| 05/07/2022 17:43:00 - 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=50, | |
| final_generation_num_beams=2, | |
| 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=<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=15, | |
| metric_for_best_model=None, | |
| mp_parameters=, | |
| no_cuda=False, | |
| num_train_epochs=5.0, | |
| optim=adamw_hf, | |
| output_dir=./, | |
| overwrite_output_dir=True, | |
| past_index=-1, | |
| per_device_eval_batch_size=2, | |
| per_device_train_batch_size=4, | |
| precision=full, | |
| predict_with_generate=True, | |
| prediction_loss_only=False, | |
| push_to_hub=False, | |
| push_to_hub_model_id=None, | |
| push_to_hub_organization=None, | |
| push_to_hub_token=<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=10, | |
| 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 17:43:00 - INFO - __main__ - JAX devices: 8, matmul precision: default | |
| 05/07/2022 17:43:01 - 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 17:43:01 - 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 17:43:02 - 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 17:43:02 - 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. | |
| preprocess train dataset: 0%| | 0/73 [00:00<?, ?ex/s] | |
| 05/07/2022 17:43:19 - 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 17:43:19 - 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 | |
| preprocess train dataset: 100%|█████████████████████████████████████████████████████████| 73/73 [00:05<00:00, 12.74ex/s] | |
| preprocess train dataset: 100%|████████████████████████████████████████████████████████| 66/66 [00:00<00:00, 344.26ex/s] | |
| preprocess train dataset: 100%|████████████████████████████████████████████████████████| 69/69 [00:00<00:00, 348.17ex/s] | |
| 100%|█████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 25.07ba/s] | |
| 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 1008.49ba/s] | |
| 100%|███████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 1090.00ba/s] | |
| 100%|████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 682.44ba/s] | |
| 100%|████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 777.44ba/s] | |
| 100%|████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 695.92ba/s] | |
| 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 17:43:20.362548: 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 17:43:20.362582: W tensorflow/stream_executor/cuda/cuda_driver.cc:269] failed call to cuInit: UNKNOWN ERROR (303) | |
| Epoch ... (1/34): 0%| | 0/34 [00:00<?, ?it/s] | |
| Training...: 0%| | 0/2 [00:00<?, ?it/s] | |
| 05/07/2022 17:43:20 - INFO - __main__ - ***** Running training ***** | |
| 05/07/2022 17:43:20 - INFO - __main__ - Num examples = 68 | |
| 05/07/2022 17:43:20 - INFO - __main__ - Num Epochs = 34 | |
| 05/07/2022 17:43:20 - INFO - __main__ - Instantaneous batch size per device = 4 | |
| 05/07/2022 17:43:20 - INFO - __main__ - Num gradient accumulation steps = 1 | |
| 05/07/2022 17:43:20 - INFO - __main__ - Total train batch size (w. parallel & distributed) = 32 | |
| 05/07/2022 17:43:20 - INFO - __main__ - Total optimization steps = 68 | |
| 05/07/2022 17:43:20 - INFO - __main__ - Gradient checkpointing: False | |
| 05/07/2022 17:43:20 - INFO - __main__ - Use scan: True | |
| Training...: 50%|████████████████████████████████████ | 1/2 [00:24<00:24, 24.75s/it] | |
| Step... (1 | Loss: 6.909794330596924, Learning Rate: 6.00004568696022e-07, Gradient Norm: 0.20182259380817413) | |
| Epoch ... (1/34): 3%|█▉ | 1/34 [00:51<27:25, 49.86s/it] | |
| Training...: 50%|████████████████████████████████████ | 1/2 [00:01<00:01, 1.34s/it] | |
| Step... (3 | Loss: 6.905749797821045, Learning Rate: 1.7999846022576094e-06, Gradient Norm: 0.21621592342853546) | |
| Epoch ... (1/34): 6%|███▉ | 2/34 [00:53<11:43, 21.99s/it] | |
| Training...: 50%|████████████████████████████████████ | 1/2 [00:01<00:01, 1.22s/it] | |
| Training...: 50%|████████████████████████████████████ | 1/2 [00:02<00:01, 1.22s/it] | |
| Evaluating ...: 75%|███████████████████████████████████████████████████▊ | 3/4 [01:09<00:22, 22.82s/it] | |
| Epoch... (3/34 | Eval Loss: 6.906824588775635 | Eval wer: 1.603448275862069 |) | |
| Epoch... (3/34 | Eval Loss: 6.906824588775635 | Eval wer: 1.603448275862069 |): 9%|▎ | 3/34 [02:06<23:19, 45.13s/it] | |
| Training...: 50%|████████████████████████████████████ | 1/2 [00:01<00:01, 1.16s/it] | |
| Epoch... (3/34 | Eval Loss: 6.906824588775635 | Eval wer: 1.603448275862069 |): 12%|▍ | 4/34 [02:07<14:07, 28.25s/it] | |
| Training...: 0%| | 0/2 [00:00<?, ?it/s] | |
| Step... (8 | Loss: 6.909614086151123, Learning Rate: 4.799978341907263e-06, Gradient Norm: 0.2112041562795639) | |
| Epoch... (3/34 | Eval Loss: 6.906824588775635 | Eval wer: 1.603448275862069 |): 15%|▌ | 5/34 [02:11<09:08, 18.93s/it] | |
| Training...: 0%| | 0/2 [00:01<?, ?it/s] | |
| Step... (10 | Loss: 6.907970905303955, Learning Rate: 5.999987479299307e-06, Gradient Norm: 0.20816193521022797) | |
| Evaluating ...: 50%|██████████████████████████████████▌ | 2/4 [00:01<00:01, 1.75it/s] | |
| Epoch... (6/34 | Eval Loss: 6.906639575958252 | Eval wer: 1.603448275862069 |) | |
| Model weights saved in /home/sanchitgandhi/flax-wav2vec2-2-bart-dummy/flax_model.msgpack | 0/2 [00:03<?, ?it/s] | |
| tokenizer config file saved in ./tokenizer_config.json | |
| Special tokens file saved in ./special_tokens_map.json | |
| Training...: 50%|████████████████████████████████████ | 1/2 [00:03<00:03, 3.85s/it] | |
| Step... (11 | Loss: 6.910458087921143, Learning Rate: 6.599992047995329e-06, Gradient Norm: 0.22143037617206573) | |
| Epoch... (6/34 | Eval Loss: 6.906639575958252 | Eval wer: 1.603448275862069 |): 18%|▋ | 6/34 [02:15<06:37, 14.19s/it] | |
| Training...: 50%|████████████████████████████████████ | 1/2 [00:01<00:01, 1.18s/it] | |
| Step... (13 | Loss: 6.905548572540283, Learning Rate: 7.800001185387373e-06, Gradient Norm: 0.2015129178762436) | |
| Epoch... (6/34 | Eval Loss: 6.906639575958252 | Eval wer: 1.603448275862069 |): 21%|▊ | 7/34 [02:18<04:39, 10.34s/it] | |
| Training...: 50%|████████████████████████████████████ | 1/2 [00:01<00:01, 1.17s/it] | |
| Training...: 50%|████████████████████████████████████ | 1/2 [00:02<00:01, 1.17s/it] | |
| Evaluating ...: 50%|██████████████████████████████████▌ | 2/4 [00:01<00:01, 1.77it/s] | |
| Epoch... (8/34 | Eval Loss: 6.906340599060059 | Eval wer: 1.603448275862069 |): 24%|▉ | 8/34 [02:22<03:43, 8.61s/it] | |
| Training...: 0%| | 0/2 [00:00<?, ?it/s] | |
| Step... (16 | Loss: 6.909521579742432, Learning Rate: 9.600014891475439e-06, Gradient Norm: 0.19841279089450836) | |
| Epoch... (8/34 | Eval Loss: 6.906340599060059 | Eval wer: 1.603448275862069 |): 26%|█ | 9/34 [02:24<02:46, 6.67s/it] | |
| Training...: 0%| | 0/2 [00:00<?, ?it/s] | |
| Step... (18 | Loss: 6.905771255493164, Learning Rate: 1.0799994925037026e-05, Gradient Norm: 0.20174430310726166) | |
| Epoch... (8/34 | Eval Loss: 6.906340599060059 | Eval wer: 1.603448275862069 |): 29%|▉ | 10/34 [02:26<02:08, 5.35s/it] | |
| Training...: 0%| | 0/2 [00:00<?, ?it/s] | |
| Training...: 0%| | 0/2 [00:01<?, ?it/s] | |
| Evaluating ...: 50%|██████████████████████████████████▌ | 2/4 [00:01<00:01, 1.82it/s] | |
| Epoch... (11/34 | Eval Loss: 6.905916213989258 | Eval wer: 1.603448275862069 |) | |
| Model weights saved in /home/sanchitgandhi/flax-wav2vec2-2-bart-dummy/flax_model.msgpack | 0/2 [00:03<?, ?it/s] | |
| tokenizer config file saved in ./tokenizer_config.json | |
| Special tokens file saved in ./special_tokens_map.json | |
| Training...: 50%|████████████████████████████████████ | 1/2 [00:03<00:03, 3.58s/it] | |
| Step... (21 | Loss: 6.905186176300049, Learning Rate: 1.2600008631125093e-05, Gradient Norm: 0.21243052184581757) | |
| Epoch... (11/34 | Eval Loss: 6.905916213989258 | Eval wer: 1.603448275862069 |): 32%|▋ | 11/34 [02:33<01:59, 5.19s/it] | |
| Training...: 50%|████████████████████████████████████ | 1/2 [00:01<00:01, 1.33s/it] | |
| Step... (23 | Loss: 6.9039998054504395, Learning Rate: 1.379998866468668e-05, Gradient Norm: 0.2145574390888214) | |
| Epoch... (11/34 | Eval Loss: 6.905916213989258 | Eval wer: 1.603448275862069 |): 35%|▋ | 12/34 [02:35<01:36, 4.37s/it] | |
| Training...: 50%|████████████████████████████████████ | 1/2 [00:01<00:01, 1.24s/it] | |
| Training...: 50%|████████████████████████████████████ | 1/2 [00:02<00:01, 1.24s/it] | |
| Evaluating ...: 25%|█████████████████▎ | 1/4 [00:00<00:02, 1.37it/s] | |
| Epoch... (13/34 | Eval Loss: 6.905399322509766 | Eval wer: 1.603448275862069 |): 38%|▊ | 13/34 [02:39<01:35, 4.56s/it] | |
| Training...: 0%| | 0/2 [00:00<?, ?it/s] | |
| Step... (26 | Loss: 6.909581184387207, Learning Rate: 1.5600002370774746e-05, Gradient Norm: 0.22509345412254333) | |
| Epoch... (13/34 | Eval Loss: 6.905399322509766 | Eval wer: 1.603448275862069 |): 41%|▊ | 14/34 [02:41<01:18, 3.90s/it] | |
| Training...: 0%| | 0/2 [00:00<?, ?it/s] | |
| Training...: 50%|████████████████████████████████████ | 1/2 [00:01<00:01, 1.21s/it] | |
| Step... (29 | Loss: 6.907866477966309, Learning Rate: 1.7400016076862812e-05, Gradient Norm: 0.20910179615020752) | |
| Epoch... (13/34 | Eval Loss: 6.905399322509766 | Eval wer: 1.603448275862069 |): 44%|▉ | 15/34 [02:45<01:05, 3.45s/it] | |
| Training...: 0%| | 0/2 [00:01<?, ?it/s] | |
| Model weights saved in /home/sanchitgandhi/flax-wav2vec2-2-bart-dummy/flax_model.msgpack | 0/2 [00:03<?, ?it/s] | |
| tokenizer config file saved in ./tokenizer_config.json | |
| Special tokens file saved in ./special_tokens_map.json | |
| Training...: 50%|████████████████████████████████████ | 1/2 [00:03<00:03, 3.71s/it] | |
| Epoch... (16/34 | Eval Loss: 6.904772758483887 | Eval wer: 1.603448275862069 |) | |
| 05/07/2022 17:46:08 - INFO - __main__ - Saving checkpoint... | |
| Step... (31 | Loss: 6.901575565338135, Learning Rate: 1.85999961104244e-05, Gradient Norm: 0.21939419209957123) | |
| Epoch... (16/34 | Eval Loss: 6.904772758483887 | Eval wer: 1.603448275862069 |): 47%|▉ | 16/34 [03:11<03:05, 10.31s/it] | |
| Training...: 50%|████████████████████████████████████ | 1/2 [00:01<00:01, 1.33s/it] | |
| Epoch... (16/34 | Eval Loss: 6.904772758483887 | Eval wer: 1.603448275862069 |): 50%|█ | 17/34 [03:13<02:15, 7.95s/it] | |
| Training...: 50%|████████████████████████████████████ | 1/2 [00:01<00:01, 1.22s/it] | |
| Step... (34 | Loss: 6.906285762786865, Learning Rate: 2.0400009816512465e-05, Gradient Norm: 0.2121836245059967) | |
| Training...: 50%|████████████████████████████████████ | 1/2 [00:02<00:01, 1.22s/it] | |
| Evaluating ...: 25%|█████████████████▎ | 1/4 [00:00<00:02, 1.32it/s] | |
| Epoch... (18/34 | Eval Loss: 6.904001712799072 | Eval wer: 1.603448275862069 |): 53%|█ | 18/34 [03:17<01:53, 7.08s/it] | |
| Training...: 0%| | 0/2 [00:00<?, ?it/s] | |
| Epoch... (18/34 | Eval Loss: 6.904001712799072 | Eval wer: 1.603448275862069 |): 56%|█ | 19/34 [03:20<01:25, 5.67s/it] | |
| Training...: 0%| | 0/2 [00:00<?, ?it/s] | |
| Step... (37 | Loss: 6.903077125549316, Learning Rate: 2.2199994418770075e-05, Gradient Norm: 0.20692755281925201) | |
| Epoch... (18/34 | Eval Loss: 6.904001712799072 | Eval wer: 1.603448275862069 |): 59%|█▏| 20/34 [03:22<01:05, 4.69s/it] | |
| Step... (39 | Loss: 6.90248966217041, Learning Rate: 2.340000355616212e-05, Gradient Norm: 0.21785803139209747) | |
| Epoch... (18/34 | Eval Loss: 6.904001712799072 | Eval wer: 1.603448275862069 |): 59%|█▏| 20/34 [03:23<01:05, 4.69s/it] | |
| Training...: 0%| | 0/2 [00:01<?, ?it/s] | |
| Evaluating ...: 25%|█████████████████▎ | 1/4 [00:00<00:02, 1.37it/s] | |
| Training...: 0%| | 0/2 [00:03<?, ?it/s] | |
| 05/07/2022 17:46:47 - INFO - __main__ - Saving checkpoint... | |
| Model weights saved in /home/sanchitgandhi/flax-wav2vec2-2-bart-dummy/flax_model.msgpack | 0/2 [00:03<?, ?it/s] | |
| tokenizer config file saved in ./tokenizer_config.json | |
| Special tokens file saved in ./special_tokens_map.json | |
| Training...: 100%|████████████████████████████████████████████████████████████████████████| 2/2 [00:05<00:00, 2.59s/it] | |
| Epoch... (21/34 | Eval Loss: 6.903112411499023 | Eval wer: 1.603448275862069 |): 62%|█▏| 21/34 [03:27<01:02, 4.83s/it] | |
| Training...: 0%| | 0/2 [00:00<?, ?it/s] | |
| Step... (42 | Loss: 6.902524471282959, Learning Rate: 2.5199988158419728e-05, Gradient Norm: 0.2166411280632019) | |
| Epoch... (21/34 | Eval Loss: 6.903112411499023 | Eval wer: 1.603448275862069 |): 65%|█▎| 22/34 [03:30<00:49, 4.11s/it] | |
| Training...: 0%| | 0/2 [00:00<?, ?it/s] | |
| Training...: 50%|████████████████████████████████████ | 1/2 [00:01<00:01, 1.35s/it] | |
| Training...: 50%|████████████████████████████████████ | 1/2 [00:02<00:01, 1.35s/it] | |
| Evaluating ...: 75%|███████████████████████████████████████████████████▊ | 3/4 [00:01<00:00, 1.78it/s] | |
| Epoch... (23/34 | Eval Loss: 6.902121543884277 | Eval wer: 1.603448275862069 |): 68%|█▎| 23/34 [03:36<00:48, 4.37s/it] | |
| Training...: 50%|████████████████████████████████████ | 1/2 [00:01<00:01, 1.22s/it] | |
| Step... (46 | Loss: 6.909830570220947, Learning Rate: 2.7600006433203816e-05, Gradient Norm: 0.20912756025791168) | |
| Epoch... (23/34 | Eval Loss: 6.902121543884277 | Eval wer: 1.603448275862069 |): 71%|█▍| 24/34 [03:38<00:37, 3.77s/it] | |
| Training...: 50%|████████████████████████████████████ | 1/2 [00:01<00:01, 1.16s/it] | |
| Step... (48 | Loss: 6.901593208312988, Learning Rate: 2.880001557059586e-05, Gradient Norm: 0.22144821286201477) | |
| Epoch... (23/34 | Eval Loss: 6.902121543884277 | Eval wer: 1.603448275862069 |): 74%|█▍| 25/34 [03:39<00:30, 3.34s/it] | |
| Training...: 0%| | 0/2 [00:00<?, ?it/s] | |
| Training...: 0%| | 0/2 [00:01<?, ?it/s] | |
| Evaluating ...: 75%|███████████████████████████████████████████████████▊ | 3/4 [00:01<00:00, 1.75it/s] | |
| Epoch... (26/34 | Eval Loss: 6.900992393493652 | Eval wer: 1.2724137931034483 |) | |
| Model weights saved in /home/sanchitgandhi/flax-wav2vec2-2-bart-dummy/flax_model.msgpack | 0/2 [00:03<?, ?it/s] | |
| tokenizer config file saved in ./tokenizer_config.json | |
| Special tokens file saved in ./special_tokens_map.json | |
| Training...: 100%|████████████████████████████████████████████████████████████████████████| 2/2 [00:04<00:00, 2.42s/it] | |
| Epoch... (26/34 | Eval Loss: 6.900992393493652 | Eval wer: 1.2724137931034483 |): 76%|▊| 26/34 [03:44<00:30, 3.79s/it] | |
| Training...: 0%| | 0/2 [00:00<?, ?it/s] | |
| Step... (51 | Loss: 6.9044108390808105, Learning Rate: 3.060000017285347e-05, Gradient Norm: 0.22064745426177979) | |
| Training...: 50%|████████████████████████████████████ | 1/2 [00:01<00:01, 1.23s/it] | |
| Step... (53 | Loss: 6.9063873291015625, Learning Rate: 3.1800009310245514e-05, Gradient Norm: 0.2018101066350937) | |
| Epoch... (26/34 | Eval Loss: 6.900992393493652 | Eval wer: 1.2724137931034483 |): 79%|▊| 27/34 [03:48<00:23, 3.39s/it] | |
| Training...: 50%|████████████████████████████████████ | 1/2 [00:01<00:01, 1.23s/it] | |
| Training...: 50%|████████████████████████████████████ | 1/2 [00:02<00:01, 1.23s/it] | |
| Evaluating ...: 50%|██████████████████████████████████▌ | 2/4 [00:01<00:01, 1.82it/s] | |
| Epoch... (28/34 | Eval Loss: 6.899757385253906 | Eval wer: 1.2724137931034483 |): 82%|▊| 28/34 [03:53<00:22, 3.82s/it] | |
| Training...: 50%|████████████████████████████████████ | 1/2 [00:01<00:01, 1.21s/it] | |
| Step... (56 | Loss: 6.906337261199951, Learning Rate: 3.359999391250312e-05, Gradient Norm: 0.21085792779922485) | |
| Epoch... (28/34 | Eval Loss: 6.899757385253906 | Eval wer: 1.2724137931034483 |): 85%|▊| 29/34 [03:54<00:16, 3.39s/it] | |
| Training...: 0%| | 0/2 [00:00<?, ?it/s] | |
| Step... (58 | Loss: 6.89849853515625, Learning Rate: 3.480000304989517e-05, Gradient Norm: 0.2046382576227188) | |
| Epoch... (28/34 | Eval Loss: 6.899757385253906 | Eval wer: 1.2724137931034483 |): 88%|▉| 30/34 [03:56<00:12, 3.09s/it] | |
| Training...: 0%| | 0/2 [00:00<?, ?it/s] | |
| Training...: 0%| | 0/2 [00:01<?, ?it/s] | |
| Evaluating ...: 25%|█████████████████▎ | 1/4 [00:00<00:02, 1.40it/s] | |
| Epoch... (31/34 | Eval Loss: 6.898369312286377 | Eval wer: 1.2724137931034483 |) | |
| Model weights saved in /home/sanchitgandhi/flax-wav2vec2-2-bart-dummy/flax_model.msgpack | 0/2 [00:03<?, ?it/s] | |
| tokenizer config file saved in ./tokenizer_config.json | |
| Special tokens file saved in ./special_tokens_map.json | |
| Training...: 50%|████████████████████████████████████ | 1/2 [00:03<00:03, 3.75s/it] | |
| Step... (61 | Loss: 6.899321556091309, Learning Rate: 3.659998765215278e-05, Gradient Norm: 0.21138229966163635) | |
| Epoch... (31/34 | Eval Loss: 6.898369312286377 | Eval wer: 1.2724137931034483 |): 91%|▉| 31/34 [04:02<00:10, 3.64s/it] | |
| Training...: 50%|████████████████████████████████████ | 1/2 [00:01<00:01, 1.21s/it] | |
| Epoch... (31/34 | Eval Loss: 6.898369312286377 | Eval wer: 1.2724137931034483 |): 94%|▉| 32/34 [04:05<00:06, 3.27s/it] | |
| Training...: 50%|████████████████████████████████████ | 1/2 [00:01<00:01, 1.24s/it] | |
| Step... (64 | Loss: 6.900187015533447, Learning Rate: 3.840000135824084e-05, Gradient Norm: 0.21020692586898804) | |
| Training...: 50%|████████████████████████████████████ | 1/2 [00:02<00:01, 1.24s/it] | |
| Evaluating ...: 25%|█████████████████▎ | 1/4 [00:00<00:02, 1.34it/s] | |
| Training...: 50%|████████████████████████████████████ | 1/2 [00:04<00:01, 1.24s/it] | |
| Epoch... (33/34 | Eval Loss: 6.896849155426025 | Eval wer: 1.3195402298850574 |): 97%|▉| 33/34 [04:10<00:03, 3.97s/it] | |
| Training...: 50%|████████████████████████████████████ | 1/2 [00:01<00:01, 1.17s/it] | |
| Epoch... (33/34 | Eval Loss: 6.896849155426025 | Eval wer: 1.3195402298850574 |): 100%|█| 34/34 [04:12<00:00, 7.41s/it] | |
| Predicting validation[:90%]...: 67%|███████████████████████████████████▎ | 2/3 [00:26<00:13, 13.16s/it] | |
| Predicting validation[:90%]...: 100%|█████████████████████████████████████████████████████| 3/3 [00:40<00:00, 13.30s/it] | |
| Predicting validation[:95%]...: 50%|██████████████████████████▌ | 2/4 [00:01<00:01, 1.81it/s] | |
| Predicting validation[:95%]...: 100%|█████████████████████████████████████████████████████| 4/4 [00:02<00:00, 1.81it/s] |