05/07/2022 18:26:07 - INFO - __main__ - Training/evaluation parameters FlaxSeq2SeqTrainingArguments( _n_gpu=-1, adafactor=False, adam_beta1=0.9, adam_beta2=0.999, adam_epsilon=1e-08, bf16=False, bf16_full_eval=False, data_seed=None, 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=None, do_eval=True, do_predict=True, do_train=True, eval_accumulation_steps=None, eval_delay=0, eval_steps=5, evaluation_strategy=no, final_generation_max_length=40, final_generation_num_beams=1, fp16=False, fp16_backend=auto, fp16_full_eval=False, fp16_opt_level=O1, generation_length_penalty=1, generation_max_length=40, generation_num_beams=1, gradient_accumulation_steps=1, gradient_checkpointing=False, greater_is_better=None, group_by_length=False, half_precision_backend=auto, hub_model_id=None, hub_strategy=every_save, hub_token=, ignore_data_skip=False, label_names=None, label_smoothing_factor=0.0, learning_rate=0.0003, length_column_name=input_length, load_best_model_at_end=False, local_rank=-1, log_level=passive, log_level_replica=passive, log_on_each_node=True, logging_dir=None, logging_first_step=False, logging_nan_inf_filter=True, logging_steps=1, logging_strategy=steps, lr_scheduler_type=linear, matmul_precision=default, max_grad_norm=1.0, max_steps=10, metric_for_best_model=None, mp_parameters=, no_cuda=False, num_train_epochs=3.0, optim=adamw_hf, output_dir=./, overwrite_output_dir=True, past_index=-1, per_device_eval_batch_size=2, per_device_train_batch_size=2, precision=full, predict_with_generate=True, 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=None, resume_from_checkpoint=None, run_name=None, save_on_each_node=False, save_steps=5, save_strategy=steps, save_total_limit=1, seed=42, sharded_ddp=, skip_memory_metrics=True, sortish_sampler=False, tf32=None, tpu_metrics_debug=False, tpu_num_cores=None, use_legacy_prediction_loop=False, warmup_ratio=0.0, warmup_steps=500, weight_decay=0.0, xpu_backend=None, ) 05/07/2022 18:26:07 - INFO - __main__ - JAX devices: 8, matmul precision: default 05/07/2022 18:26:07 - WARNING - datasets.builder - Reusing dataset librispeech_asr (/home/sanchitgandhi/cache/huggingface/datasets/hf-internal-testing___librispeech_asr/clean/2.1.0/d3bc4c2bc2078fcde3ad0f0f635862e4c0fef78ba94c4a34c4c250a097af240b) 05/07/2022 18:26:08 - WARNING - datasets.builder - Reusing dataset librispeech_asr (/home/sanchitgandhi/cache/huggingface/datasets/hf-internal-testing___librispeech_asr/clean/2.1.0/d3bc4c2bc2078fcde3ad0f0f635862e4c0fef78ba94c4a34c4c250a097af240b) loading configuration file ./config.json You passed along `num_labels=3` with an incompatible id to label map: {'0': 'LABEL_0', '1': 'LABEL_1'}. The number of labels wil be overwritten to 2. Model config SpeechEncoderDecoderConfig { "_name_or_path": "./", "architectures": [ "SpeechEncoderDecoderModel" ], "decoder": { "_name_or_path": "", "activation_dropout": 0.0, "activation_function": "gelu", "add_cross_attention": true, "architectures": null, "attention_dropout": 0.1, "bad_words_ids": null, "bos_token_id": 0, "chunk_size_feed_forward": 0, "classifier_dropout": 0.0, "cross_attention_hidden_size": null, "d_model": 16, "decoder_attention_heads": 4, "decoder_ffn_dim": 4, "decoder_layerdrop": 0.0, "decoder_layers": 2, "decoder_start_token_id": 2, "diversity_penalty": 0.0, "do_sample": false, "dropout": 0.1, "early_stopping": false, "encoder_attention_heads": 4, "encoder_ffn_dim": 4, "encoder_layerdrop": 0.0, "encoder_layers": 2, "encoder_no_repeat_ngram_size": 0, "eos_token_id": 2, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": 2, "fuse_matmuls": false, "gradient_checkpointing": false, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "init_std": 0.02, "is_decoder": true, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 100, "min_length": 0, "model_type": "bart", "no_repeat_ngram_size": 0, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 2, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": 1, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "scale_embedding": false, "sep_token_id": null, "task_specific_params": null, "temperature": 1.0, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": null, "torchscript": false, "transformers_version": "4.18.0.dev0", "typical_p": 1.0, "use_bfloat16": false, "use_cache": true, "use_scan": true, "vocab_size": 1000 }, "decoder_start_token_id": 0, "encoder": { "_name_or_path": "", "activation_dropout": 0.1, "adapter_kernel_size": 3, "adapter_stride": 2, "add_adapter": true, "add_cross_attention": false, "apply_spec_augment": true, "architectures": null, "attention_dropout": 0.1, "bad_words_ids": null, "bos_token_id": 1, "chunk_size_feed_forward": 0, "classifier_proj_size": 256, "codevector_dim": 256, "contrastive_logits_temperature": 0.1, "conv_bias": false, "conv_dim": [ 32, 32, 32 ], "conv_kernel": [ 8, 8, 8 ], "conv_stride": [ 4, 4, 4 ], "cross_attention_hidden_size": null, "ctc_loss_reduction": "sum", "ctc_zero_infinity": false, "decoder_start_token_id": null, "diversity_loss_weight": 0.1, "diversity_penalty": 0.0, "do_sample": false, "do_stable_layer_norm": true, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": 2, "exponential_decay_length_penalty": null, "feat_extract_activation": "gelu", "feat_extract_dropout": 0.0, "feat_extract_norm": "layer", "feat_proj_dropout": 0.0, "feat_quantizer_dropout": 0.0, "final_dropout": 0.0, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "fuse_matmuls": false, "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout": 0.1, "hidden_dropout_prob": 0.1, "hidden_size": 16, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 20, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_eps": 1e-05, "layerdrop": 0.0, "length_penalty": 1.0, "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": 0.1, "max_length": 20, "min_length": 0, "model_type": "wav2vec2", "no_repeat_ngram_size": 0, "num_adapter_layers": 3, "num_attention_heads": 2, "num_beam_groups": 1, "num_beams": 1, "num_codevector_groups": 2, "num_codevectors_per_group": 320, "num_conv_pos_embedding_groups": 2, "num_conv_pos_embeddings": 16, "num_feat_extract_layers": 3, "num_hidden_layers": 4, "num_negatives": 10, "num_return_sequences": 1, "output_attentions": false, "output_hidden_size": 16, "output_hidden_states": false, "output_scores": false, "pad_token_id": 0, "prefix": null, "problem_type": null, "proj_codevector_dim": 256, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "task_specific_params": null, "tdnn_dilation": [ 1, 2, 3, 1, 1 ], "tdnn_dim": [ 512, 512, 512, 512, 1500 ], "tdnn_kernel": [ 5, 3, 3, 1, 1 ], "temperature": 1.0, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": null, "torchscript": false, "transformers_version": "4.18.0.dev0", "typical_p": 1.0, "use_bfloat16": false, "use_scan": true, "use_weighted_layer_sum": false, "vocab_size": 32, "xvector_output_dim": 512 }, "eos_token_id": 2, "is_encoder_decoder": true, "max_length": 40, "model_type": "speech-encoder-decoder", "pad_token_id": 1, "processor_class": "Wav2Vec2Processor", "tie_word_embeddings": false, "transformers_version": null, "use_cache": false } loading feature extractor configuration file ./preprocessor_config.json Feature extractor Wav2Vec2FeatureExtractor { "do_normalize": true, "feature_extractor_type": "Wav2Vec2FeatureExtractor", "feature_size": 1, "padding_side": "right", "padding_value": 0.0, "return_attention_mask": false, "sampling_rate": 16000 } Didn't find file ./added_tokens.json. We won't load it. loading file ./vocab.json loading file ./merges.txt loading file ./tokenizer.json loading file None loading file ./special_tokens_map.json loading file ./tokenizer_config.json loading weights file ./flax_model.msgpack 05/07/2022 18:26:09 - WARNING - datasets.builder - Reusing dataset librispeech_asr (/home/sanchitgandhi/cache/huggingface/datasets/hf-internal-testing___librispeech_asr/clean/2.1.0/d3bc4c2bc2078fcde3ad0f0f635862e4c0fef78ba94c4a34c4c250a097af240b) 05/07/2022 18:26:09 - WARNING - datasets.builder - Reusing dataset librispeech_asr (/home/sanchitgandhi/cache/huggingface/datasets/hf-internal-testing___librispeech_asr/clean/2.1.0/d3bc4c2bc2078fcde3ad0f0f635862e4c0fef78ba94c4a34c4c250a097af240b) All model checkpoint weights were used when initializing FlaxSpeechEncoderDecoderModel. All the weights of FlaxSpeechEncoderDecoderModel were initialized from the model checkpoint at ./. If your task is similar to the task the model of the checkpoint was trained on, you can already use FlaxSpeechEncoderDecoderModel for predictions without further training. Feature extractor saved in ./preprocessor_config.json tokenizer config file saved in ./tokenizer_config.json Special tokens file saved in ./special_tokens_map.json Configuration saved in ./config.json loading feature extractor configuration file ./preprocessor_config.json loading configuration file ./config.json You passed along `num_labels=3` with an incompatible id to label map: {'0': 'LABEL_0', '1': 'LABEL_1'}. The number of labels wil be overwritten to 2. Model config SpeechEncoderDecoderConfig { "_name_or_path": "./", "architectures": [ "SpeechEncoderDecoderModel" ], "decoder": { "_name_or_path": "", "activation_dropout": 0.0, "activation_function": "gelu", "add_cross_attention": true, "architectures": null, "attention_dropout": 0.1, "bad_words_ids": null, "bos_token_id": 0, "chunk_size_feed_forward": 0, "classifier_dropout": 0.0, "cross_attention_hidden_size": null, "d_model": 16, "decoder_attention_heads": 4, "decoder_ffn_dim": 4, "decoder_layerdrop": 0.0, "decoder_layers": 2, "decoder_start_token_id": 2, "diversity_penalty": 0.0, "do_sample": false, "dropout": 0.1, "early_stopping": false, "encoder_attention_heads": 4, "encoder_ffn_dim": 4, "encoder_layerdrop": 0.0, "encoder_layers": 2, "encoder_no_repeat_ngram_size": 0, "eos_token_id": 2, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": 2, "fuse_matmuls": false, "gradient_checkpointing": false, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "init_std": 0.02, "is_decoder": true, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 100, "min_length": 0, "model_type": "bart", "no_repeat_ngram_size": 0, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 2, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": 1, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "scale_embedding": false, "sep_token_id": null, "task_specific_params": null, "temperature": 1.0, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": null, "torchscript": false, "transformers_version": "4.18.0.dev0", "typical_p": 1.0, "use_bfloat16": false, "use_cache": true, "use_scan": true, "vocab_size": 1000 }, "decoder_start_token_id": 0, "encoder": { "_name_or_path": "", "activation_dropout": 0.1, "adapter_kernel_size": 3, "adapter_stride": 2, "add_adapter": true, "add_cross_attention": false, "apply_spec_augment": true, "architectures": null, "attention_dropout": 0.1, "bad_words_ids": null, "bos_token_id": 1, "chunk_size_feed_forward": 0, "classifier_proj_size": 256, "codevector_dim": 256, "contrastive_logits_temperature": 0.1, "conv_bias": false, "conv_dim": [ 32, 32, 32 ], "conv_kernel": [ 8, 8, 8 ], "conv_stride": [ 4, 4, 4 ], "cross_attention_hidden_size": null, "ctc_loss_reduction": "sum", "ctc_zero_infinity": false, "decoder_start_token_id": null, "diversity_loss_weight": 0.1, "diversity_penalty": 0.0, "do_sample": false, "do_stable_layer_norm": true, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": 2, "exponential_decay_length_penalty": null, "feat_extract_activation": "gelu", "feat_extract_dropout": 0.0, "feat_extract_norm": "layer", "feat_proj_dropout": 0.0, "feat_quantizer_dropout": 0.0, "final_dropout": 0.0, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "fuse_matmuls": false, "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout": 0.1, "hidden_dropout_prob": 0.1, "hidden_size": 16, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 20, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_eps": 1e-05, "layerdrop": 0.0, "length_penalty": 1.0, "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": 0.1, "max_length": 20, "min_length": 0, "model_type": "wav2vec2", "no_repeat_ngram_size": 0, "num_adapter_layers": 3, "num_attention_heads": 2, "num_beam_groups": 1, "num_beams": 1, "num_codevector_groups": 2, "num_codevectors_per_group": 320, "num_conv_pos_embedding_groups": 2, "num_conv_pos_embeddings": 16, "num_feat_extract_layers": 3, "num_hidden_layers": 4, "num_negatives": 10, "num_return_sequences": 1, "output_attentions": false, "output_hidden_size": 16, "output_hidden_states": false, "output_scores": false, "pad_token_id": 0, "prefix": null, "problem_type": null, "proj_codevector_dim": 256, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "task_specific_params": null, "tdnn_dilation": [ 1, 2, 3, 1, 1 ], "tdnn_dim": [ 512, 512, 512, 512, 1500 ], "tdnn_kernel": [ 5, 3, 3, 1, 1 ], "temperature": 1.0, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": null, "torchscript": false, "transformers_version": "4.18.0.dev0", "typical_p": 1.0, "use_bfloat16": false, "use_scan": true, "use_weighted_layer_sum": false, "vocab_size": 32, "xvector_output_dim": 512 }, "eos_token_id": 2, "is_encoder_decoder": true, "max_length": 40, "model_type": "speech-encoder-decoder", "pad_token_id": 1, "processor_class": "Wav2Vec2Processor", "tie_word_embeddings": false, "transformers_version": null, "use_cache": false } loading feature extractor configuration file ./preprocessor_config.json Feature extractor Wav2Vec2FeatureExtractor { "do_normalize": true, "feature_extractor_type": "Wav2Vec2FeatureExtractor", "feature_size": 1, "padding_side": "right", "padding_value": 0.0, "return_attention_mask": false, "sampling_rate": 16000 } Didn't find file ./added_tokens.json. We won't load it. loading file ./vocab.json loading file ./merges.txt loading file ./tokenizer.json loading file None loading file ./special_tokens_map.json loading file ./tokenizer_config.json 2022-05-07 18:26:20.354208: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcuda.so.1'; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory 2022-05-07 18:26:20.354247: W tensorflow/stream_executor/cuda/cuda_driver.cc:269] failed call to cuInit: UNKNOWN ERROR (303) 05/07/2022 18:26:20 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/hf-internal-testing___librispeech_asr/clean/2.1.0/d3bc4c2bc2078fcde3ad0f0f635862e4c0fef78ba94c4a34c4c250a097af240b/cache-172908eb2439798c.arrow 05/07/2022 18:26:20 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/hf-internal-testing___librispeech_asr/clean/2.1.0/d3bc4c2bc2078fcde3ad0f0f635862e4c0fef78ba94c4a34c4c250a097af240b/cache-172908eb2439798c.arrow 05/07/2022 18:26:20 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/hf-internal-testing___librispeech_asr/clean/2.1.0/d3bc4c2bc2078fcde3ad0f0f635862e4c0fef78ba94c4a34c4c250a097af240b/cache-3788df45b822e09d.arrow 05/07/2022 18:26:20 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/hf-internal-testing___librispeech_asr/clean/2.1.0/d3bc4c2bc2078fcde3ad0f0f635862e4c0fef78ba94c4a34c4c250a097af240b/cache-836619e0a5bdc111.arrow 05/07/2022 18:26:20 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/hf-internal-testing___librispeech_asr/clean/2.1.0/d3bc4c2bc2078fcde3ad0f0f635862e4c0fef78ba94c4a34c4c250a097af240b/cache-760f29b7172d4ca5.arrow 05/07/2022 18:26:20 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/hf-internal-testing___librispeech_asr/clean/2.1.0/d3bc4c2bc2078fcde3ad0f0f635862e4c0fef78ba94c4a34c4c250a097af240b/cache-760f29b7172d4ca5.arrow 05/07/2022 18:26:20 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/hf-internal-testing___librispeech_asr/clean/2.1.0/d3bc4c2bc2078fcde3ad0f0f635862e4c0fef78ba94c4a34c4c250a097af240b/cache-c95f128933ad1116.arrow 05/07/2022 18:26:20 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/hf-internal-testing___librispeech_asr/clean/2.1.0/d3bc4c2bc2078fcde3ad0f0f635862e4c0fef78ba94c4a34c4c250a097af240b/cache-0b5b21388629ee07.arrow 05/07/2022 18:26:20 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/hf-internal-testing___librispeech_asr/clean/2.1.0/d3bc4c2bc2078fcde3ad0f0f635862e4c0fef78ba94c4a34c4c250a097af240b/cache-19bf1682e842ea83.arrow 05/07/2022 18:26:20 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/hf-internal-testing___librispeech_asr/clean/2.1.0/d3bc4c2bc2078fcde3ad0f0f635862e4c0fef78ba94c4a34c4c250a097af240b/cache-19bf1682e842ea83.arrow 05/07/2022 18:26:20 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/hf-internal-testing___librispeech_asr/clean/2.1.0/d3bc4c2bc2078fcde3ad0f0f635862e4c0fef78ba94c4a34c4c250a097af240b/cache-d26d6988d1d20694.arrow 05/07/2022 18:26:20 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/hf-internal-testing___librispeech_asr/clean/2.1.0/d3bc4c2bc2078fcde3ad0f0f635862e4c0fef78ba94c4a34c4c250a097af240b/cache-735fc28d6b3118f5.arrow /home/sanchitgandhi/flax-dummy/./ is already a clone of https://huggingface.co/sanchit-gandhi/flax-dummy. Make sure you pull the latest changes with `repo.git_pull()`. Epoch ... (1/3): 0%| | 0/3 [00:00