diff --git "a/logs.txt" "b/logs.txt" new file mode 100644--- /dev/null +++ "b/logs.txt" @@ -0,0 +1,16022 @@ +W0423 17:35:18.793000 5422 torch/distributed/run.py:792] +W0423 17:35:18.793000 5422 torch/distributed/run.py:792] ***************************************** +W0423 17:35:18.793000 5422 torch/distributed/run.py:792] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. +W0423 17:35:18.793000 5422 torch/distributed/run.py:792] ***************************************** +/root/workdir/.venv/lib/python3.10/site-packages/transformers/training_args.py:2085: FutureWarning: `--push_to_hub_organization` is deprecated and will be removed in version 5 of 🤗 Transformers. Use `--hub_model_id` instead and pass the full repo name to this argument (in this case CLEAR-Global/w2v-bert-2.0-hausa_naijavoices_100h). + warnings.warn( +04/23/2025 17:35:24 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: True, 16-bits training: True +04/23/2025 17:35:24 - INFO - __main__ - Training/evaluation parameters TrainingArguments( +_n_gpu=1, +accelerator_config={'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None, 'use_configured_state': False}, +adafactor=False, +adam_beta1=0.9, +adam_beta2=0.999, +adam_epsilon=1e-08, +auto_find_batch_size=False, +average_tokens_across_devices=False, +batch_eval_metrics=False, +bf16=False, +bf16_full_eval=False, +data_seed=None, +dataloader_drop_last=False, +dataloader_num_workers=44, +dataloader_persistent_workers=False, +dataloader_pin_memory=True, +dataloader_prefetch_factor=None, +ddp_backend=None, +ddp_broadcast_buffers=None, +ddp_bucket_cap_mb=None, +ddp_find_unused_parameters=None, +ddp_timeout=1800, +debug=[], +deepspeed=None, +disable_tqdm=False, +dispatch_batches=None, +do_eval=True, +do_predict=False, +do_train=True, +eval_accumulation_steps=None, +eval_delay=0, +eval_do_concat_batches=True, +eval_on_start=False, +eval_steps=1000, +eval_strategy=steps, +eval_use_gather_object=False, +evaluation_strategy=None, +fp16=True, +fp16_backend=auto, +fp16_full_eval=False, +fp16_opt_level=O1, +fsdp=[], +fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, +fsdp_min_num_params=0, +fsdp_transformer_layer_cls_to_wrap=None, +full_determinism=False, +gradient_accumulation_steps=1, +gradient_checkpointing=True, +gradient_checkpointing_kwargs=None, +greater_is_better=False, +group_by_length=True, +half_precision_backend=auto, +hub_always_push=False, +hub_model_id=CLEAR-Global/w2v-bert-2.0-hausa_naijavoices_100h, +hub_private_repo=None, +hub_strategy=checkpoint, +hub_token=, +ignore_data_skip=False, +include_for_metrics=[], +include_inputs_for_metrics=False, +include_num_input_tokens_seen=False, +include_tokens_per_second=False, +jit_mode_eval=False, +label_names=None, +label_smoothing_factor=0.0, +learning_rate=3e-05, +length_column_name=input_length, +load_best_model_at_end=True, +local_rank=0, +log_level=passive, +log_level_replica=warning, +log_on_each_node=True, +logging_dir=./w2v-bert-2.0-hausa_naijavoices_100h/runs/Apr23_17-35-24_synvoices-hausa-2, +logging_first_step=False, +logging_nan_inf_filter=True, +logging_steps=1.0, +logging_strategy=steps, +lr_scheduler_kwargs={}, +lr_scheduler_type=linear, +max_grad_norm=1.0, +max_steps=-1, +metric_for_best_model=loss, +mp_parameters=, +neftune_noise_alpha=None, +no_cuda=False, +num_train_epochs=250.0, +optim=adamw_torch, +optim_args=None, +optim_target_modules=None, +output_dir=./w2v-bert-2.0-hausa_naijavoices_100h, +overwrite_output_dir=False, +past_index=-1, +per_device_eval_batch_size=160, +per_device_train_batch_size=160, +prediction_loss_only=False, +push_to_hub=True, +push_to_hub_model_id=None, +push_to_hub_organization=CLEAR-Global, +push_to_hub_token=, +ray_scope=last, +remove_unused_columns=True, +report_to=['tensorboard'], +restore_callback_states_from_checkpoint=False, +resume_from_checkpoint=None, +run_name=./w2v-bert-2.0-hausa_naijavoices_100h, +save_on_each_node=False, +save_only_model=False, +save_safetensors=True, +save_steps=1000, +save_strategy=steps, +save_total_limit=1, +seed=42, +skip_memory_metrics=True, +split_batches=None, +tf32=None, +torch_compile=False, +torch_compile_backend=None, +torch_compile_mode=None, +torch_empty_cache_steps=None, +torchdynamo=None, +tpu_metrics_debug=False, +tpu_num_cores=None, +use_cpu=False, +use_ipex=False, +use_legacy_prediction_loop=False, +use_liger_kernel=False, +use_mps_device=False, +warmup_ratio=0.1, +warmup_steps=0, +weight_decay=0.0, +) +/root/workdir/.venv/lib/python3.10/site-packages/transformers/training_args.py:2085: FutureWarning: `--push_to_hub_organization` is deprecated and will be removed in version 5 of 🤗 Transformers. Use `--hub_model_id` instead and pass the full repo name to this argument (in this case CLEAR-Global/w2v-bert-2.0-hausa_naijavoices_100h). + warnings.warn( +04/23/2025 17:35:24 - WARNING - __main__ - Process rank: 1, device: cuda:1, n_gpu: 1, distributed training: True, 16-bits training: True + Downloading data: 0%| | 0/24 [00:00', 'eos_token': '', 'unk_token': '[UNK]', 'pad_token': '[PAD]'}, clean_up_tokenization_spaces=False, added_tokens_decoder={ + 85: AddedToken("[UNK]", rstrip=True, lstrip=True, single_word=False, normalized=False, special=False), + 86: AddedToken("[PAD]", rstrip=True, lstrip=True, single_word=False, normalized=False, special=False), + 87: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), + 88: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), +} +) + +{ + "processor_class": "Wav2Vec2BertProcessor" +} + +Using auto half precision backend +04/23/2025 17:39:26 - INFO - __main__ - Fine-tuning model from scratch +The following columns in the training set don't have a corresponding argument in `Wav2Vec2BertForCTC.forward` and have been ignored: input_length. If input_length are not expected by `Wav2Vec2BertForCTC.forward`, you can safely ignore this message. +***** Running training ***** + Num examples = 114,548 + Num Epochs = 250 + Instantaneous batch size per device = 160 + Total train batch size (w. parallel, distributed & accumulation) = 320 + Gradient Accumulation steps = 1 + Total optimization steps = 89,500 + Number of trainable parameters = 605,768,601 + 0%| | 0/89500 [00:00