diff --git "a/run.ami.log" "b/run.ami.log" new file mode 100644--- /dev/null +++ "b/run.ami.log" @@ -0,0 +1,23038 @@ +/opt/conda/lib/python3.12/site-packages/transformers/training_args.py:1483: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of 🤗 Transformers. Use `eval_strategy` instead + warnings.warn( +05/25/2024 17:57:49 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: False, 16-bits training: True +05/25/2024 17:57:49 - 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, +batch_eval_metrics=False, +bf16=False, +bf16_full_eval=False, +data_seed=None, +dataloader_drop_last=False, +dataloader_num_workers=0, +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_steps=1000, +eval_strategy=IntervalStrategy.STEPS, +evaluation_strategy=steps, +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=None, +group_by_length=True, +half_precision_backend=auto, +hub_always_push=False, +hub_model_id=None, +hub_private_repo=False, +hub_strategy=HubStrategy.EVERY_SAVE, +hub_token=, +ignore_data_skip=False, +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=0.0003, +length_column_name=length, +load_best_model_at_end=False, +local_rank=0, +log_level=passive, +log_level_replica=warning, +log_on_each_node=True, +logging_dir=./runs/May25_17-57-49_tz579-raptorlake, +logging_first_step=False, +logging_nan_inf_filter=True, +logging_steps=1.0, +logging_strategy=IntervalStrategy.STEPS, +lr_scheduler_kwargs={}, +lr_scheduler_type=SchedulerType.LINEAR, +max_grad_norm=1.0, +max_steps=-1, +metric_for_best_model=None, +mp_parameters=, +neftune_noise_alpha=None, +no_cuda=False, +num_train_epochs=2.0, +optim=OptimizerNames.ADAMW_TORCH, +optim_args=None, +optim_target_modules=None, +output_dir=./, +overwrite_output_dir=True, +past_index=-1, +per_device_eval_batch_size=16, +per_device_train_batch_size=16, +prediction_loss_only=False, +push_to_hub=True, +push_to_hub_model_id=None, +push_to_hub_organization=None, +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=./, +save_on_each_node=False, +save_only_model=False, +save_safetensors=True, +save_steps=400, +save_strategy=IntervalStrategy.STEPS, +save_total_limit=3, +seed=42, +skip_memory_metrics=True, +split_batches=None, +tf32=None, +torch_compile=False, +torch_compile_backend=None, +torch_compile_mode=None, +torchdynamo=None, +tpu_metrics_debug=False, +tpu_num_cores=None, +use_cpu=False, +use_ipex=False, +use_legacy_prediction_loop=False, +use_mps_device=False, +warmup_ratio=0.0, +warmup_steps=500, +weight_decay=0.0, +) +/opt/conda/lib/python3.12/site-packages/datasets/load.py:1486: FutureWarning: The repository for edinburghcstr/ami contains custom code which must be executed to correctly load the dataset. You can inspect the repository content at https://hf.co/datasets/edinburghcstr/ami +You can avoid this message in future by passing the argument `trust_remote_code=True`. +Passing `trust_remote_code=True` will be mandatory to load this dataset from the next major release of `datasets`. + warnings.warn( +loading configuration file config.json from cache at /home/Work/common_huggingface/hub/models--facebook--wav2vec2-large-lv60/snapshots/0cde644b64dac88d8416bec1c92a4099b850ba0b/config.json +Model config Wav2Vec2Config { + "_name_or_path": "facebook/wav2vec2-large-lv60", + "activation_dropout": 0.1, + "adapter_attn_dim": null, + "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": 0.1, + "gradient_checkpointing": false, + "hidden_act": "gelu", + "hidden_dropout": 0.1, + "hidden_dropout_prob": 0.1, + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 4096, + "layer_norm_eps": 1e-05, + "layerdrop": 0.0, + "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": 0.05, + "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 + ], + "transformers_version": "4.42.0.dev0", + "use_weighted_layer_sum": false, + "vocab_size": 32, + "xvector_output_dim": 512 +} + + Map: 0%| | 0/108502 [00:00', 'eos_token': '', 'unk_token': '[UNK]', 'pad_token': '[PAD]'}, clean_up_tokenization_spaces=True), added_tokens_decoder={ + 28: AddedToken("[UNK]", rstrip=True, lstrip=True, single_word=False, normalized=False, special=False), + 29: AddedToken("[PAD]", rstrip=True, lstrip=True, single_word=False, normalized=False, special=False), + 30: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), + 31: AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), +} + +{ + "processor_class": "Wav2Vec2Processor" +} + +Using auto 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. If input_length are not expected by `Wav2Vec2ForCTC.forward`, you can safely ignore this message. +***** Running training ***** + Num examples = 102,201 + Num Epochs = 2 + Instantaneous batch size per device = 16 + Total train batch size (w. parallel, distributed & accumulation) = 16 + Gradient Accumulation steps = 1 + Total optimization steps = 12,776 + Number of trainable parameters = 311,261,344 + 0%| | 0/12776 [00:00