/home/sanchitgandhi/hf/lib/python3.8/site-packages/chex/_src/pytypes.py:37: FutureWarning: jax.tree_structure is deprecated, and will be removed in a future release. Use jax.tree_util.tree_structure instead. PyTreeDef = type(jax.tree_structure(None)) wandb: Currently logged in as: sanchit-gandhi. Use `wandb login --relogin` to force relogin wandb: wandb version 0.13.2 is available! To upgrade, please run: wandb: $ pip install wandb --upgrade wandb: Tracking run with wandb version 0.12.18 wandb: Run data is saved locally in /home/sanchitgandhi/train-flax-wav2vec2-2-bart-large-voxpopuli-black-box/wandb/run-20220908_090454-q13mjl8e wandb: Run `wandb offline` to turn off syncing. wandb: Syncing run flax-wav2vec2-2-bart-large-voxpopuli-black-box wandb: ⭐️ View project at https://wandb.ai/sanchit-gandhi/voxpopuli wandb: 🚀 View run at https://wandb.ai/sanchit-gandhi/voxpopuli/runs/q13mjl8e INFO:__main__:Training/evaluation parameters FlaxSeq2SeqTrainingArguments( _n_gpu=-1, adafactor=False, adam_beta1=0.9, adam_beta2=0.999, adam_epsilon=1e-08, auto_find_batch_size=False, 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=10000, evaluation_strategy=no, final_generation_max_length=200, final_generation_num_beams=5, fp16=False, fp16_backend=auto, fp16_full_eval=False, fp16_opt_level=O1, fsdp=, fsdp_min_num_params=0, fsdp_transformer_layer_cls_to_wrap=None, full_determinism=False, generation_length_penalty=1.2, generation_max_length=200, generation_num_beams=5, gradient_accumulation_steps=1, gradient_checkpointing=True, greater_is_better=None, group_by_length=False, half_precision_backend=auto, hub_model_id=None, hub_private_repo=False, hub_strategy=every_save, hub_token=, ignore_data_skip=False, include_inputs_for_metrics=False, jit_mode_eval=False, label_names=None, label_smoothing_factor=0.0, learning_rate=0.0001, length_column_name=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=25, logging_strategy=steps, lr_scheduler_type=linear, matmul_precision=default, max_grad_norm=1.0, max_steps=50000, metric_for_best_model=None, mp_parameters=, no_cuda=False, num_train_epochs=3.0, optim=adamw_hf, output_dir=./flax-wav2vec2-2-bart-large-voxpopuli-black-box, overwrite_output_dir=True, past_index=-1, per_device_eval_batch_size=1, per_device_train_batch_size=8, 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=, ray_scope=last, remove_unused_columns=True, report_to=None, resume_from_checkpoint=None, run_name=None, save_on_each_node=False, save_steps=10000, save_strategy=steps, save_total_limit=None, seed=42, sharded_ddp=, skip_memory_metrics=True, sortish_sampler=False, tf32=None, torchdynamo=None, tpu_metrics_debug=False, tpu_num_cores=None, use_ipex=False, use_legacy_prediction_loop=False, warmup_ratio=0.0, warmup_steps=500, weight_decay=0.0, xpu_backend=None, ) INFO:__main__:JAX devices: 8, matmul precision: default WARNING:datasets.builder:Reusing dataset voxpopuli (/home/sanchitgandhi/cache/huggingface/datasets/polinaeterna___voxpopuli/en/1.3.0/8b39f6ff8dd8ced6def21f53eb18fbfd9701047d67b6c9da17f47f36ebedb4f8) WARNING:datasets.builder:Reusing dataset voxpopuli (/home/sanchitgandhi/cache/huggingface/datasets/polinaeterna___voxpopuli/en/1.3.0/8b39f6ff8dd8ced6def21f53eb18fbfd9701047d67b6c9da17f47f36ebedb4f8) WARNING:datasets.builder:Reusing dataset voxpopuli (/home/sanchitgandhi/cache/huggingface/datasets/polinaeterna___voxpopuli/en/1.3.0/8b39f6ff8dd8ced6def21f53eb18fbfd9701047d67b6c9da17f47f36ebedb4f8) loading configuration file https://huggingface.co/sanchit-gandhi/flax-wav2vec2-2-bart-large-scan/resolve/main/config.json from cache at /home/sanchitgandhi/.cache/huggingface/transformers/e6d3af8a2b6624d8adf8fc289717c121400164223b3e51d49b639aa34d1d3048.c9a58c9120361b7b034a0136cc74d5dce009e745c4cc111c255d5f3d0a9e2fd9 /home/sanchitgandhi/transformers/src/transformers/configuration_utils.py:368: UserWarning: Passing `gradient_checkpointing` to a config initialization is deprecated and will be removed in v5 Transformers. Using `model.gradient_checkpointing_enable()` instead, or if you are using the `Trainer` API, pass `gradient_checkpointing=True` in your `TrainingArguments`. warnings.warn( Model config SpeechEncoderDecoderConfig { "_name_or_path": "sanchit-gandhi/flax-wav2vec2-2-bart-large-scan", "architectures": [ "SpeechEncoderDecoderModel" ], "decoder": { "_name_or_path": "", "activation_dropout": 0.1, "activation_function": "gelu", "add_bias_logits": false, "add_cross_attention": true, "add_final_layer_norm": false, "architectures": [ "BartModel" ], "attention_dropout": 0.1, "bad_words_ids": null, "bos_token_id": 0, "chunk_size_feed_forward": 0, "classif_dropout": 0.1, "classifier_dropout": 0.0, "cross_attention_hidden_size": null, "d_model": 1024, "decoder_attention_heads": 16, "decoder_ffn_dim": 4096, "decoder_layerdrop": 0.0, "decoder_layers": 12, "decoder_start_token_id": 2, "diversity_penalty": 0.0, "do_sample": false, "dropout": 0.1, "early_stopping": true, "encoder_attention_heads": 16, "encoder_ffn_dim": 4096, "encoder_layerdrop": 0.0, "encoder_layers": 12, "encoder_no_repeat_ngram_size": 0, "eos_token_id": 2, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": 0, "forced_eos_token_id": 2, "fuse_matmuls": false, "gradient_checkpointing": true, "id2label": { "0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2" }, "init_std": 0.02, "is_decoder": true, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1, "LABEL_2": 2 }, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 1024, "min_length": 0, "model_type": "bart", "no_repeat_ngram_size": 3, "normalize_before": false, "num_beam_groups": 1, "num_beams": 4, "num_hidden_layers": 12, "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": { "summarization": { "length_penalty": 1.0, "max_length": 128, "min_length": 12, "num_beams": 4 }, "summarization_cnn": { "length_penalty": 2.0, "max_length": 142, "min_length": 56, "num_beams": 4 }, "summarization_xsum": { "length_penalty": 1.0, "max_length": 62, "min_length": 11, "num_beams": 6 } }, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "float32", "torchscript": false, "transformers_version": "4.21.0.dev0", "typical_p": 1.0, "use_bfloat16": false, "use_cache": true, "use_scan": true, "vocab_size": 50265 }, "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": [ "Wav2Vec2ForPreTraining" ], "attention_dropout": 0.1, "bad_words_ids": null, "bos_token_id": 1, "chunk_size_feed_forward": 0, "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 ], "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": true, "hidden_act": "gelu", "hidden_dropout": 0.1, "hidden_dropout_prob": 0.1, "hidden_size": 1024, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 4096, "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": 16, "num_beam_groups": 1, "num_beams": 1, "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, "num_return_sequences": 1, "output_attentions": false, "output_hidden_size": 1024, "output_hidden_states": false, "output_scores": false, "pad_token_id": 0, "prefix": null, "problem_type": null, "proj_codevector_dim": 768, "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, "tf_legacy_loss": false, "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": "4.21.0.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 https://huggingface.co/sanchit-gandhi/flax-wav2vec2-2-bart-large-scan/resolve/main/preprocessor_config.json from cache at /home/sanchitgandhi/.cache/huggingface/transformers/bc2232c616201c7d3d66ba3f6a7d1186306134838dfb19786149f0e16122787d.bbc1eb890a39c82e710a893223b8452ac5b78e8b57083b2f893aa7dc59d4ed69 Feature extractor Wav2Vec2FeatureExtractor { "do_normalize": true, "feature_extractor_type": "Wav2Vec2FeatureExtractor", "feature_size": 1, "padding_side": "right", "padding_value": 0.0, "return_attention_mask": true, "sampling_rate": 16000 } loading file https://huggingface.co/sanchit-gandhi/flax-wav2vec2-2-bart-large-scan/resolve/main/vocab.json from cache at /home/sanchitgandhi/.cache/huggingface/transformers/86c0de13925d1534934e540ff4c9dd778f49761b4eaf59dae3335a4f6690a814.bfdcc444ff249bca1a95ca170ec350b442f81804d7df3a95a2252217574121d7 loading file https://huggingface.co/sanchit-gandhi/flax-wav2vec2-2-bart-large-scan/resolve/main/merges.txt from cache at /home/sanchitgandhi/.cache/huggingface/transformers/7cf4fc91891684e1177d1c519689e4c310ebdec965e00d6e45134bb9227ab01b.f5b91da9e34259b8f4d88dbc97c740667a0e8430b96314460cdb04e86d4fc435 loading file https://huggingface.co/sanchit-gandhi/flax-wav2vec2-2-bart-large-scan/resolve/main/tokenizer.json from cache at /home/sanchitgandhi/.cache/huggingface/transformers/c02f3f3009bfacaa24cfead1d0f7fbf4fc2fb5f8092f68703449f02aa3a28e03.393fa6a095aa312a3cce4d5263e471bd94ec0215e6c63448a6464d59ff900814 loading file https://huggingface.co/sanchit-gandhi/flax-wav2vec2-2-bart-large-scan/resolve/main/added_tokens.json from cache at None loading file https://huggingface.co/sanchit-gandhi/flax-wav2vec2-2-bart-large-scan/resolve/main/special_tokens_map.json from cache at /home/sanchitgandhi/.cache/huggingface/transformers/505d61b8f6e05764b5aec1483bfdd13a310681a5af54957263604323be3bbabf.a11ebb04664c067c8fe5ef8f8068b0f721263414a26058692f7b2e4ba2a1b342 loading file https://huggingface.co/sanchit-gandhi/flax-wav2vec2-2-bart-large-scan/resolve/main/tokenizer_config.json from cache at /home/sanchitgandhi/.cache/huggingface/transformers/ff79c23164eac352d7f9651f3c3774a962ce80f81460d9e17d689235fa34ee80.0e8b2b497f91e23302894a5c1f19ced6334b0abd450a7bce75a67bf0f9ee5c54 loading weights file https://huggingface.co/sanchit-gandhi/flax-wav2vec2-2-bart-large-scan/resolve/main/flax_model.msgpack from cache at /home/sanchitgandhi/.cache/huggingface/transformers/1279dc21f7dd9ed546f166e7e445e068b2672ddfa5386b2e3a3a973b8d668365.8e03496bb6919447aeb468483249e7b65dfb59c42989be9787af0aa6aa9b3f50 tcmalloc: large alloc 2353618944 bytes == 0xa19b0000 @ 0x7f0edf2a6680 0x7f0edf2c7824 0x5fb391 0x64be71 0x5c6366 0x4f3b9e 0x651588 0x505a63 0x56bbfa 0x569dba 0x50bca0 0x56cc1f 0x569dba 0x5f6eb3 0x56bacd 0x569dba 0x6902a7 0x67f951 0x67f9cf 0x67fa71 0x681b97 0x6b9d32 0x6ba0bd 0x7f0edf0b90b3 0x5fc5fe /home/sanchitgandhi/hf/lib/python3.8/site-packages/flax/core/lift.py:112: FutureWarning: jax.tree_flatten is deprecated, and will be removed in a future release. Use jax.tree_util.tree_flatten instead. scopes, treedef = jax.tree_flatten(scope_tree) /home/sanchitgandhi/hf/lib/python3.8/site-packages/flax/linen/transforms.py:249: FutureWarning: jax.tree_leaves is deprecated, and will be removed in a future release. Use jax.tree_util.tree_leaves instead. jax.tree_leaves(tree))) /home/sanchitgandhi/hf/lib/python3.8/site-packages/flax/core/lift.py:729: FutureWarning: jax.tree_leaves is deprecated, and will be removed in a future release. Use jax.tree_util.tree_leaves instead. lengths = set(jax.tree_leaves(lengths)) /home/sanchitgandhi/hf/lib/python3.8/site-packages/flax/core/axes_scan.py:134: FutureWarning: jax.tree_flatten is deprecated, and will be removed in a future release. Use jax.tree_util.tree_flatten instead. in_avals, in_tree = jax.tree_flatten(input_avals) /home/sanchitgandhi/hf/lib/python3.8/site-packages/flax/core/axes_scan.py:146: FutureWarning: jax.tree_unflatten is deprecated, and will be removed in a future release. Use jax.tree_util.tree_unflatten instead. broadcast_in, constants_out = jax.tree_unflatten(out_tree(), out_flat) All model checkpoint weights were used when initializing FlaxSpeechEncoderDecoderModel. All the weights of FlaxSpeechEncoderDecoderModel were initialized from the model checkpoint at sanchit-gandhi/flax-wav2vec2-2-bart-large-scan. 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. /home/sanchitgandhi/transformers/src/transformers/modeling_flax_utils.py:904: FutureWarning: jax.tree_map is deprecated, and will be removed in a future release. Use jax.tree_util.tree_map instead. param_dtypes = jax.tree_map(lambda x: x.dtype, state) WARNING:datasets.arrow_dataset:Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/polinaeterna___voxpopuli/en/1.3.0/8b39f6ff8dd8ced6def21f53eb18fbfd9701047d67b6c9da17f47f36ebedb4f8/cache-fb5fd5dfa8aea4e5.arrow WARNING:datasets.arrow_dataset:Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/polinaeterna___voxpopuli/en/1.3.0/8b39f6ff8dd8ced6def21f53eb18fbfd9701047d67b6c9da17f47f36ebedb4f8/cache-e2933449fdeea96a.arrow WARNING:datasets.arrow_dataset:Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/polinaeterna___voxpopuli/en/1.3.0/8b39f6ff8dd8ced6def21f53eb18fbfd9701047d67b6c9da17f47f36ebedb4f8/cache-ca0120d6c29116f1.arrow WARNING:datasets.arrow_dataset:Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/polinaeterna___voxpopuli/en/1.3.0/8b39f6ff8dd8ced6def21f53eb18fbfd9701047d67b6c9da17f47f36ebedb4f8/cache-8a5eb85627df79b1.arrow WARNING:datasets.arrow_dataset:Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/polinaeterna___voxpopuli/en/1.3.0/8b39f6ff8dd8ced6def21f53eb18fbfd9701047d67b6c9da17f47f36ebedb4f8/cache-4c39282db57ba962.arrow WARNING:datasets.arrow_dataset:Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/polinaeterna___voxpopuli/en/1.3.0/8b39f6ff8dd8ced6def21f53eb18fbfd9701047d67b6c9da17f47f36ebedb4f8/cache-f9a1acfe373833a8.arrow WARNING:datasets.arrow_dataset:Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/polinaeterna___voxpopuli/en/1.3.0/8b39f6ff8dd8ced6def21f53eb18fbfd9701047d67b6c9da17f47f36ebedb4f8/cache-424b904bf98fad64.arrow WARNING:datasets.arrow_dataset:Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/polinaeterna___voxpopuli/en/1.3.0/8b39f6ff8dd8ced6def21f53eb18fbfd9701047d67b6c9da17f47f36ebedb4f8/cache-f96755fa6046ca2e.arrow WARNING:datasets.arrow_dataset:Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/polinaeterna___voxpopuli/en/1.3.0/8b39f6ff8dd8ced6def21f53eb18fbfd9701047d67b6c9da17f47f36ebedb4f8/cache-580b2563a982c19b.arrow WARNING:datasets.arrow_dataset:Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/polinaeterna___voxpopuli/en/1.3.0/8b39f6ff8dd8ced6def21f53eb18fbfd9701047d67b6c9da17f47f36ebedb4f8/cache-9806a482376c6730.arrow WARNING:datasets.arrow_dataset:Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/polinaeterna___voxpopuli/en/1.3.0/8b39f6ff8dd8ced6def21f53eb18fbfd9701047d67b6c9da17f47f36ebedb4f8/cache-b270bba7252ddff9.arrow run_flax_speech_recognition_seq2seq.py:1052: FutureWarning: load_metric is deprecated and will be removed in the next major version of datasets. Use 'evaluate.load' instead, from the new library 🤗 Evaluate: https://huggingface.co/docs/evaluate wer_metric = load_metric("wer") Feature extractor saved in ./flax-wav2vec2-2-bart-large-voxpopuli-black-box/preprocessor_config.json tokenizer config file saved in ./flax-wav2vec2-2-bart-large-voxpopuli-black-box/tokenizer_config.json Special tokens file saved in ./flax-wav2vec2-2-bart-large-voxpopuli-black-box/special_tokens_map.json Configuration saved in ./flax-wav2vec2-2-bart-large-voxpopuli-black-box/config.json loading feature extractor configuration file ./flax-wav2vec2-2-bart-large-voxpopuli-black-box/preprocessor_config.json loading configuration file ./flax-wav2vec2-2-bart-large-voxpopuli-black-box/config.json /home/sanchitgandhi/transformers/src/transformers/configuration_utils.py:368: UserWarning: Passing `gradient_checkpointing` to a config initialization is deprecated and will be removed in v5 Transformers. Using `model.gradient_checkpointing_enable()` instead, or if you are using the `Trainer` API, pass `gradient_checkpointing=True` in your `TrainingArguments`. warnings.warn( Model config SpeechEncoderDecoderConfig { "_name_or_path": "./flax-wav2vec2-2-bart-large-voxpopuli-black-box", "architectures": [ "SpeechEncoderDecoderModel" ], "decoder": { "_name_or_path": "", "activation_dropout": 0.2, "activation_function": "gelu", "add_bias_logits": false, "add_cross_attention": true, "add_final_layer_norm": false, "architectures": [ "BartModel" ], "attention_dropout": 0.1, "bad_words_ids": null, "bos_token_id": 0, "chunk_size_feed_forward": 0, "classif_dropout": 0.1, "classifier_dropout": 0.0, "cross_attention_hidden_size": null, "d_model": 1024, "decoder_attention_heads": 16, "decoder_ffn_dim": 4096, "decoder_layerdrop": 0.0, "decoder_layers": 12, "decoder_start_token_id": 2, "diversity_penalty": 0.0, "do_sample": false, "dropout": 0.2, "early_stopping": true, "encoder_attention_heads": 16, "encoder_ffn_dim": 4096, "encoder_layerdrop": 0.0, "encoder_layers": 12, "encoder_no_repeat_ngram_size": 0, "eos_token_id": 2, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": 0, "forced_eos_token_id": 2, "fuse_matmuls": false, "gradient_checkpointing": true, "id2label": { "0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2" }, "init_std": 0.02, "is_decoder": true, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1, "LABEL_2": 2 }, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 1024, "min_length": 0, "model_type": "bart", "no_repeat_ngram_size": 3, "normalize_before": false, "num_beam_groups": 1, "num_beams": 4, "num_hidden_layers": 12, "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": { "summarization": { "length_penalty": 1.0, "max_length": 128, "min_length": 12, "num_beams": 4 }, "summarization_cnn": { "length_penalty": 2.0, "max_length": 142, "min_length": 56, "num_beams": 4 }, "summarization_xsum": { "length_penalty": 1.0, "max_length": 62, "min_length": 11, "num_beams": 6 } }, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "float32", "torchscript": false, "transformers_version": "4.21.0.dev0", "typical_p": 1.0, "use_bfloat16": false, "use_cache": true, "use_scan": true, "vocab_size": 50265 }, "decoder_start_token_id": 0, "encoder": { "_name_or_path": "", "activation_dropout": 0.2, "adapter_kernel_size": 3, "adapter_stride": 2, "add_adapter": true, "add_cross_attention": false, "apply_spec_augment": true, "architectures": [ "Wav2Vec2ForPreTraining" ], "attention_dropout": 0.1, "bad_words_ids": null, "bos_token_id": 1, "chunk_size_feed_forward": 0, "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 ], "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": 0.2, "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": true, "hidden_act": "gelu", "hidden_dropout": 0.2, "hidden_dropout_prob": 0.1, "hidden_size": 1024, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 4096, "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": 16, "num_beam_groups": 1, "num_beams": 1, "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, "num_return_sequences": 1, "output_attentions": false, "output_hidden_size": 1024, "output_hidden_states": false, "output_scores": false, "pad_token_id": 0, "prefix": null, "problem_type": null, "proj_codevector_dim": 768, "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, "tf_legacy_loss": false, "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": "4.21.0.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 ./flax-wav2vec2-2-bart-large-voxpopuli-black-box/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": true, "sampling_rate": 16000 } Didn't find file ./flax-wav2vec2-2-bart-large-voxpopuli-black-box/added_tokens.json. We won't load it. loading file ./flax-wav2vec2-2-bart-large-voxpopuli-black-box/vocab.json loading file ./flax-wav2vec2-2-bart-large-voxpopuli-black-box/merges.txt loading file ./flax-wav2vec2-2-bart-large-voxpopuli-black-box/tokenizer.json loading file None loading file ./flax-wav2vec2-2-bart-large-voxpopuli-black-box/special_tokens_map.json loading file ./flax-wav2vec2-2-bart-large-voxpopuli-black-box/tokenizer_config.json WARNING:__main__:Unable to display metrics through TensorBoard because the package is not installed: Please run `pip install tensorboard` to enable. /home/sanchitgandhi/train-flax-wav2vec2-2-bart-large-voxpopuli-black-box/./flax-wav2vec2-2-bart-large-voxpopuli-black-box is already a clone of https://huggingface.co/sanchit-gandhi/flax-wav2vec2-2-bart-large-voxpopuli-black-box. Make sure you pull the latest changes with `repo.git_pull()`. WARNING:huggingface_hub.repository:/home/sanchitgandhi/train-flax-wav2vec2-2-bart-large-voxpopuli-black-box/./flax-wav2vec2-2-bart-large-voxpopuli-black-box is already a clone of https://huggingface.co/sanchit-gandhi/flax-wav2vec2-2-bart-large-voxpopuli-black-box. Make sure you pull the latest changes with `repo.git_pull()`. run_flax_speech_recognition_seq2seq.py:336: FutureWarning: jax.tree_map is deprecated, and will be removed in a future release. Use jax.tree_util.tree_map instead. return jax.tree_map(lambda x: x.astype(jnp.float32) if x.dtype == jnp.bfloat16 else x, t) /home/sanchitgandhi/hf/lib/python3.8/site-packages/optax/_src/transform.py:319: FutureWarning: jax.tree_map is deprecated, and will be removed in a future release. Use jax.tree_util.tree_map instead. mu = jax.tree_map( # First moment /home/sanchitgandhi/hf/lib/python3.8/site-packages/optax/_src/transform.py:321: FutureWarning: jax.tree_map is deprecated, and will be removed in a future release. Use jax.tree_util.tree_map instead. nu = jax.tree_map(jnp.zeros_like, params) # Second moment INFO:__main__:***** Running training ***** INFO:__main__: Num examples = 167029 INFO:__main__: Num Epochs = 20 INFO:__main__: Instantaneous batch size per device = 8 INFO:__main__: Num gradient accumulation steps = 1 INFO:__main__: Total train batch size (w. parallel & distributed) = 64 INFO:__main__: Total optimization steps = 50000 INFO:__main__: Gradient checkpointing: True INFO:__main__: Use scan: True INFO:__main__: Fuse matmuls: False Epoch ... (1/20): 0% 0/20 [00:00