diff --git "a/nohup.out" "b/nohup.out" new file mode 100644--- /dev/null +++ "b/nohup.out" @@ -0,0 +1,23287 @@ +02/06/2022 16:31:57 - WARNING - __main__ - Process rank: -1, device: cuda:0, n_gpu: 1distributed training: False, 16-bits training: True +02/06/2022 16:31:57 - INFO - __main__ - Training/evaluation parameters TrainingArguments( +_n_gpu=1, +adafactor=False, +adam_beta1=0.9, +adam_beta2=0.999, +adam_epsilon=1e-08, +bf16=False, +bf16_full_eval=False, +dataloader_drop_last=False, +dataloader_num_workers=0, +dataloader_pin_memory=True, +ddp_bucket_cap_mb=None, +ddp_find_unused_parameters=None, +debug=[], +deepspeed=None, +disable_tqdm=False, +do_eval=True, +do_predict=False, +do_train=True, +eval_accumulation_steps=None, +eval_steps=500, +evaluation_strategy=IntervalStrategy.STEPS, +fp16=True, +fp16_backend=auto, +fp16_full_eval=False, +fp16_opt_level=O1, +gradient_accumulation_steps=4, +gradient_checkpointing=True, +greater_is_better=None, +group_by_length=True, +half_precision_backend=auto, +hub_model_id=None, +hub_strategy=HubStrategy.EVERY_SAVE, +hub_token=, +ignore_data_skip=False, +label_names=None, +label_smoothing_factor=0.0, +learning_rate=0.0001, +length_column_name=input_length, +load_best_model_at_end=False, +local_rank=-1, +log_level=-1, +log_level_replica=-1, +log_on_each_node=True, +logging_dir=./runs/Feb06_16-31-57_job-cb7cc850-8327-4ab0-bdf4-0ebe63e2788c, +logging_first_step=False, +logging_nan_inf_filter=True, +logging_steps=100, +logging_strategy=IntervalStrategy.STEPS, +lr_scheduler_type=SchedulerType.LINEAR, +max_grad_norm=1.0, +max_steps=-1, +metric_for_best_model=None, +mp_parameters=, +no_cuda=False, +num_train_epochs=100.0, +optim=OptimizerNames.ADAMW_HF, +output_dir=./, +overwrite_output_dir=True, +past_index=-1, +per_device_eval_batch_size=8, +per_device_train_batch_size=8, +prediction_loss_only=False, +push_to_hub=True, +push_to_hub_model_id=None, +push_to_hub_organization=None, +push_to_hub_token=, +remove_unused_columns=True, +report_to=['tensorboard'], +resume_from_checkpoint=None, +run_name=./, +save_on_each_node=False, +save_steps=500, +save_strategy=IntervalStrategy.STEPS, +save_total_limit=3, +seed=42, +sharded_ddp=[], +skip_memory_metrics=True, +tf32=None, +tpu_metrics_debug=False, +tpu_num_cores=None, +use_legacy_prediction_loop=False, +warmup_ratio=0.0, +warmup_steps=2000, +weight_decay=0.0, +xpu_backend=None, +) +02/06/2022 16:31:57 - WARNING - datasets.builder - Reusing dataset common_voice (/workspace/.cache/huggingface/datasets/common_voice/zh-HK/6.1.0/5693bfc0feeade582a78c2fb250bc88f52bd86f0a7f1bb22bfee67e715de30fd) +02/06/2022 16:31:58 - WARNING - datasets.builder - Reusing dataset common_voice (/workspace/.cache/huggingface/datasets/common_voice/zh-HK/6.1.0/5693bfc0feeade582a78c2fb250bc88f52bd86f0a7f1bb22bfee67e715de30fd) +02/06/2022 16:31:58 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /workspace/.cache/huggingface/datasets/common_voice/zh-HK/6.1.0/5693bfc0feeade582a78c2fb250bc88f52bd86f0a7f1bb22bfee67e715de30fd/cache-4b9c7ee298793a4a.arrow +02/06/2022 16:31:58 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /workspace/.cache/huggingface/datasets/common_voice/zh-HK/6.1.0/5693bfc0feeade582a78c2fb250bc88f52bd86f0a7f1bb22bfee67e715de30fd/cache-229158ba70a553cf.arrow +loading configuration file https://huggingface.co/facebook/wav2vec2-xls-r-300m/resolve/main/config.json from cache at /workspace/.cache/huggingface/transformers/dabc27df63e37bd2a7a221c7774e35f36a280fbdf917cf54cadfc7df8c786f6f.a3e4c3c967d9985881e0ae550a5f6f668f897db5ab2e0802f9b97973b15970e6 +Model config Wav2Vec2Config { + "_name_or_path": "facebook/wav2vec2-xls-r-300m", + "activation_dropout": 0.0, + "adapter_kernel_size": 3, + "adapter_stride": 2, + "add_adapter": false, + "apply_spec_augment": true, + "architectures": [ + "Wav2Vec2ForPreTraining" + ], + "attention_dropout": 0.1, + "bos_token_id": 1, + "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 + ], + "ctc_loss_reduction": "sum", + "ctc_zero_infinity": false, + "diversity_loss_weight": 0.1, + "do_stable_layer_norm": true, + "eos_token_id": 2, + "feat_extract_activation": "gelu", + "feat_extract_dropout": 0.0, + "feat_extract_norm": "layer", + "feat_proj_dropout": 0.1, + "feat_quantizer_dropout": 0.0, + "final_dropout": 0.0, + "gradient_checkpointing": false, + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 4096, + "layer_norm_eps": 1e-05, + "layerdrop": 0.1, + "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": 0.075, + "model_type": "wav2vec2", + "num_adapter_layers": 3, + "num_attention_heads": 16, + "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, + "output_hidden_size": 1024, + "pad_token_id": 0, + "proj_codevector_dim": 768, + "tdnn_dilation": [ + 1, + 2, + 3, + 1, + 1 + ], + "tdnn_dim": [ + 512, + 512, + 512, + 512, + 1500 + ], + "tdnn_kernel": [ + 5, + 3, + 3, + 1, + 1 + ], + "torch_dtype": "float32", + "transformers_version": "4.17.0.dev0", + "use_weighted_layer_sum": false, + "vocab_size": 32, + "xvector_output_dim": 512 +} + + 0%| | 0/1 [00:00 to the vocabulary +Adding to the vocabulary +Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. +loading configuration file https://huggingface.co/facebook/wav2vec2-xls-r-300m/resolve/main/config.json from cache at /workspace/.cache/huggingface/transformers/dabc27df63e37bd2a7a221c7774e35f36a280fbdf917cf54cadfc7df8c786f6f.a3e4c3c967d9985881e0ae550a5f6f668f897db5ab2e0802f9b97973b15970e6 +Model config Wav2Vec2Config { + "_name_or_path": "facebook/wav2vec2-xls-r-300m", + "activation_dropout": 0.0, + "adapter_kernel_size": 3, + "adapter_stride": 2, + "add_adapter": false, + "apply_spec_augment": true, + "architectures": [ + "Wav2Vec2ForPreTraining" + ], + "attention_dropout": 0.1, + "bos_token_id": 1, + "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 + ], + "ctc_loss_reduction": "sum", + "ctc_zero_infinity": false, + "diversity_loss_weight": 0.1, + "do_stable_layer_norm": true, + "eos_token_id": 2, + "feat_extract_activation": "gelu", + "feat_extract_dropout": 0.0, + "feat_extract_norm": "layer", + "feat_proj_dropout": 0.1, + "feat_quantizer_dropout": 0.0, + "final_dropout": 0.0, + "gradient_checkpointing": false, + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 4096, + "layer_norm_eps": 1e-05, + "layerdrop": 0.1, + "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": 0.075, + "model_type": "wav2vec2", + "num_adapter_layers": 3, + "num_attention_heads": 16, + "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, + "output_hidden_size": 1024, + "pad_token_id": 0, + "proj_codevector_dim": 768, + "tdnn_dilation": [ + 1, + 2, + 3, + 1, + 1 + ], + "tdnn_dim": [ + 512, + 512, + 512, + 512, + 1500 + ], + "tdnn_kernel": [ + 5, + 3, + 3, + 1, + 1 + ], + "torch_dtype": "float32", + "transformers_version": "4.17.0.dev0", + "use_weighted_layer_sum": false, + "vocab_size": 32, + "xvector_output_dim": 512 +} + +loading feature extractor configuration file https://huggingface.co/facebook/wav2vec2-xls-r-300m/resolve/main/preprocessor_config.json from cache at /workspace/.cache/huggingface/transformers/6fb028b95b394059e7d3b367bbca2382b576c66aebe896f04d2cd34e1b575f5b.d4484dc1c81456a2461485e7168b04347a7b9a4e3b1ef3aba723323b33e12326 +Feature extractor Wav2Vec2FeatureExtractor { + "do_normalize": true, + "feature_extractor_type": "Wav2Vec2FeatureExtractor", + "feature_size": 1, + "padding_side": "right", + "padding_value": 0, + "return_attention_mask": true, + "sampling_rate": 16000 +} + +loading weights file https://huggingface.co/facebook/wav2vec2-xls-r-300m/resolve/main/pytorch_model.bin from cache at /workspace/.cache/huggingface/transformers/1e6a6507f3b689035cd4b247e2a37c154e27f39143f31357a49b4e38baeccc36.1edb32803799e27ed554eb7dd935f6745b1a0b17b0ea256442fe24db6eb546cd +Some weights of the model checkpoint at facebook/wav2vec2-xls-r-300m were not used when initializing Wav2Vec2ForCTC: ['project_hid.bias', 'quantizer.codevectors', 'quantizer.weight_proj.weight', 'project_q.weight', 'project_hid.weight', 'project_q.bias', 'quantizer.weight_proj.bias'] +- This IS expected if you are initializing Wav2Vec2ForCTC from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). +- This IS NOT expected if you are initializing Wav2Vec2ForCTC from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). +Some weights of Wav2Vec2ForCTC were not initialized from the model checkpoint at facebook/wav2vec2-xls-r-300m and are newly initialized: ['lm_head.weight', 'lm_head.bias'] +You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference. +02/06/2022 16:32:04 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /workspace/.cache/huggingface/datasets/common_voice/zh-HK/6.1.0/5693bfc0feeade582a78c2fb250bc88f52bd86f0a7f1bb22bfee67e715de30fd/cache-34b3c26b7a1907b4.arrow + preprocess datasets: 0%| | 0/3000 [00:00 to the vocabulary +Adding to the vocabulary +/workspace/wav2vec2-xls-r-300m-zh-HK-v2/./ is already a clone of https://huggingface.co/w11wo/wav2vec2-xls-r-300m-zh-HK-v2. Make sure you pull the latest changes with `repo.git_pull()`. +02/06/2022 16:32:48 - WARNING - huggingface_hub.repository - /workspace/wav2vec2-xls-r-300m-zh-HK-v2/./ is already a clone of https://huggingface.co/w11wo/wav2vec2-xls-r-300m-zh-HK-v2. Make sure you pull the latest changes with `repo.git_pull()`. +Using amp half precision backend +The following columns in the training set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length. +/opt/conda/lib/python3.8/site-packages/transformers/optimization.py:306: FutureWarning: This implementation of AdamW is deprecated and will be removed in a future version. Use thePyTorch implementation torch.optim.AdamW instead, or set `no_deprecation_warning=True` to disable this warning + warnings.warn( +***** Running training ***** + Num examples = 11949 + Num Epochs = 100 + Instantaneous batch size per device = 8 + Total train batch size (w. parallel, distributed & accumulation) = 32 + Gradient Accumulation steps = 4 + Total optimization steps = 37300 + 0%| | 0/37300 [00:00 main + +02/07/2022 12:45:51 - WARNING - huggingface_hub.repository - To https://huggingface.co/w11wo/wav2vec2-xls-r-300m-zh-HK-v2 + 52f4175..ace94fa main -> main + + Upload file pytorch_model.bin: 100%|██████████| 1.19G/1.19G [00:55<00:00, 27.3MB/s] Upload file pytorch_model.bin: 100%|██████████| 1.19G/1.19G [00:55<00:00, 27.3MB/s] Upload file pytorch_model.bin: 100%|██████████| 1.19G/1.19G [00:55<00:00, 23.0MB/s] + + Upload file runs/Feb06_16-31-57_job-cb7cc850-8327-4ab0-bdf4-0ebe63e2788c/events.out.tfevents.1644165171.job-cb7cc850-8327-4ab0-bdf4-0ebe63e2788c: 100%|██████████| 89.4k/89.4k [00:55<00:00, 1.59kB/s] + Upload file runs/Feb06_16-31-57_job-cb7cc850-8327-4ab0-bdf4-0ebe63e2788c/events.out.tfevents.1644165171.job-cb7cc850-8327-4ab0-bdf4-0ebe63e2788c: 100%|██████████| 89.4k/89.4k [00:55<00:00, 1.59kB/s] Upload file runs/Feb06_16-31-57_job-cb7cc850-8327-4ab0-bdf4-0ebe63e2788c/events.out.tfevents.1644165171.job-cb7cc850-8327-4ab0-bdf4-0ebe63e2788c: 100%|██████████| 89.4k/89.4k [00:55<00:00, 1.59kB/s] +Dropping the following result as it does not have all the necessary fields: +{'dataset': {'name': 'common_voice', 'type': 'common_voice', 'args': 'zh-HK'}} +To https://huggingface.co/w11wo/wav2vec2-xls-r-300m-zh-HK-v2 + ace94fa..5679ecf main -> main + +02/07/2022 12:45:57 - WARNING - huggingface_hub.repository - To https://huggingface.co/w11wo/wav2vec2-xls-r-300m-zh-HK-v2 + ace94fa..5679ecf main -> main + +***** train metrics ***** + epoch = 100.0 + train_loss = 3.7852 + train_runtime = 20:10:40.10 + train_samples = 11949 + train_samples_per_second = 16.45 + train_steps_per_second = 0.513 +02/07/2022 12:46:00 - INFO - __main__ - *** Evaluate *** +The following columns in the evaluation set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length. +***** Running Evaluation ***** + Num examples = 2302 + Batch size = 8 + 0%| | 0/288 [00:00 main + +***** eval metrics ***** + epoch = 100.0 + eval_cer = 0.3173 + eval_loss = 0.8089 + eval_runtime = 0:01:56.95 + eval_samples = 2302 + eval_samples_per_second = 19.682 + eval_steps_per_second = 2.462 + eval_wer = 1.2499 +02/07/2022 12:48:24 - WARNING - huggingface_hub.repository - To https://huggingface.co/w11wo/wav2vec2-xls-r-300m-zh-HK-v2 + 5679ecf..5d161f0 main -> main + +Dropping the following result as it does not have all the necessary fields: +{'dataset': {'name': 'COMMON_VOICE - ZH-HK', 'type': 'common_voice', 'args': 'Config: zh-HK, Training split: train+validation, Eval split: test'}} +To https://huggingface.co/w11wo/wav2vec2-xls-r-300m-zh-HK-v2 + 5d161f0..52b2e2e main -> main + +02/07/2022 12:48:31 - WARNING - huggingface_hub.repository - To https://huggingface.co/w11wo/wav2vec2-xls-r-300m-zh-HK-v2 + 5d161f0..52b2e2e main -> main +