diff --git "a/nohup.out" "b/nohup.out" new file mode 100644--- /dev/null +++ "b/nohup.out" @@ -0,0 +1,585 @@ +01/31/2022 11:15:19 - WARNING - __main__ - Process rank: -1, device: cuda:0, n_gpu: 1distributed training: False, 16-bits training: True +01/31/2022 11:15:19 - 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=7.5e-05, +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/Jan31_11-15-19_job-aa543290-d6de-4d4d-8a32-2149b1b8e7e3, +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=50.0, +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=[], +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, +) + Downloading: 0%| | 0.00/4.67k [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-1b/resolve/main/config.json from cache at /workspace/.cache/huggingface/transformers/19f816c26d6fef49a4dfc0fc6b841c37792a250d2697d8432769f8af5698f1dc.90dd5f300087b6277c408283c36aefa2efb15afd0d3e210b3a7c3f3efc478d03 +Model config Wav2Vec2Config { + "_name_or_path": "facebook/wav2vec2-xls-r-1b", + "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": 1024, + "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": 1280, + "initializer_range": 0.02, + "intermediate_size": 5120, + "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": 48, + "num_negatives": 100, + "output_hidden_size": 1280, + "pad_token_id": 0, + "proj_codevector_dim": 1024, + "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 +} + +https://huggingface.co/facebook/wav2vec2-xls-r-1b/resolve/main/preprocessor_config.json not found in cache or force_download set to True, downloading to /workspace/.cache/huggingface/transformers/tmpjxesrf60 + Downloading: 0%| | 0.00/212 [00:00 to the vocabulary +Adding to the vocabulary +/workspace/wav2vec2-xls-r-1b-korean/./ is already a clone of https://huggingface.co/anantoj/wav2vec2-xls-r-1b-korean. Make sure you pull the latest changes with `repo.git_pull()`. +01/31/2022 11:22:37 - WARNING - huggingface_hub.repository - /workspace/wav2vec2-xls-r-1b-korean/./ is already a clone of https://huggingface.co/anantoj/wav2vec2-xls-r-1b-korean. 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 = 22262 + Num Epochs = 50 + Instantaneous batch size per device = 8 + Total train batch size (w. parallel, distributed & accumulation) = 32 + Gradient Accumulation steps = 4 + Total optimization steps = 34750 + 0%| | 0/34750 [00:00