training_args.do_train: True 01/28/2022 11:13:09 - WARNING - __main__ - Process rank: -1, device: cuda:0, n_gpu: 1distributed training: False, 16-bits training: False 01/28/2022 11:13:09 - 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=False, 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-07, 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=./output/runs/Jan28_11-13-09_arjuna, 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=1.0, optim=OptimizerNames.ADAMW_HF, output_dir=./output, overwrite_output_dir=True, past_index=-1, per_device_eval_batch_size=2, per_device_train_batch_size=2, 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=./output, 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, ) do_train: True load train 01/28/2022 11:13:09 - WARNING - datasets.builder - Reusing dataset common_voice (/home/cahya/.cache/huggingface/datasets/common_voice/tr/6.1.0/5693bfc0feeade582a78c2fb250bc88f52bd86f0a7f1bb22bfee67e715de30fd) 01/28/2022 11:13:10 - WARNING - datasets.builder - Reusing dataset common_voice (/home/cahya/.cache/huggingface/datasets/common_voice/tr/6.1.0/5693bfc0feeade582a78c2fb250bc88f52bd86f0a7f1bb22bfee67e715de30fd) char ignored: [',', '?', '.', '!', ';', ':', '""', '%', "'", '"', "'", "'", '`', '…', '’', '»', '«', '‘', '“', '”', '�', 'é', 'û'] [,?.!;:""%'"''`…’»«‘“”�éû] 01/28/2022 11:13:10 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/cahya/.cache/huggingface/datasets/common_voice/tr/6.1.0/5693bfc0feeade582a78c2fb250bc88f52bd86f0a7f1bb22bfee67e715de30fd/cache-a0df3a81748e62dd.arrow 01/28/2022 11:13:10 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/cahya/.cache/huggingface/datasets/common_voice/tr/6.1.0/5693bfc0feeade582a78c2fb250bc88f52bd86f0a7f1bb22bfee67e715de30fd/cache-859966f17c7349fb.arrow config: Wav2Vec2Config { "_name_or_path": "cahya/wav2vec2-base-turkish-artificial-cv", "activation_dropout": 0.055, "adapter_kernel_size": 3, "adapter_stride": 2, "add_adapter": false, "apply_spec_augment": true, "architectures": [ "Wav2Vec2ForCTC" ], "attention_dropout": 0.094, "bos_token_id": 1, "classifier_proj_size": 256, "codevector_dim": 256, "contrastive_logits_temperature": 0.1, "conv_bias": false, "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": "mean", "ctc_zero_infinity": true, "diversity_loss_weight": 0.1, "do_stable_layer_norm": false, "eos_token_id": 2, "feat_extract_activation": "gelu", "feat_extract_norm": "group", "feat_proj_dropout": 0.04, "feat_quantizer_dropout": 0.0, "final_dropout": 0.1, "gradient_checkpointing": true, "hidden_act": "gelu", "hidden_dropout": 0.047, "hidden_size": 768, "initializer_range": 0.02, "intermediate_size": 3072, "layer_norm_eps": 1e-05, "layerdrop": 0.041, "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": 0.4, "model_type": "wav2vec2", "num_adapter_layers": 3, "num_attention_heads": 12, "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": 12, "num_negatives": 100, "output_hidden_size": 768, "pad_token_id": 39, "proj_codevector_dim": 256, "tdnn_dilation": [ 1, 2, 3, 1, 1 ], "tdnn_dim": [ 512, 512, 512, 512, 1500 ], "tdnn_kernel": [ 5, 3, 3, 1, 1 ], "transformers_version": "4.17.0.dev0", "use_weighted_layer_sum": false, "vocab_size": 40, "xvector_output_dim": 512 } dataset: DatasetDict({ train: Dataset({ features: ['client_id', 'path', 'audio', 'up_votes', 'down_votes', 'age', 'gender', 'accent', 'locale', 'segment', 'target_text'], num_rows: 3478 }) eval: Dataset({ features: ['client_id', 'path', 'audio', 'up_votes', 'down_votes', 'age', 'gender', 'accent', 'locale', 'segment', 'target_text'], num_rows: 1647 }) }) vocab: {'-': 1, 'a': 2, 'b': 3, 'c': 4, 'd': 5, 'e': 6, 'f': 7, 'g': 8, 'h': 9, 'i': 10, 'j': 11, 'k': 12, 'l': 13, 'm': 14, 'n': 15, 'o': 16, 'p': 17, 'q': 18, 'r': 19, 's': 20, 't': 21, 'u': 22, 'v': 23, 'w': 24, 'x': 25, 'y': 26, 'z': 27, 'â': 28, 'ç': 29, 'ë': 30, 'î': 31, 'ö': 32, 'ü': 33, 'ğ': 34, 'ı': 35, 'ş': 36, '̇': 37, '|': 0, '[UNK]': 38, '[PAD]': 39}