnn
27781
+ Upload file runs/Mar26_17-11-01_sanchit--v100/events.out.tfevents.1648367457.sanchit--v100.2600125.2: 100%|█| 358/358 [0ields:t operations will not be computed-27 07:27:04,529 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
27782
+ 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-27 07:27:04,529 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
27783
+ 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-27 07:27:04,529 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
27784
+ 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-27 07:27:04,529 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...
wandb/run-20220326_171130-bdf5nvyg/files/wandb-summary.json CHANGED
The diff for this file is too large to render. See raw diff
wandb/run-20220326_171130-bdf5nvyg/logs/debug-internal.log CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9390843eb9e29cbff8081fd9c955aa5e548c4aadf12a40b738c2dccf6b263b4
3
- size 11827180
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a603cc76fb8ccdc56150cd3878113b89b22c07d0b4ec2e46932e497828729492
3
+ size 11849093
wandb/run-20220326_171130-bdf5nvyg/logs/debug.log CHANGED
@@ -25,3 +25,293 @@ config: {}
25
  2022-03-26 17:11:32,041 INFO MainThread:2600125 [wandb_init.py:init():651] run started, returning control to user process
26
  2022-03-26 17:11:32,045 INFO MainThread:2600125 [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/Mar26_17-11-01_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
  2022-03-26 17:11:32,049 INFO MainThread:2600125 [wandb_watch.py:watch():43] Watching
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25
  2022-03-26 17:11:32,041 INFO MainThread:2600125 [wandb_init.py:init():651] run started, returning control to user process
26
  2022-03-26 17:11:32,045 INFO MainThread:2600125 [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/Mar26_17-11-01_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
  2022-03-26 17:11:32,049 INFO MainThread:2600125 [wandb_watch.py:watch():43] Watching
28
+ 2022-03-27 07:51:59,061 INFO MainThread:2600125 [wandb_run.py:_atexit_cleanup():1797] got exitcode: 1
29
+ 2022-03-27 07:51:59,064 INFO MainThread:2600125 [wandb_run.py:_restore():1769] restore
30
+ 2022-03-27 07:52:01,626 INFO MainThread:2600125 [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
+ 2022-03-27 07:52:01,793 INFO MainThread:2600125 [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
+ 2022-03-27 07:52:02,482 INFO MainThread:2600125 [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
+ 2022-03-27 07:52:02,721 INFO MainThread:2600125 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
55
+ wandb_count: 5
56
+ }
57
+ pusher_stats {
58
+ uploaded_bytes: 2017
59
+ total_bytes: 9450687
60
+ }
61
+
62
+ 2022-03-27 07:52:02,823 INFO MainThread:2600125 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
63
+ wandb_count: 5
64
+ }
65
+ pusher_stats {
66
+ uploaded_bytes: 1307153
67
+ total_bytes: 9450687
68
+ }
69
+
70
+ 2022-03-27 07:52:02,925 INFO MainThread:2600125 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
71
+ wandb_count: 5
72
+ }
73
+ pusher_stats {
74
+ uploaded_bytes: 9450687
75
+ total_bytes: 9450687
76
+ }
77
+
78
+ 2022-03-27 07:52:03,027 INFO MainThread:2600125 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
79
+ wandb_count: 5
80
+ }
81
+ pusher_stats {
82
+ uploaded_bytes: 9450687
83
+ total_bytes: 9450687
84
+ }
85
+
86
+ 2022-03-27 07:52:03,129 INFO MainThread:2600125 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
87
+ wandb_count: 5
88
+ }
89
+ pusher_stats {
90
+ uploaded_bytes: 9450687
91
+ total_bytes: 9450687
92
+ }
93
+
94
+ 2022-03-27 07:52:03,231 INFO MainThread:2600125 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
95
+ wandb_count: 5
96
+ }
97
+ pusher_stats {
98
+ uploaded_bytes: 9450687
99
+ total_bytes: 9450687
100
+ }
101
+
102
+ 2022-03-27 07:52:03,333 INFO MainThread:2600125 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
103
+ wandb_count: 5
104
+ }
105
+ pusher_stats {
106
+ uploaded_bytes: 9450687
107
+ total_bytes: 9450687
108
+ }
109
+
110
+ 2022-03-27 07:52:03,435 INFO MainThread:2600125 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
111
+ wandb_count: 5
112
+ }
113
+ pusher_stats {
114
+ uploaded_bytes: 9450687
115
+ total_bytes: 9450687
116
+ }
117
+
118
+ 2022-03-27 07:52:03,537 INFO MainThread:2600125 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
119
+ wandb_count: 5
120
+ }
121
+ pusher_stats {
122
+ uploaded_bytes: 9450687
123
+ total_bytes: 9450687
124
+ }
125
+
126
+ 2022-03-27 07:52:03,639 INFO MainThread:2600125 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
127
+ wandb_count: 5
128
+ }
129
+ pusher_stats {
130
+ uploaded_bytes: 9450687
131
+ total_bytes: 9450687
132
+ }
133
+
134
+ 2022-03-27 07:52:03,741 INFO MainThread:2600125 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
135
+ wandb_count: 5
136
+ }
137
+ pusher_stats {
138
+ uploaded_bytes: 9450687
139
+ total_bytes: 9450687
140
+ }
141
+
142
+ 2022-03-27 07:52:03,843 INFO MainThread:2600125 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
143
+ wandb_count: 5
144
+ }
145
+ pusher_stats {
146
+ uploaded_bytes: 9450687
147
+ total_bytes: 9450687
148
+ }
149
+
150
+ 2022-03-27 07:52:03,945 INFO MainThread:2600125 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
151
+ wandb_count: 5
152
+ }
153
+ pusher_stats {
154
+ uploaded_bytes: 9450687
155
+ total_bytes: 9450687
156
+ }
157
+
158
+ 2022-03-27 07:52:04,048 INFO MainThread:2600125 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
159
+ wandb_count: 5
160
+ }
161
+ pusher_stats {
162
+ uploaded_bytes: 9450687
163
+ total_bytes: 9450687
164
+ }
165
+
166
+ 2022-03-27 07:52:04,149 INFO MainThread:2600125 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
167
+ wandb_count: 5
168
+ }
169
+ pusher_stats {
170
+ uploaded_bytes: 9450687
171
+ total_bytes: 9450687
172
+ }
173
+
174
+ 2022-03-27 07:52:04,252 INFO MainThread:2600125 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
175
+ wandb_count: 5
176
+ }
177
+ pusher_stats {
178
+ uploaded_bytes: 9450687
179
+ total_bytes: 9450687
180
+ }
181
+
182
+ 2022-03-27 07:52:04,353 INFO MainThread:2600125 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
183
+ wandb_count: 5
184
+ }
185
+ pusher_stats {
186
+ uploaded_bytes: 9450687
187
+ total_bytes: 9450687
188
+ }
189
+
190
+ 2022-03-27 07:52:04,456 INFO MainThread:2600125 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
191
+ wandb_count: 5
192
+ }
193
+ pusher_stats {
194
+ uploaded_bytes: 9450687
195
+ total_bytes: 9450687
196
+ }
197
+
198
+ 2022-03-27 07:52:04,558 INFO MainThread:2600125 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
199
+ wandb_count: 5
200
+ }
201
+ pusher_stats {
202
+ uploaded_bytes: 9450687
203
+ total_bytes: 9450687
204
+ }
205
+
206
+ 2022-03-27 07:52:04,660 INFO MainThread:2600125 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
207
+ wandb_count: 5
208
+ }
209
+ pusher_stats {
210
+ uploaded_bytes: 9450687
211
+ total_bytes: 9450687
212
+ }
213
+
214
+ 2022-03-27 07:52:04,762 INFO MainThread:2600125 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
215
+ wandb_count: 5
216
+ }
217
+ pusher_stats {
218
+ uploaded_bytes: 9450687
219
+ total_bytes: 9450687
220
+ }
221
+
222
+ 2022-03-27 07:52:04,865 INFO MainThread:2600125 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
223
+ wandb_count: 5
224
+ }
225
+ pusher_stats {
226
+ uploaded_bytes: 9450687
227
+ total_bytes: 9450687
228
+ }
229
+
230
+ 2022-03-27 07:52:04,967 INFO MainThread:2600125 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
231
+ wandb_count: 5
232
+ }
233
+ pusher_stats {
234
+ uploaded_bytes: 9450687
235
+ total_bytes: 9450687
236
+ }
237
+
238
+ 2022-03-27 07:52:05,069 INFO MainThread:2600125 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
239
+ wandb_count: 5
240
+ }
241
+ pusher_stats {
242
+ uploaded_bytes: 9450687
243
+ total_bytes: 9450687
244
+ }
245
+
246
+ 2022-03-27 07:52:05,171 INFO MainThread:2600125 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
247
+ wandb_count: 5
248
+ }
249
+ pusher_stats {
250
+ uploaded_bytes: 9450687
251
+ total_bytes: 9450687
252
+ }
253
+
254
+ 2022-03-27 07:52:05,274 INFO MainThread:2600125 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
255
+ wandb_count: 5
256
+ }
257
+ pusher_stats {
258
+ uploaded_bytes: 9450687
259
+ total_bytes: 9450687
260
+ }
261
+
262
+ 2022-03-27 07:52:05,376 INFO MainThread:2600125 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
263
+ wandb_count: 5
264
+ }
265
+ pusher_stats {
266
+ uploaded_bytes: 9450687
267
+ total_bytes: 9450687
268
+ }
269
+
270
+ 2022-03-27 07:52:05,478 INFO MainThread:2600125 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
271
+ wandb_count: 5
272
+ }
273
+ pusher_stats {
274
+ uploaded_bytes: 9450687
275
+ total_bytes: 9450687
276
+ }
277
+
278
+ 2022-03-27 07:52:05,580 INFO MainThread:2600125 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
279
+ wandb_count: 5
280
+ }
281
+ pusher_stats {
282
+ uploaded_bytes: 9450687
283
+ total_bytes: 9450687
284
+ }
285
+
286
+ 2022-03-27 07:52:05,683 INFO MainThread:2600125 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
287
+ wandb_count: 5
288
+ }
289
+ pusher_stats {
290
+ uploaded_bytes: 9450687
291
+ total_bytes: 9450687
292
+ }
293
+
294
+ 2022-03-27 07:52:06,234 INFO MainThread:2600125 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
295
+ wandb_count: 5
296
+ }
297
+ pusher_stats {
298
+ uploaded_bytes: 9450687
299
+ total_bytes: 9450687
300
+ }
301
+
302
+ 2022-03-27 07:52:06,458 INFO MainThread:2600125 [wandb_run.py:_wait_for_finish():1929] got exit ret: done: true
303
+ exit_result {
304
+ }
305
+ file_counts {
306
+ wandb_count: 5
307
+ }
308
+ pusher_stats {
309
+ uploaded_bytes: 9450687
310
+ total_bytes: 9450687
311
+ }
312
+ local_info {
313
+ }
314
+
315
+ 2022-03-27 07:52:07,690 INFO MainThread:2600125 [wandb_run.py:_append_history():2144] rendering history
316
+ 2022-03-27 07:52:07,691 INFO MainThread:2600125 [wandb_run.py:_append_summary():2102] rendering summary
317
+ 2022-03-27 07:52:07,692 INFO MainThread:2600125 [wandb_run.py:_append_files():2194] logging synced files
wandb/run-20220326_171130-bdf5nvyg/run-bdf5nvyg.wandb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07b8089a65e54817bb1f82c0125e890f0820c2f064b6baa83ff71388e0349784
3
- size 455282886
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48d341aaff4f893a4bef5a07545d91b8c5d62f99821d32541d200cc020652c58
3
+ size 456607881
wandb/run-20220327_194752-3s89mmo1/files/config.yaml ADDED
The diff for this file is too large to render. See raw diff
wandb/run-20220327_194752-3s89mmo1/files/output.log ADDED
The diff for this file is too large to render. See raw diff
wandb/run-20220327_194752-3s89mmo1/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-20220327_194752-3s89mmo1/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": "2022-03-27T19:47:53.602699",
5
+ "startedAt": "2022-03-27T19:47:52.168793",
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": "0e7d81d852f0471f3c394766af5606f0999f6a68"
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-20220327_194752-3s89mmo1/files/wandb-summary.json ADDED
The diff for this file is too large to render. See raw diff
wandb/run-20220327_194752-3s89mmo1/logs/debug-internal.log ADDED
The diff for this file is too large to render. See raw diff
wandb/run-20220327_194752-3s89mmo1/logs/debug.log ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2022-03-27 19:47:52,172 INFO MainThread:3630555 [wandb_setup.py:_flush():75] Loading settings from /home/sanchit_huggingface_co/.config/wandb/settings
2
+ 2022-03-27 19:47:52,172 INFO MainThread:3630555 [wandb_setup.py:_flush():75] Loading settings from /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/settings
3
+ 2022-03-27 19:47:52,172 INFO MainThread:3630555 [wandb_setup.py:_flush():75] Loading settings from environment variables: {}
4
+ 2022-03-27 19:47:52,172 INFO MainThread:3630555 [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
+ 2022-03-27 19:47:52,172 INFO MainThread:3630555 [wandb_init.py:_log_setup():386] Logging user logs to /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220327_194752-3s89mmo1/logs/debug.log
6
+ 2022-03-27 19:47:52,173 INFO MainThread:3630555 [wandb_init.py:_log_setup():387] Logging internal logs to /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220327_194752-3s89mmo1/logs/debug-internal.log
7
+ 2022-03-27 19:47:52,173 INFO MainThread:3630555 [wandb_init.py:init():420] calling init triggers
8
+ 2022-03-27 19:47:52,173 INFO MainThread:3630555 [wandb_init.py:init():425] wandb.init called with sweep_config: {}
9
+ config: {}
10
+ 2022-03-27 19:47:52,173 INFO MainThread:3630555 [wandb_init.py:init():471] starting backend
11
+ 2022-03-27 19:47:52,173 INFO MainThread:3630555 [backend.py:_multiprocessing_setup():99] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
12
+ 2022-03-27 19:47:52,228 INFO MainThread:3630555 [backend.py:ensure_launched():219] starting backend process...
13
+ 2022-03-27 19:47:52,282 INFO MainThread:3630555 [backend.py:ensure_launched():224] started backend process with pid: 3631076
14
+ 2022-03-27 19:47:52,284 INFO MainThread:3630555 [wandb_init.py:init():480] backend started and connected
15
+ 2022-03-27 19:47:52,295 INFO MainThread:3630555 [wandb_init.py:init():550] updated telemetry
16
+ 2022-03-27 19:47:52,423 INFO MainThread:3630555 [wandb_init.py:init():581] communicating current version
17
+ 2022-03-27 19:47:53,151 INFO MainThread:3630555 [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
+ 2022-03-27 19:47:53,151 INFO MainThread:3630555 [wandb_init.py:init():596] communicating run to backend with 30 second timeout
20
+ 2022-03-27 19:47:53,597 INFO MainThread:3630555 [wandb_init.py:init():624] starting run threads in backend
21
+ 2022-03-27 19:47:53,701 INFO MainThread:3630555 [wandb_run.py:_console_start():1827] atexit reg
22
+ 2022-03-27 19:47:53,702 INFO MainThread:3630555 [wandb_run.py:_redirect():1701] redirect: SettingsConsole.REDIRECT
23
+ 2022-03-27 19:47:53,702 INFO MainThread:3630555 [wandb_run.py:_redirect():1706] Redirecting console.
24
+ 2022-03-27 19:47:53,704 INFO MainThread:3630555 [wandb_run.py:_redirect():1762] Redirects installed.
25
+ 2022-03-27 19:47:53,704 INFO MainThread:3630555 [wandb_init.py:init():651] run started, returning control to user process
26
+ 2022-03-27 19:47:53,706 INFO MainThread:3630555 [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_19-47-24_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 19:47:53,709 INFO MainThread:3630555 [wandb_watch.py:watch():43] Watching
28
+ 2022-03-27 21:00:56,294 INFO MainThread:3630555 [wandb_run.py:_atexit_cleanup():1797] got exitcode: 255
29
+ 2022-03-27 21:00:56,295 INFO MainThread:3630555 [wandb_run.py:_restore():1769] restore
wandb/run-20220327_194752-3s89mmo1/run-3s89mmo1.wandb ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e1fccbcbfc0696d0b8046a50b297fc90d8e8fa3849e7c8871c4b3c4348a6a8a
3
+ size 39129334
wandb/run-20220327_210229-2wif55w7/files/config.yaml ADDED
The diff for this file is too large to render. See raw diff
wandb/run-20220327_210229-2wif55w7/files/output.log ADDED
The diff for this file is too large to render. See raw diff
wandb/run-20220327_210229-2wif55w7/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-20220327_210229-2wif55w7/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": "2022-03-27T21:02:30.824313",
5
+ "startedAt": "2022-03-27T21:02:29.735384",
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": "0e7d81d852f0471f3c394766af5606f0999f6a68"
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-20220327_210229-2wif55w7/files/wandb-summary.json ADDED
The diff for this file is too large to render. See raw diff
wandb/run-20220327_210229-2wif55w7/logs/debug-internal.log ADDED
The diff for this file is too large to render. See raw diff
wandb/run-20220327_210229-2wif55w7/logs/debug.log ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2022-03-27 21:02:29,737 INFO MainThread:3678730 [wandb_setup.py:_flush():75] Loading settings from /home/sanchit_huggingface_co/.config/wandb/settings
2
+ 2022-03-27 21:02:29,737 INFO MainThread:3678730 [wandb_setup.py:_flush():75] Loading settings from /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/settings
3
+ 2022-03-27 21:02:29,737 INFO MainThread:3678730 [wandb_setup.py:_flush():75] Loading settings from environment variables: {}
4
+ 2022-03-27 21:02:29,737 INFO MainThread:3678730 [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
+ 2022-03-27 21:02:29,737 INFO MainThread:3678730 [wandb_init.py:_log_setup():386] Logging user logs to /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220327_210229-2wif55w7/logs/debug.log
6
+ 2022-03-27 21:02:29,737 INFO MainThread:3678730 [wandb_init.py:_log_setup():387] Logging internal logs to /home/sanchit_huggingface_co/wav2vec2-2-bart-large-cnn/wandb/run-20220327_210229-2wif55w7/logs/debug-internal.log
7
+ 2022-03-27 21:02:29,737 INFO MainThread:3678730 [wandb_init.py:init():420] calling init triggers
8
+ 2022-03-27 21:02:29,737 INFO MainThread:3678730 [wandb_init.py:init():425] wandb.init called with sweep_config: {}
9
+ config: {}
10
+ 2022-03-27 21:02:29,737 INFO MainThread:3678730 [wandb_init.py:init():471] starting backend
11
+ 2022-03-27 21:02:29,737 INFO MainThread:3678730 [backend.py:_multiprocessing_setup():99] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
12
+ 2022-03-27 21:02:29,793 INFO MainThread:3678730 [backend.py:ensure_launched():219] starting backend process...
13
+ 2022-03-27 21:02:29,848 INFO MainThread:3678730 [backend.py:ensure_launched():224] started backend process with pid: 3679204
14
+ 2022-03-27 21:02:29,850 INFO MainThread:3678730 [wandb_init.py:init():480] backend started and connected
15
+ 2022-03-27 21:02:29,860 INFO MainThread:3678730 [wandb_init.py:init():550] updated telemetry
16
+ 2022-03-27 21:02:29,991 INFO MainThread:3678730 [wandb_init.py:init():581] communicating current version
17
+ 2022-03-27 21:02:30,705 INFO MainThread:3678730 [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
+ 2022-03-27 21:02:30,705 INFO MainThread:3678730 [wandb_init.py:init():596] communicating run to backend with 30 second timeout
20
+ 2022-03-27 21:02:30,819 INFO MainThread:3678730 [wandb_init.py:init():624] starting run threads in backend
21
+ 2022-03-27 21:02:30,920 INFO MainThread:3678730 [wandb_run.py:_console_start():1827] atexit reg
22
+ 2022-03-27 21:02:30,921 INFO MainThread:3678730 [wandb_run.py:_redirect():1701] redirect: SettingsConsole.REDIRECT
23
+ 2022-03-27 21:02:30,921 INFO MainThread:3678730 [wandb_run.py:_redirect():1706] Redirecting console.
24
+ 2022-03-27 21:02:30,923 INFO MainThread:3678730 [wandb_run.py:_redirect():1762] Redirects installed.
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
wandb/run-20220327_210229-2wif55w7/run-2wif55w7.wandb ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b1103ad43563867cb478c1d4484ca6b77916673005be667be03d54ba7d180f5
3
+ size 102138274