up

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7285b3dc9e5948807a019ca6ef6f0e6906b7ee5f5df7b54f5b4d3edb5fc9295e
-size 3087090488
+oid sha256:e4037918156ace2010dc63b440c1cb40eb20519d3e00db942e461310b69141da
+size 1962672704

run_librispeech.sh

@@ -8,15 +8,14 @@ CUDA_VISIBLE_DEVICES=1 python run_speech_recognition_seq2seq.py \
 	--output_dir="./" \
 	--preprocessing_num_workers="1" \
 	--length_column_name="input_length" \
-	--overwrite_output_dir \
-	--num_train_epochs="20" \
+	--num_train_epochs="10" \
 	--per_device_train_batch_size="8" \
 	--per_device_eval_batch_size="8" \
 	--gradient_accumulation_steps="4" \
 	--generation_max_length="40" \
 	--generation_num_beams="1" \
-	--learning_rate="1e-5" \
-	--warmup_steps="1500" \
+	--learning_rate="5e-6" \
+	--warmup_steps="1" \
 	--evaluation_strategy="steps" \
 	--text_column_name="text" \
 	--save_steps="1500" \

runs/Mar22_09-43-31_sanchit--v100/1647942245.8723397/events.out.tfevents.1647942245.sanchit--v100.28799.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:023b1f94c7c83692f32b524cdc0564feb6575075993a352d49245633f5cb4168
+size 4973

runs/Mar22_09-43-31_sanchit--v100/events.out.tfevents.1647942245.sanchit--v100.28799.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79f4906479e41c9fb04dbdb15fc16f65c273445968e0703b4fab67b92a13ea8e
+size 9217

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f4f5cc9e51e1021b8fa699625bf6dc9ded0122f755ddc86c59d92bc08aa6cb2
+oid sha256:06fa7821d09961cd241516145a69a71e9038d56760a9b05e9a4d5fdc9fb6abab
 size 3119

wandb/debug-internal.log

@@ -1 +1 @@
-run-20220320_205317-13fe1w7o/logs/debug-internal.log
+run-20220322_094406-dk50d3c6/logs/debug-internal.log

wandb/debug.log

@@ -1 +1 @@
-run-20220320_205317-13fe1w7o/logs/debug.log
+run-20220322_094406-dk50d3c6/logs/debug.log

wandb/latest-run

@@ -1 +1 @@
-run-20220320_205317-13fe1w7o
+run-20220322_094406-dk50d3c6

wandb/run-20220320_205317-13fe1w7o/files/config.yaml

@@ -12413,7 +12413,14 @@ _wandb:
       - 1
       - 5
       - 11
+      2:
+      - 1
+      - 5
+      - 11
+      - 12
       3:
+      - 1
+      - 7
       - 13
       4: 3.9.5
       5: 0.12.10

wandb/run-20220320_205317-13fe1w7o/files/output.log

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93a9ddb32faa240a1e6f127d25e88d0496a2acdb3094c299d4fb2348af9c9841
-size 20837744
+oid sha256:90f71bb80f11890b0cac5a2c47081e4f0b3447789beb433a9324208591c8e4ca
+size 20866534

wandb/run-20220320_205317-13fe1w7o/logs/debug-internal.log

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cca7294a398a9f7f78639dd2a70d5d67944266d2d5d636c94f57b97c8d194ab
-size 28887039
+oid sha256:ddfabea5070e4f931f8429c56cb5099ea467d239d7be5806ab49646bf1bd14d3
+size 28923693

wandb/run-20220320_205317-13fe1w7o/logs/debug.log

@@ -25,3 +25,109 @@ config: {}
 2022-03-20 20:53:18,789 INFO    MainThread:15700 [wandb_init.py:init():651] run started, returning control to user process
 2022-03-20 20:53:18,792 INFO    MainThread:15700 [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': 50, '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': ['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': {'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': 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': ['RobertaForMaskedLM'], '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': 0, 'pad_token_id': 1, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'roberta-large', 'transformers_version': '4.17.0.dev0', 'vocab_size': 50265, 'hidden_size': 1024, 'num_hidden_layers': 24, 'num_attention_heads': 16, 'hidden_act': 'gelu', 'intermediate_size': 4096, 'hidden_dropout_prob': 0.1, 'attention_probs_dropout_prob': 0.1, 'max_position_embeddings': 514, 'type_vocab_size': 1, 'initializer_range': 0.02, 'layer_norm_eps': 1e-05, 'position_embedding_type': 'absolute', 'use_cache': False, 'classifier_dropout': None, 'model_type': 'roberta'}, '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': False, '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': 4, 'eval_accumulation_steps': 'None', 'learning_rate': 1e-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': 20.0, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'warmup_ratio': 0.0, 'warmup_steps': 1500, 'log_level': -1, 'log_level_replica': -1, 'log_on_each_node': True, 'logging_dir': './runs/Mar20_20-52-47_sanchit--v100', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 1, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 1500, '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': 1500, '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}
 2022-03-20 20:53:18,795 INFO    MainThread:15700 [wandb_watch.py:watch():43] Watching
+2022-03-22 05:40:34,532 INFO    MainThread:15700 [wandb_run.py:_atexit_cleanup():1797] got exitcode: 1
+2022-03-22 05:40:34,536 INFO    MainThread:15700 [wandb_run.py:_restore():1769] restore
+2022-03-22 05:40:37,094 INFO    MainThread:15700 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
+  wandb_count: 1
+}
+pusher_stats {
+  uploaded_bytes: 2076
+  total_bytes: 2076
+}
+
+2022-03-22 05:40:37,296 INFO    MainThread:15700 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
+  wandb_count: 1
+}
+pusher_stats {
+  uploaded_bytes: 2076
+  total_bytes: 2076
+}
+
+2022-03-22 05:40:38,187 INFO    MainThread:15700 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
+  wandb_count: 1
+}
+pusher_stats {
+  uploaded_bytes: 2076
+  total_bytes: 2076
+}
+
+2022-03-22 05:40:38,289 INFO    MainThread:15700 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 2076
+  total_bytes: 22860023
+}
+
+2022-03-22 05:40:38,391 INFO    MainThread:15700 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 11528977
+  total_bytes: 22860023
+}
+
+2022-03-22 05:40:38,493 INFO    MainThread:15700 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 22833937
+  total_bytes: 22860023
+}
+
+2022-03-22 05:40:38,594 INFO    MainThread:15700 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 22860023
+  total_bytes: 22860023
+}
+
+2022-03-22 05:40:38,696 INFO    MainThread:15700 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 22860023
+  total_bytes: 22860023
+}
+
+2022-03-22 05:40:38,798 INFO    MainThread:15700 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 22860023
+  total_bytes: 22860023
+}
+
+2022-03-22 05:40:38,899 INFO    MainThread:15700 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 22860023
+  total_bytes: 22860023
+}
+
+2022-03-22 05:40:39,563 INFO    MainThread:15700 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 22860023
+  total_bytes: 22860023
+}
+
+2022-03-22 05:40:39,715 INFO    MainThread:15700 [wandb_run.py:_wait_for_finish():1929] got exit ret: done: true
+exit_result {
+}
+file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 22860023
+  total_bytes: 22860023
+}
+local_info {
+}
+
+2022-03-22 05:40:40,864 INFO    MainThread:15700 [wandb_run.py:_append_history():2144] rendering history
+2022-03-22 05:40:40,865 INFO    MainThread:15700 [wandb_run.py:_append_summary():2102] rendering summary
+2022-03-22 05:40:40,866 INFO    MainThread:15700 [wandb_run.py:_append_files():2194] logging synced files

wandb/run-20220320_205317-13fe1w7o/run-13fe1w7o.wandb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc584fa32866581aa312e0bb5e6f8da16bbf6729330af258ee64c4e32f6ebc37
-size 1258830711
+oid sha256:70198de64e8f4ae8e6e98d3ef1b9b43d7cfd935da1c4fe60e44dc500fd014f1f
+size 1260506629

wandb/run-20220322_094406-dk50d3c6/files/config.yaml

@@ -0,0 +1,719 @@
+wandb_version: 1
+
+_n_gpu:
+  desc: null
+  value: 1
+_name_or_path:
+  desc: null
+  value: ./
+_wandb:
+  desc: null
+  value:
+    cli_version: 0.12.10
+    framework: huggingface
+    huggingface_version: 4.17.0.dev0
+    is_jupyter_run: false
+    is_kaggle_kernel: false
+    m:
+    - 1: train/global_step
+      6:
+      - 3
+    - 1: train/train_runtime
+      5: 1
+      6:
+      - 1
+    - 1: train/train_samples_per_second
+      5: 1
+      6:
+      - 1
+    - 1: train/train_steps_per_second
+      5: 1
+      6:
+      - 1
+    - 1: train/total_flos
+      5: 1
+      6:
+      - 1
+    - 1: train/train_loss
+      5: 1
+      6:
+      - 1
+    - 1: train/epoch
+      5: 1
+      6:
+      - 1
+    python_version: 3.9.5
+    start_time: 1647942246
+    t:
+      1:
+      - 1
+      - 5
+      - 11
+      3:
+      - 13
+      4: 3.9.5
+      5: 0.12.10
+      6: 4.17.0.dev0
+      8:
+      - 5
+adafactor:
+  desc: null
+  value: false
+adam_beta1:
+  desc: null
+  value: 0.9
+adam_beta2:
+  desc: null
+  value: 0.999
+adam_epsilon:
+  desc: null
+  value: 1.0e-08
+add_cross_attention:
+  desc: null
+  value: false
+architectures:
+  desc: null
+  value:
+  - SpeechEncoderDecoderModel
+bad_words_ids:
+  desc: null
+  value: null
+bf16:
+  desc: null
+  value: false
+bf16_full_eval:
+  desc: null
+  value: false
+bos_token_id:
+  desc: null
+  value: null
+chunk_size_feed_forward:
+  desc: null
+  value: 0
+cross_attention_hidden_size:
+  desc: null
+  value: null
+dataloader_drop_last:
+  desc: null
+  value: false
+dataloader_num_workers:
+  desc: null
+  value: 0
+dataloader_pin_memory:
+  desc: null
+  value: true
+ddp_bucket_cap_mb:
+  desc: null
+  value: None
+ddp_find_unused_parameters:
+  desc: null
+  value: None
+debug:
+  desc: null
+  value: '[]'
+decoder:
+  desc: null
+  value:
+    _name_or_path: roberta-large
+    add_cross_attention: true
+    architectures:
+    - RobertaForMaskedLM
+    attention_probs_dropout_prob: 0.1
+    bad_words_ids: null
+    bos_token_id: 0
+    chunk_size_feed_forward: 0
+    classifier_dropout: null
+    cross_attention_hidden_size: null
+    decoder_start_token_id: null
+    diversity_penalty: 0.0
+    do_sample: false
+    early_stopping: false
+    encoder_no_repeat_ngram_size: 0
+    eos_token_id: 2
+    finetuning_task: null
+    forced_bos_token_id: null
+    forced_eos_token_id: null
+    hidden_act: gelu
+    hidden_dropout_prob: 0.1
+    hidden_size: 1024
+    id2label:
+      '0': LABEL_0
+      '1': LABEL_1
+    initializer_range: 0.02
+    intermediate_size: 4096
+    is_decoder: true
+    is_encoder_decoder: false
+    label2id:
+      LABEL_0: 0
+      LABEL_1: 1
+    layer_norm_eps: 1.0e-05
+    length_penalty: 1.0
+    max_length: 20
+    max_position_embeddings: 514
+    min_length: 0
+    model_type: roberta
+    no_repeat_ngram_size: 0
+    num_attention_heads: 16
+    num_beam_groups: 1
+    num_beams: 1
+    num_hidden_layers: 24
+    num_return_sequences: 1
+    output_attentions: false
+    output_hidden_states: false
+    output_scores: false
+    pad_token_id: 1
+    position_embedding_type: absolute
+    prefix: null
+    problem_type: null
+    pruned_heads: {}
+    remove_invalid_values: false
+    repetition_penalty: 1.0
+    return_dict: true
+    return_dict_in_generate: false
+    sep_token_id: null
+    task_specific_params: null
+    temperature: 1.0
+    tie_encoder_decoder: false
+    tie_word_embeddings: true
+    tokenizer_class: null
+    top_k: 50
+    top_p: 1.0
+    torch_dtype: null
+    torchscript: false
+    transformers_version: 4.17.0.dev0
+    type_vocab_size: 1
+    use_bfloat16: false
+    use_cache: false
+    vocab_size: 50265
+decoder_start_token_id:
+  desc: null
+  value: 0
+deepspeed:
+  desc: null
+  value: None
+disable_tqdm:
+  desc: null
+  value: false
+diversity_penalty:
+  desc: null
+  value: 0.0
+do_eval:
+  desc: null
+  value: true
+do_predict:
+  desc: null
+  value: false
+do_sample:
+  desc: null
+  value: false
+do_train:
+  desc: null
+  value: true
+early_stopping:
+  desc: null
+  value: false
+encoder:
+  desc: null
+  value:
+    _name_or_path: facebook/wav2vec2-large-lv60
+    activation_dropout: 0.1
+    adapter_kernel_size: 3
+    adapter_stride: 2
+    add_adapter: false
+    add_cross_attention: false
+    apply_spec_augment: true
+    architectures:
+    - Wav2Vec2ForPreTraining
+    attention_dropout: 0.1
+    bad_words_ids: null
+    bos_token_id: 1
+    chunk_size_feed_forward: 0
+    classifier_proj_size: 256
+    codevector_dim: 768
+    contrastive_logits_temperature: 0.1
+    conv_bias: true
+    conv_dim:
+    - 512
+    - 512
+    - 512
+    - 512
+    - 512
+    - 512
+    - 512
+    conv_kernel:
+    - 10
+    - 3
+    - 3
+    - 3
+    - 3
+    - 2
+    - 2
+    conv_stride:
+    - 5
+    - 2
+    - 2
+    - 2
+    - 2
+    - 2
+    - 2
+    cross_attention_hidden_size: null
+    ctc_loss_reduction: sum
+    ctc_zero_infinity: false
+    decoder_start_token_id: null
+    diversity_loss_weight: 0.1
+    diversity_penalty: 0.0
+    do_sample: false
+    do_stable_layer_norm: true
+    early_stopping: false
+    encoder_no_repeat_ngram_size: 0
+    eos_token_id: 2
+    feat_extract_activation: gelu
+    feat_extract_dropout: 0.0
+    feat_extract_norm: layer
+    feat_proj_dropout: 0.0
+    feat_quantizer_dropout: 0.0
+    final_dropout: 0.0
+    finetuning_task: null
+    forced_bos_token_id: null
+    forced_eos_token_id: null
+    gradient_checkpointing: false
+    hidden_act: gelu
+    hidden_dropout: 0.1
+    hidden_dropout_prob: 0.1
+    hidden_size: 1024
+    id2label:
+      '0': LABEL_0
+      '1': LABEL_1
+    initializer_range: 0.02
+    intermediate_size: 4096
+    is_decoder: false
+    is_encoder_decoder: false
+    label2id:
+      LABEL_0: 0
+      LABEL_1: 1
+    layer_norm_eps: 1.0e-05
+    layerdrop: 0.0
+    length_penalty: 1.0
+    mask_feature_length: 10
+    mask_feature_min_masks: 0
+    mask_feature_prob: 0.0
+    mask_time_length: 10
+    mask_time_min_masks: 2
+    mask_time_prob: 0.1
+    max_length: 20
+    min_length: 0
+    model_type: wav2vec2
+    no_repeat_ngram_size: 0
+    num_adapter_layers: 3
+    num_attention_heads: 16
+    num_beam_groups: 1
+    num_beams: 1
+    num_codevector_groups: 2
+    num_codevectors_per_group: 320
+    num_conv_pos_embedding_groups: 16
+    num_conv_pos_embeddings: 128
+    num_feat_extract_layers: 7
+    num_hidden_layers: 24
+    num_negatives: 100
+    num_return_sequences: 1
+    output_attentions: false
+    output_hidden_size: 1024
+    output_hidden_states: false
+    output_scores: false
+    pad_token_id: 0
+    prefix: null
+    problem_type: null
+    proj_codevector_dim: 768
+    pruned_heads: {}
+    remove_invalid_values: false
+    repetition_penalty: 1.0
+    return_dict: true
+    return_dict_in_generate: false
+    sep_token_id: null
+    task_specific_params: null
+    tdnn_dilation:
+    - 1
+    - 2
+    - 3
+    - 1
+    - 1
+    tdnn_dim:
+    - 512
+    - 512
+    - 512
+    - 512
+    - 1500
+    tdnn_kernel:
+    - 5
+    - 3
+    - 3
+    - 1
+    - 1
+    temperature: 1.0
+    tie_encoder_decoder: false
+    tie_word_embeddings: true
+    tokenizer_class: null
+    top_k: 50
+    top_p: 1.0
+    torch_dtype: null
+    torchscript: false
+    transformers_version: 4.17.0.dev0
+    use_bfloat16: false
+    use_weighted_layer_sum: false
+    vocab_size: 32
+    xvector_output_dim: 512
+encoder_no_repeat_ngram_size:
+  desc: null
+  value: 0
+eos_token_id:
+  desc: null
+  value: 2
+eval_accumulation_steps:
+  desc: null
+  value: None
+eval_batch_size:
+  desc: null
+  value: 8
+eval_steps:
+  desc: null
+  value: 1500
+evaluation_strategy:
+  desc: null
+  value: steps
+finetuning_task:
+  desc: null
+  value: null
+forced_bos_token_id:
+  desc: null
+  value: null
+forced_eos_token_id:
+  desc: null
+  value: null
+fp16:
+  desc: null
+  value: true
+fp16_backend:
+  desc: null
+  value: auto
+fp16_full_eval:
+  desc: null
+  value: false
+fp16_opt_level:
+  desc: null
+  value: O1
+generation_max_length:
+  desc: null
+  value: 40
+generation_num_beams:
+  desc: null
+  value: 1
+gradient_accumulation_steps:
+  desc: null
+  value: 4
+gradient_checkpointing:
+  desc: null
+  value: true
+greater_is_better:
+  desc: null
+  value: None
+group_by_length:
+  desc: null
+  value: true
+half_precision_backend:
+  desc: null
+  value: amp
+hub_model_id:
+  desc: null
+  value: None
+hub_strategy:
+  desc: null
+  value: every_save
+hub_token:
+  desc: null
+  value: <HUB_TOKEN>
+id2label:
+  desc: null
+  value:
+    '0': LABEL_0
+    '1': LABEL_1
+ignore_data_skip:
+  desc: null
+  value: false
+is_decoder:
+  desc: null
+  value: false
+is_encoder_decoder:
+  desc: null
+  value: true
+label2id:
+  desc: null
+  value:
+    LABEL_0: 0
+    LABEL_1: 1
+label_names:
+  desc: null
+  value: None
+label_smoothing_factor:
+  desc: null
+  value: 0.0
+learning_rate:
+  desc: null
+  value: 5.0e-06
+length_column_name:
+  desc: null
+  value: input_length
+length_penalty:
+  desc: null
+  value: 1.0
+load_best_model_at_end:
+  desc: null
+  value: false
+local_rank:
+  desc: null
+  value: -1
+log_level:
+  desc: null
+  value: -1
+log_level_replica:
+  desc: null
+  value: -1
+log_on_each_node:
+  desc: null
+  value: true
+logging_dir:
+  desc: null
+  value: ./runs/Mar22_09-43-31_sanchit--v100
+logging_first_step:
+  desc: null
+  value: false
+logging_nan_inf_filter:
+  desc: null
+  value: true
+logging_steps:
+  desc: null
+  value: 1
+logging_strategy:
+  desc: null
+  value: steps
+lr_scheduler_type:
+  desc: null
+  value: linear
+max_grad_norm:
+  desc: null
+  value: 1.0
+max_length:
+  desc: null
+  value: 50
+max_steps:
+  desc: null
+  value: -1
+metric_for_best_model:
+  desc: null
+  value: None
+min_length:
+  desc: null
+  value: 0
+model_type:
+  desc: null
+  value: speech-encoder-decoder
+mp_parameters:
+  desc: null
+  value: ''
+no_cuda:
+  desc: null
+  value: false
+no_repeat_ngram_size:
+  desc: null
+  value: 0
+num_beam_groups:
+  desc: null
+  value: 1
+num_beams:
+  desc: null
+  value: 1
+num_return_sequences:
+  desc: null
+  value: 1
+num_train_epochs:
+  desc: null
+  value: 10.0
+optim:
+  desc: null
+  value: adamw_hf
+output_attentions:
+  desc: null
+  value: false
+output_dir:
+  desc: null
+  value: ./
+output_hidden_states:
+  desc: null
+  value: false
+output_scores:
+  desc: null
+  value: false
+overwrite_output_dir:
+  desc: null
+  value: false
+pad_token_id:
+  desc: null
+  value: 1
+past_index:
+  desc: null
+  value: -1
+per_device_eval_batch_size:
+  desc: null
+  value: 8
+per_device_train_batch_size:
+  desc: null
+  value: 8
+per_gpu_eval_batch_size:
+  desc: null
+  value: None
+per_gpu_train_batch_size:
+  desc: null
+  value: None
+predict_with_generate:
+  desc: null
+  value: true
+prediction_loss_only:
+  desc: null
+  value: false
+prefix:
+  desc: null
+  value: null
+problem_type:
+  desc: null
+  value: null
+processor_class:
+  desc: null
+  value: Wav2Vec2Processor
+pruned_heads:
+  desc: null
+  value: {}
+push_to_hub:
+  desc: null
+  value: true
+push_to_hub_model_id:
+  desc: null
+  value: None
+push_to_hub_organization:
+  desc: null
+  value: None
+push_to_hub_token:
+  desc: null
+  value: <PUSH_TO_HUB_TOKEN>
+remove_invalid_values:
+  desc: null
+  value: false
+remove_unused_columns:
+  desc: null
+  value: true
+repetition_penalty:
+  desc: null
+  value: 1.0
+report_to:
+  desc: null
+  value: '[''tensorboard'', ''wandb'']'
+resume_from_checkpoint:
+  desc: null
+  value: None
+return_dict:
+  desc: null
+  value: true
+return_dict_in_generate:
+  desc: null
+  value: false
+run_name:
+  desc: null
+  value: ./
+save_on_each_node:
+  desc: null
+  value: false
+save_steps:
+  desc: null
+  value: 1500
+save_strategy:
+  desc: null
+  value: steps
+save_total_limit:
+  desc: null
+  value: 1
+seed:
+  desc: null
+  value: 42
+sep_token_id:
+  desc: null
+  value: null
+sharded_ddp:
+  desc: null
+  value: '[]'
+skip_memory_metrics:
+  desc: null
+  value: true
+sortish_sampler:
+  desc: null
+  value: false
+task_specific_params:
+  desc: null
+  value: null
+temperature:
+  desc: null
+  value: 1.0
+tf32:
+  desc: null
+  value: None
+tie_encoder_decoder:
+  desc: null
+  value: false
+tie_word_embeddings:
+  desc: null
+  value: false
+tokenizer_class:
+  desc: null
+  value: null
+top_k:
+  desc: null
+  value: 50
+top_p:
+  desc: null
+  value: 1.0
+torch_dtype:
+  desc: null
+  value: torch.float32
+torchscript:
+  desc: null
+  value: false
+tpu_metrics_debug:
+  desc: null
+  value: false
+tpu_num_cores:
+  desc: null
+  value: None
+train_batch_size:
+  desc: null
+  value: 8
+transformers_version:
+  desc: null
+  value: null
+use_bfloat16:
+  desc: null
+  value: false
+use_cache:
+  desc: null
+  value: false
+use_legacy_prediction_loop:
+  desc: null
+  value: false
+warmup_ratio:
+  desc: null
+  value: 0.0
+warmup_steps:
+  desc: null
+  value: 1
+weight_decay:
+  desc: null
+  value: 0.0
+xpu_backend:
+  desc: null
+  value: None

wandb/run-20220322_094406-dk50d3c6/files/output.log

@@ -0,0 +1,63 @@
+
+  0%|                                                                                                                                         | 0/8920 [00:00<?, ?it/s]
+{'train_runtime': 18.8534, 'train_samples_per_second': 15136.821, 'train_steps_per_second': 473.125, 'train_loss': 0.0, 'epoch': 18.5}
+Training completed. Do not forget to share your model on huggingface.co/models =)
+  0%|                                                                                                                                         | 0/8920 [00:17<?, ?it/s]
+Skipping the first batches:   0%|                                                                                                             | 0/1776 [00:18<?, ?it/s]
+[INFO|trainer.py:2114] 2022-03-22 09:44:24,681 >> Saving model checkpoint to ./
+[INFO|configuration_utils.py:438] 2022-03-22 09:44:24,683 >> Configuration saved in ./config.json
+[INFO|modeling_utils.py:1081] 2022-03-22 09:44:40,163 >> Model weights saved in ./pytorch_model.bin
+[INFO|feature_extraction_utils.py:324] 2022-03-22 09:44:40,165 >> Configuration saved in ./preprocessor_config.json
+[INFO|trainer.py:2114] 2022-03-22 09:44:40,166 >> Saving model checkpoint to ./
+[INFO|configuration_utils.py:438] 2022-03-22 09:44:40,168 >> Configuration saved in ./config.json
+Exception in thread NetStatThr:
+Traceback (most recent call last):
+  File "/usr/lib/python3.9/threading.py", line 954, in _bootstrap_inner
+    self.run()
+  File "/usr/lib/python3.9/threading.py", line 892, in run
+    self._target(*self._args, **self._kwargs)
+  File "/home/sanchit_huggingface_co/gcp/lib/python3.9/site-packages/wandb/sdk/wandb_run.py", line 148, in check_network_status
+    status_response = self._interface.communicate_network_status()
+  File "/home/sanchit_huggingface_co/gcp/lib/python3.9/site-packages/wandb/sdk/interface/interface.py", line 125, in communicate_network_status
+    resp = self._communicate_network_status(status)
+  File "/home/sanchit_huggingface_co/gcp/lib/python3.9/site-packages/wandb/sdk/interface/interface_shared.py", line 388, in _communicate_network_status
+    resp = self._communicate(req, local=True)
+  File "/home/sanchit_huggingface_co/gcp/lib/python3.9/site-packages/wandb/sdk/interface/interface_shared.py", line 213, in _communicate
+    return self._communicate_async(rec, local=local).get(timeout=timeout)
+  File "/home/sanchit_huggingface_co/gcp/lib/python3.9/site-packages/wandb/sdk/interface/interface_shared.py", line 218, in _communicate_async
+    raise Exception("The wandb backend process has shutdown")
+Exception: The wandb backend process has shutdown
+Traceback (most recent call last):
+  File "/home/sanchit_huggingface_co/gcp/lib/python3.9/site-packages/torch/serialization.py", line 379, in save
+    _save(obj, opened_zipfile, pickle_module, pickle_protocol)
+  File "/home/sanchit_huggingface_co/gcp/lib/python3.9/site-packages/torch/serialization.py", line 499, in _save
+    zip_file.write_record(name, storage.data_ptr(), num_bytes)
+KeyboardInterrupt
+During handling of the above exception, another exception occurred:
+Traceback (most recent call last):
+  File "/home/sanchit_huggingface_co/gcp/lib/python3.9/site-packages/torch/serialization.py", line 380, in save
+    return
+  File "/home/sanchit_huggingface_co/gcp/lib/python3.9/site-packages/torch/serialization.py", line 259, in __exit__
+    self.file_like.write_end_of_file()
+RuntimeError: [enforce fail at inline_container.cc:300] . unexpected pos 1962672704 vs 1962672592
+During handling of the above exception, another exception occurred:
+Traceback (most recent call last):
+  File "/home/sanchit_huggingface_co/wav2vec2-2-roberta-no-adapter-regularisation/run_speech_recognition_seq2seq.py", line 539, in <module>
+    main()
+  File "/home/sanchit_huggingface_co/wav2vec2-2-roberta-no-adapter-regularisation/run_speech_recognition_seq2seq.py", line 492, in main
+    trainer.save_model()  # Saves the feature extractor too for easy upload
+  File "/home/sanchit_huggingface_co/transformers/src/transformers/trainer.py", line 2080, in save_model
+    self.push_to_hub(commit_message="Model save")
+  File "/home/sanchit_huggingface_co/transformers/src/transformers/trainer.py", line 2812, in push_to_hub
+    self.save_model(_internal_call=True)
+  File "/home/sanchit_huggingface_co/transformers/src/transformers/trainer.py", line 2076, in save_model
+    self._save(output_dir)
+  File "/home/sanchit_huggingface_co/transformers/src/transformers/trainer.py", line 2128, in _save
+    self.model.save_pretrained(output_dir, state_dict=state_dict)
+  File "/home/sanchit_huggingface_co/transformers/src/transformers/modeling_utils.py", line 1079, in save_pretrained
+    save_function(state_dict, output_model_file)
+  File "/home/sanchit_huggingface_co/gcp/lib/python3.9/site-packages/torch/serialization.py", line 381, in save
+    _legacy_save(obj, opened_file, pickle_module, pickle_protocol)
+  File "/home/sanchit_huggingface_co/gcp/lib/python3.9/site-packages/torch/serialization.py", line 214, in __exit__
+    self.file_like.close()
+KeyboardInterrupt

wandb/run-20220322_094406-dk50d3c6/files/requirements.txt

@@ -0,0 +1,186 @@
+absl-py==1.0.0
+aiohttp==3.8.1
+aiosignal==1.2.0
+anyio==3.5.0
+appdirs==1.4.4
+argon2-cffi-bindings==21.2.0
+argon2-cffi==21.3.0
+asttokens==2.0.5
+async-timeout==4.0.2
+attrs==21.4.0
+audioread==2.1.9
+babel==2.9.1
+backcall==0.2.0
+bitsandbytes-cuda113==0.26.0
+black==22.1.0
+bleach==4.1.0
+cachetools==5.0.0
+certifi==2021.10.8
+cffi==1.15.0
+charset-normalizer==2.0.11
+chex==0.1.0
+click==8.0.3
+clldutils==3.10.1
+colorlog==6.6.0
+csvw==1.11.0
+cycler==0.11.0
+datasets==1.18.3
+debugpy==1.5.1
+decorator==5.1.1
+defusedxml==0.7.1
+dill==0.3.4
+dlinfo==1.2.1
+dm-tree==0.1.6
+docker-pycreds==0.4.0
+entrypoints==0.4
+executing==0.8.2
+filelock==3.4.2
+flatbuffers==2.0
+flax==0.4.0
+fonttools==4.29.1
+frozenlist==1.3.0
+fsspec==2022.1.0
+gitdb==4.0.9
+gitpython==3.1.27
+google-auth-oauthlib==0.4.6
+google-auth==2.6.0
+grpcio==1.43.0
+huggingface-hub==0.4.0
+hypothesis==6.36.1
+idna==3.3
+importlib-metadata==4.10.1
+ipdb==0.13.9
+ipykernel==6.8.0
+ipython-genutils==0.2.0
+ipython==8.0.1
+ipywidgets==7.6.5
+isodate==0.6.1
+jax==0.2.28
+jaxlib==0.1.76+cuda11.cudnn82
+jedi==0.18.1
+jinja2==3.0.3
+jiwer==2.3.0
+joblib==1.1.0
+json5==0.9.6
+jsonschema==4.4.0
+jupyter-client==7.1.2
+jupyter-console==6.4.0
+jupyter-core==4.9.1
+jupyter-server==1.13.5
+jupyter==1.0.0
+jupyterlab-pygments==0.1.2
+jupyterlab-server==2.10.3
+jupyterlab-widgets==1.0.2
+jupyterlab==3.2.9
+kiwisolver==1.3.2
+librosa==0.8.1
+llvmlite==0.38.0
+markdown==3.3.6
+markupsafe==2.0.1
+matplotlib-inline==0.1.3
+matplotlib==3.5.1
+mistune==0.8.4
+msgpack==1.0.3
+multidict==6.0.2
+multiprocess==0.70.12.2
+mypy-extensions==0.4.3
+nbclassic==0.3.5
+nbclient==0.5.10
+nbconvert==6.4.1
+nbformat==5.1.3
+nest-asyncio==1.5.4
+notebook==6.4.8
+numba==0.55.1
+numpy==1.21.5
+oauthlib==3.2.0
+opt-einsum==3.3.0
+optax==0.1.0
+packaging==21.3
+pandas==1.4.0
+pandocfilters==1.5.0
+parso==0.8.3
+pathspec==0.9.0
+pathtools==0.1.2
+pexpect==4.8.0
+phonemizer==3.0.1
+pickleshare==0.7.5
+pillow==9.0.0
+pip==22.0.2
+pkg-resources==0.0.0
+platformdirs==2.4.1
+pooch==1.6.0
+prometheus-client==0.13.1
+promise==2.3
+prompt-toolkit==3.0.26
+protobuf==3.19.4
+psutil==5.9.0
+ptyprocess==0.7.0
+pure-eval==0.2.2
+pyarrow==6.0.1
+pyasn1-modules==0.2.8
+pyasn1==0.4.8
+pycparser==2.21
+pyctcdecode==0.3.0
+pygments==2.11.2
+pygtrie==2.4.2
+pyparsing==3.0.7
+pyrsistent==0.18.1
+python-dateutil==2.8.2
+python-levenshtein==0.12.2
+pytz==2021.3
+pyyaml==6.0
+pyzmq==22.3.0
+qtconsole==5.2.2
+qtpy==2.0.1
+regex==2022.1.18
+requests-oauthlib==1.3.1
+requests==2.27.1
+resampy==0.2.2
+rfc3986==2.0.0
+rsa==4.8
+sacremoses==0.0.47
+scikit-learn==1.0.2
+scipy==1.7.3
+segments==2.2.0
+send2trash==1.8.0
+sentry-sdk==1.5.6
+setuptools==44.1.1
+shortuuid==1.0.8
+six==1.16.0
+smmap==5.0.0
+sniffio==1.2.0
+sortedcontainers==2.4.0
+soundfile==0.10.3.post1
+stack-data==0.1.4
+tabulate==0.8.9
+tensorboard-data-server==0.6.1
+tensorboard-plugin-wit==1.8.1
+tensorboard==2.8.0
+termcolor==1.1.0
+terminado==0.13.1
+testpath==0.5.0
+threadpoolctl==3.1.0
+tokenizers==0.11.4
+toml==0.10.2
+tomli==2.0.0
+toolz==0.11.2
+torch==1.10.2+cu113
+torchaudio==0.10.2+cu113
+tornado==6.1
+tqdm==4.62.3
+traitlets==5.1.1
+transformers==4.17.0.dev0
+typing-extensions==3.10.0.2
+uritemplate==4.1.1
+urllib3==1.26.8
+wandb==0.12.10
+wcwidth==0.2.5
+webencodings==0.5.1
+websocket-client==1.2.3
+werkzeug==2.0.2
+wheel==0.37.1
+widgetsnbextension==3.5.2
+xxhash==2.0.2
+yarl==1.7.2
+yaspin==2.1.0
+zipp==3.7.0

wandb/run-20220322_094406-dk50d3c6/files/wandb-metadata.json

@@ -0,0 +1,57 @@
+{
+    "os": "Linux-5.11.0-1028-gcp-x86_64-with-glibc2.33",
+    "python": "3.9.5",
+    "heartbeatAt": "2022-03-22T09:44:07.352031",
+    "startedAt": "2022-03-22T09:44:06.223354",
+    "docker": null,
+    "gpu": "Tesla V100-SXM2-16GB",
+    "gpu_count": 2,
+    "cpu_count": 16,
+    "cuda": null,
+    "args": [
+        "--dataset_name=librispeech_asr",
+        "--model_name_or_path=./",
+        "--dataset_config_name=clean",
+        "--train_split_name=train.100",
+        "--eval_split_name=validation",
+        "--output_dir=./",
+        "--preprocessing_num_workers=1",
+        "--length_column_name=input_length",
+        "--num_train_epochs=10",
+        "--per_device_train_batch_size=8",
+        "--per_device_eval_batch_size=8",
+        "--gradient_accumulation_steps=4",
+        "--generation_max_length=40",
+        "--generation_num_beams=1",
+        "--learning_rate=5e-6",
+        "--warmup_steps=1",
+        "--evaluation_strategy=steps",
+        "--text_column_name=text",
+        "--save_steps=1500",
+        "--eval_steps=1500",
+        "--logging_steps=1",
+        "--save_total_limit=1",
+        "--freeze_feature_encoder",
+        "--gradient_checkpointing",
+        "--fp16",
+        "--group_by_length",
+        "--predict_with_generate",
+        "--do_lower_case",
+        "--do_eval",
+        "--do_train",
+        "--push_to_hub",
+        "--use_auth_token"
+    ],
+    "state": "running",
+    "program": "/home/sanchit_huggingface_co/wav2vec2-2-roberta-no-adapter-regularisation/run_speech_recognition_seq2seq.py",
+    "codePath": "run_speech_recognition_seq2seq.py",
+    "git": {
+        "remote": "https://huggingface.co/sanchit-gandhi/wav2vec2-2-roberta-no-adapter-regularisation",
+        "commit": "b1adb5d25491507607d3af93c76df3608caf1fb0"
+    },
+    "email": "sanchit@huggingface.co",
+    "root": "/home/sanchit_huggingface_co/wav2vec2-2-roberta-no-adapter-regularisation",
+    "host": "sanchit--v100",
+    "username": "sanchit_huggingface_co",
+    "executable": "/home/sanchit_huggingface_co/gcp/bin/python"
+}

wandb/run-20220322_094406-dk50d3c6/files/wandb-summary.json

@@ -0,0 +1 @@
+{"train/train_runtime": 18.8534, "train/train_samples_per_second": 15136.821, "train/train_steps_per_second": 473.125, "train/total_flos": 0.0, "train/train_loss": 0.0, "train/epoch": 18.5, "train/global_step": 16500, "_runtime": 18, "_timestamp": 1647942264, "_step": 0}

wandb/run-20220322_094406-dk50d3c6/logs/debug-internal.log

@@ -0,0 +1,55 @@
+2022-03-22 09:44:07,143 INFO    MainThread:28952 [internal.py:wandb_internal():89] W&B internal server running at pid: 28952, started at: 2022-03-22 09:44:07.142893
+2022-03-22 09:44:07,145 DEBUG   HandlerThread:28952 [handler.py:handle_request():131] handle_request: check_version
+2022-03-22 09:44:07,145 INFO    WriterThread:28952 [datastore.py:open_for_write():77] open: /home/sanchit_huggingface_co/wav2vec2-2-roberta-no-adapter-regularisation/wandb/run-20220322_094406-dk50d3c6/run-dk50d3c6.wandb
+2022-03-22 09:44:07,146 DEBUG   SenderThread:28952 [sender.py:send():235] send: header
+2022-03-22 09:44:07,147 DEBUG   SenderThread:28952 [sender.py:send_request():249] send_request: check_version
+2022-03-22 09:44:07,214 DEBUG   SenderThread:28952 [sender.py:send():235] send: run
+2022-03-22 09:44:07,345 INFO    SenderThread:28952 [dir_watcher.py:__init__():169] watching files in: /home/sanchit_huggingface_co/wav2vec2-2-roberta-no-adapter-regularisation/wandb/run-20220322_094406-dk50d3c6/files
+2022-03-22 09:44:07,345 INFO    SenderThread:28952 [sender.py:_start_run_threads():809] run started: dk50d3c6 with start time 1647942246
+2022-03-22 09:44:07,345 DEBUG   SenderThread:28952 [sender.py:send():235] send: summary
+2022-03-22 09:44:07,345 INFO    SenderThread:28952 [sender.py:_save_file():944] saving file wandb-summary.json with policy end
+2022-03-22 09:44:07,345 DEBUG   HandlerThread:28952 [handler.py:handle_request():131] handle_request: run_start
+2022-03-22 09:44:07,351 DEBUG   HandlerThread:28952 [meta.py:__init__():36] meta init
+2022-03-22 09:44:07,351 DEBUG   HandlerThread:28952 [meta.py:__init__():50] meta init done
+2022-03-22 09:44:07,352 DEBUG   HandlerThread:28952 [meta.py:probe():210] probe
+2022-03-22 09:44:07,358 DEBUG   HandlerThread:28952 [meta.py:_setup_git():200] setup git
+2022-03-22 09:44:07,371 DEBUG   HandlerThread:28952 [meta.py:_setup_git():207] setup git done
+2022-03-22 09:44:07,371 DEBUG   HandlerThread:28952 [meta.py:_save_pip():54] save pip
+2022-03-22 09:44:07,372 DEBUG   HandlerThread:28952 [meta.py:_save_pip():68] save pip done
+2022-03-22 09:44:07,372 DEBUG   HandlerThread:28952 [meta.py:probe():248] probe done
+2022-03-22 09:44:07,446 DEBUG   SenderThread:28952 [sender.py:send():235] send: files
+2022-03-22 09:44:07,447 INFO    SenderThread:28952 [sender.py:_save_file():944] saving file wandb-metadata.json with policy now
+2022-03-22 09:44:07,451 DEBUG   HandlerThread:28952 [handler.py:handle_request():131] handle_request: stop_status
+2022-03-22 09:44:07,452 DEBUG   SenderThread:28952 [sender.py:send_request():249] send_request: stop_status
+2022-03-22 09:44:07,495 DEBUG   SenderThread:28952 [sender.py:send():235] send: config
+2022-03-22 09:44:07,496 DEBUG   SenderThread:28952 [sender.py:send():235] send: metric
+2022-03-22 09:44:07,496 DEBUG   SenderThread:28952 [sender.py:send():235] send: metric
+2022-03-22 09:44:07,496 WARNING SenderThread:28952 [sender.py:send_metric():902] Seen metric with glob (shouldnt happen)
+2022-03-22 09:44:07,757 INFO    Thread-11 :28952 [upload_job.py:push():137] Uploaded file /tmp/tmphh6di6ecwandb/3layvpmg-wandb-metadata.json
+2022-03-22 09:44:08,347 INFO    Thread-8  :28952 [dir_watcher.py:_on_file_created():217] file/dir created: /home/sanchit_huggingface_co/wav2vec2-2-roberta-no-adapter-regularisation/wandb/run-20220322_094406-dk50d3c6/files/requirements.txt
+2022-03-22 09:44:08,347 INFO    Thread-8  :28952 [dir_watcher.py:_on_file_created():217] file/dir created: /home/sanchit_huggingface_co/wav2vec2-2-roberta-no-adapter-regularisation/wandb/run-20220322_094406-dk50d3c6/files/wandb-metadata.json
+2022-03-22 09:44:08,347 INFO    Thread-8  :28952 [dir_watcher.py:_on_file_created():217] file/dir created: /home/sanchit_huggingface_co/wav2vec2-2-roberta-no-adapter-regularisation/wandb/run-20220322_094406-dk50d3c6/files/output.log
+2022-03-22 09:44:08,347 INFO    Thread-8  :28952 [dir_watcher.py:_on_file_created():217] file/dir created: /home/sanchit_huggingface_co/wav2vec2-2-roberta-no-adapter-regularisation/wandb/run-20220322_094406-dk50d3c6/files/wandb-summary.json
+2022-03-22 09:44:10,346 INFO    Thread-8  :28952 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/wav2vec2-2-roberta-no-adapter-regularisation/wandb/run-20220322_094406-dk50d3c6/files/output.log
+2022-03-22 09:44:22,703 DEBUG   HandlerThread:28952 [handler.py:handle_request():131] handle_request: stop_status
+2022-03-22 09:44:22,703 DEBUG   SenderThread:28952 [sender.py:send_request():249] send_request: stop_status
+2022-03-22 09:44:24,681 DEBUG   SenderThread:28952 [sender.py:send():235] send: metric
+2022-03-22 09:44:24,681 DEBUG   SenderThread:28952 [sender.py:send():235] send: metric
+2022-03-22 09:44:24,681 DEBUG   SenderThread:28952 [sender.py:send():235] send: metric
+2022-03-22 09:44:24,681 DEBUG   SenderThread:28952 [sender.py:send():235] send: metric
+2022-03-22 09:44:24,682 DEBUG   SenderThread:28952 [sender.py:send():235] send: metric
+2022-03-22 09:44:24,682 DEBUG   SenderThread:28952 [sender.py:send():235] send: metric
+2022-03-22 09:44:24,682 DEBUG   SenderThread:28952 [sender.py:send():235] send: history
+2022-03-22 09:44:24,682 DEBUG   SenderThread:28952 [sender.py:send():235] send: summary
+2022-03-22 09:44:24,684 INFO    SenderThread:28952 [sender.py:_save_file():944] saving file wandb-summary.json with policy end
+2022-03-22 09:44:25,351 INFO    Thread-8  :28952 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/wav2vec2-2-roberta-no-adapter-regularisation/wandb/run-20220322_094406-dk50d3c6/files/wandb-summary.json
+2022-03-22 09:44:26,351 INFO    Thread-8  :28952 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/wav2vec2-2-roberta-no-adapter-regularisation/wandb/run-20220322_094406-dk50d3c6/files/output.log
+2022-03-22 09:44:35,816 DEBUG   SenderThread:28952 [sender.py:send():235] send: stats
+2022-03-22 09:44:37,748 DEBUG   HandlerThread:28952 [handler.py:handle_request():131] handle_request: stop_status
+2022-03-22 09:44:37,748 DEBUG   SenderThread:28952 [sender.py:send_request():249] send_request: stop_status
+2022-03-22 09:44:38,355 INFO    Thread-8  :28952 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/wav2vec2-2-roberta-no-adapter-regularisation/wandb/run-20220322_094406-dk50d3c6/files/config.yaml
+2022-03-22 09:44:42,356 INFO    Thread-8  :28952 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/wav2vec2-2-roberta-no-adapter-regularisation/wandb/run-20220322_094406-dk50d3c6/files/output.log
+2022-03-22 09:44:43,532 WARNING MainThread:28952 [internal.py:wandb_internal():152] Internal process interrupt: 1
+2022-03-22 09:44:43,701 WARNING MainThread:28952 [internal.py:wandb_internal():152] Internal process interrupt: 2
+2022-03-22 09:44:43,702 ERROR   MainThread:28952 [internal.py:wandb_internal():155] Internal process interrupted.
+2022-03-22 09:44:44,051 INFO    MainThread:28952 [internal.py:handle_exit():79] Internal process exited

wandb/run-20220322_094406-dk50d3c6/logs/debug.log

@@ -0,0 +1,30 @@
+2022-03-22 09:44:06,225 INFO    MainThread:28799 [wandb_setup.py:_flush():75] Loading settings from /home/sanchit_huggingface_co/.config/wandb/settings
+2022-03-22 09:44:06,225 INFO    MainThread:28799 [wandb_setup.py:_flush():75] Loading settings from /home/sanchit_huggingface_co/wav2vec2-2-roberta-no-adapter-regularisation/wandb/settings
+2022-03-22 09:44:06,225 INFO    MainThread:28799 [wandb_setup.py:_flush():75] Loading settings from environment variables: {}
+2022-03-22 09:44:06,225 INFO    MainThread:28799 [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-roberta-no-adapter-regularisation/run_speech_recognition_seq2seq.py'}
+2022-03-22 09:44:06,225 INFO    MainThread:28799 [wandb_init.py:_log_setup():386] Logging user logs to /home/sanchit_huggingface_co/wav2vec2-2-roberta-no-adapter-regularisation/wandb/run-20220322_094406-dk50d3c6/logs/debug.log
+2022-03-22 09:44:06,225 INFO    MainThread:28799 [wandb_init.py:_log_setup():387] Logging internal logs to /home/sanchit_huggingface_co/wav2vec2-2-roberta-no-adapter-regularisation/wandb/run-20220322_094406-dk50d3c6/logs/debug-internal.log
+2022-03-22 09:44:06,225 INFO    MainThread:28799 [wandb_init.py:init():420] calling init triggers
+2022-03-22 09:44:06,225 INFO    MainThread:28799 [wandb_init.py:init():425] wandb.init called with sweep_config: {}
+config: {}
+2022-03-22 09:44:06,225 INFO    MainThread:28799 [wandb_init.py:init():471] starting backend
+2022-03-22 09:44:06,225 INFO    MainThread:28799 [backend.py:_multiprocessing_setup():99] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2022-03-22 09:44:06,280 INFO    MainThread:28799 [backend.py:ensure_launched():219] starting backend process...
+2022-03-22 09:44:06,331 INFO    MainThread:28799 [backend.py:ensure_launched():224] started backend process with pid: 28952
+2022-03-22 09:44:06,333 INFO    MainThread:28799 [wandb_init.py:init():480] backend started and connected
+2022-03-22 09:44:06,344 INFO    MainThread:28799 [wandb_init.py:init():550] updated telemetry
+2022-03-22 09:44:06,466 INFO    MainThread:28799 [wandb_init.py:init():581] communicating current version
+2022-03-22 09:44:07,212 INFO    MainThread:28799 [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"
+
+2022-03-22 09:44:07,213 INFO    MainThread:28799 [wandb_init.py:init():596] communicating run to backend with 30 second timeout
+2022-03-22 09:44:07,345 INFO    MainThread:28799 [wandb_init.py:init():624] starting run threads in backend
+2022-03-22 09:44:07,451 INFO    MainThread:28799 [wandb_run.py:_console_start():1827] atexit reg
+2022-03-22 09:44:07,451 INFO    MainThread:28799 [wandb_run.py:_redirect():1701] redirect: SettingsConsole.REDIRECT
+2022-03-22 09:44:07,452 INFO    MainThread:28799 [wandb_run.py:_redirect():1706] Redirecting console.
+2022-03-22 09:44:07,453 INFO    MainThread:28799 [wandb_run.py:_redirect():1762] Redirects installed.
+2022-03-22 09:44:07,453 INFO    MainThread:28799 [wandb_init.py:init():651] run started, returning control to user process
+2022-03-22 09:44:07,456 INFO    MainThread:28799 [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': 50, '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': ['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': {'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': 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': ['RobertaForMaskedLM'], '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': 0, 'pad_token_id': 1, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'roberta-large', 'transformers_version': '4.17.0.dev0', 'vocab_size': 50265, 'hidden_size': 1024, 'num_hidden_layers': 24, 'num_attention_heads': 16, 'hidden_act': 'gelu', 'intermediate_size': 4096, 'hidden_dropout_prob': 0.1, 'attention_probs_dropout_prob': 0.1, 'max_position_embeddings': 514, 'type_vocab_size': 1, 'initializer_range': 0.02, 'layer_norm_eps': 1e-05, 'position_embedding_type': 'absolute', 'use_cache': False, 'classifier_dropout': None, 'model_type': 'roberta'}, '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': False, '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': False, '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': 4, 'eval_accumulation_steps': 'None', 'learning_rate': 5e-06, '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': 1, 'log_level': -1, 'log_level_replica': -1, 'log_on_each_node': True, 'logging_dir': './runs/Mar22_09-43-31_sanchit--v100', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 1, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 1500, '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': 1500, '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}
+2022-03-22 09:44:07,459 INFO    MainThread:28799 [wandb_watch.py:watch():43] Watching
+2022-03-22 09:44:50,125 INFO    MainThread:28799 [wandb_run.py:_atexit_cleanup():1797] got exitcode: 255
+2022-03-22 09:44:50,127 INFO    MainThread:28799 [wandb_run.py:_restore():1769] restore
+2022-03-22 09:44:52,599 INFO    MainThread:28799 [wandb_run.py:_restore():1769] restore