|
wandb: Currently logged in as: sanchit-gandhi (use `wandb login --relogin` to force relogin) |
|
wandb: wandb version 0.12.17 is available! To upgrade, please run: |
|
wandb: $ pip install wandb --upgrade |
|
wandb: Tracking run with wandb version 0.12.15 |
|
wandb: Run data is saved locally in /home/sanchitgandhi/flax-wav2vec2-2-bart-large-ls-960h-feature-encoder/wandb/run-20220530_175928-2nzi0chc |
|
wandb: Run `wandb offline` to turn off syncing. |
|
wandb: Syncing run flax-wav2vec2-2-bart-large-ls-960h-feature-encoder |
|
wandb: ⭐️ View project at https://wandb.ai/sanchit-gandhi/librispeech_960h |
|
wandb: 🚀 View run at https://wandb.ai/sanchit-gandhi/librispeech_960h/runs/2nzi0chc |
|
05/30/2022 17:59:29 - 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=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,
|
|
generation_length_penalty=1.2,
|
|
generation_max_length=40,
|
|
generation_num_beams=1,
|
|
gradient_accumulation_steps=2,
|
|
gradient_checkpointing=True,
|
|
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=0.0001,
|
|
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=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=./,
|
|
overwrite_output_dir=True,
|
|
past_index=-1,
|
|
per_device_eval_batch_size=4,
|
|
per_device_train_batch_size=4,
|
|
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=<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=10000,
|
|
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,
|
|
)
|
|
05/30/2022 17:59:29 - INFO - __main__ - JAX devices: 8, matmul precision: default
|
|
05/30/2022 17:59:30 - WARNING - datasets.builder - Reusing dataset librispeech_asr (/home/sanchitgandhi/cache/huggingface/datasets/librispeech_asr/all/2.1.0/14c8bffddb861b4b3a4fcdff648a56980dbb808f3fc56f5a3d56b18ee88458eb)
|
|
05/30/2022 17:59:30 - WARNING - datasets.builder - Reusing dataset librispeech_asr (/home/sanchitgandhi/cache/huggingface/datasets/librispeech_asr/all/2.1.0/14c8bffddb861b4b3a4fcdff648a56980dbb808f3fc56f5a3d56b18ee88458eb)
|
|
05/30/2022 17:59:30 - WARNING - datasets.builder - Reusing dataset librispeech_asr (/home/sanchitgandhi/cache/huggingface/datasets/librispeech_asr/all/2.1.0/14c8bffddb861b4b3a4fcdff648a56980dbb808f3fc56f5a3d56b18ee88458eb)
|
|
05/30/2022 17:59:31 - WARNING - datasets.builder - Reusing dataset librispeech_asr (/home/sanchitgandhi/cache/huggingface/datasets/librispeech_asr/all/2.1.0/14c8bffddb861b4b3a4fcdff648a56980dbb808f3fc56f5a3d56b18ee88458eb)
|
|
05/30/2022 17:59:31 - WARNING - datasets.builder - Reusing dataset librispeech_asr (/home/sanchitgandhi/cache/huggingface/datasets/librispeech_asr/all/2.1.0/14c8bffddb861b4b3a4fcdff648a56980dbb808f3fc56f5a3d56b18ee88458eb)
|
|
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:358: 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,
|
|
"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": "4.18.0.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,
|
|
"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 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 == 0xa2612000 @ 0x7fb1de660680 0x7fb1de681824 0x5f8a01 0x648cf1 0x5c4676 0x4f290e 0x64f718 0x5048b3 0x56b1da 0x56939a 0x50aaa0 0x56c28c 0x56939a 0x5f6a13 0x56b0ae 0x56939a 0x68d047 0x67e351 0x67e3cf 0x67e471 0x67e817 0x6b6fe2 0x6b736d 0x7fb1de4730b3 0x5fa5ce
|
|
/home/sanchitgandhi/hf/lib/python3.8/site-packages/jax/_src/tree_util.py:188: FutureWarning: jax.tree_util.tree_multimap() is deprecated. Please use jax.tree_util.tree_map() instead as a drop-in replacement.
|
|
warnings.warn('jax.tree_util.tree_multimap() is deprecated. Please use jax.tree_util.tree_map() '
|
|
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.
|
|
05/30/2022 18:00:06 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/librispeech_asr/all/2.1.0/14c8bffddb861b4b3a4fcdff648a56980dbb808f3fc56f5a3d56b18ee88458eb/cache-5bcd522a0f1116c8.arrow
|
|
05/30/2022 18:00:06 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/librispeech_asr/all/2.1.0/14c8bffddb861b4b3a4fcdff648a56980dbb808f3fc56f5a3d56b18ee88458eb/cache-148286b6e8c7c55a.arrow
|
|
05/30/2022 18:00:06 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/librispeech_asr/all/2.1.0/14c8bffddb861b4b3a4fcdff648a56980dbb808f3fc56f5a3d56b18ee88458eb/cache-6afe8daa3edc3979.arrow
|
|
05/30/2022 18:00:06 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/librispeech_asr/all/2.1.0/14c8bffddb861b4b3a4fcdff648a56980dbb808f3fc56f5a3d56b18ee88458eb/cache-fb71416814467da1.arrow
|
|
05/30/2022 18:00:06 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/librispeech_asr/all/2.1.0/14c8bffddb861b4b3a4fcdff648a56980dbb808f3fc56f5a3d56b18ee88458eb/cache-c4d90e72e7945373.arrow
|
|
05/30/2022 18:00:06 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/librispeech_asr/all/2.1.0/14c8bffddb861b4b3a4fcdff648a56980dbb808f3fc56f5a3d56b18ee88458eb/cache-1441a1a362f45f74.arrow
|
|
05/30/2022 18:00:06 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/librispeech_asr/all/2.1.0/14c8bffddb861b4b3a4fcdff648a56980dbb808f3fc56f5a3d56b18ee88458eb/cache-86716240f0d5e9ce.arrow
|
|
05/30/2022 18:00:06 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/librispeech_asr/all/2.1.0/14c8bffddb861b4b3a4fcdff648a56980dbb808f3fc56f5a3d56b18ee88458eb/cache-567649d38b4eb4b9.arrow
|
|
05/30/2022 18:00:06 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/librispeech_asr/all/2.1.0/14c8bffddb861b4b3a4fcdff648a56980dbb808f3fc56f5a3d56b18ee88458eb/cache-a0253d3135dc5a4b.arrow
|
|
05/30/2022 18:00:06 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/librispeech_asr/all/2.1.0/14c8bffddb861b4b3a4fcdff648a56980dbb808f3fc56f5a3d56b18ee88458eb/cache-90f3995b6106b9f2.arrow
|
|
05/30/2022 18:00:06 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/librispeech_asr/all/2.1.0/14c8bffddb861b4b3a4fcdff648a56980dbb808f3fc56f5a3d56b18ee88458eb/cache-c1105482a786c706.arrow
|
|
05/30/2022 18:00:06 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/librispeech_asr/all/2.1.0/14c8bffddb861b4b3a4fcdff648a56980dbb808f3fc56f5a3d56b18ee88458eb/cache-2c5d0ae89484568c.arrow
|
|
05/30/2022 18:00:06 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/librispeech_asr/all/2.1.0/14c8bffddb861b4b3a4fcdff648a56980dbb808f3fc56f5a3d56b18ee88458eb/cache-e43260f16a4667dc.arrow
|
|
05/30/2022 18:00:06 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/librispeech_asr/all/2.1.0/14c8bffddb861b4b3a4fcdff648a56980dbb808f3fc56f5a3d56b18ee88458eb/cache-d1485c81a0cbb06c.arrow
|
|
05/30/2022 18:00:06 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/librispeech_asr/all/2.1.0/14c8bffddb861b4b3a4fcdff648a56980dbb808f3fc56f5a3d56b18ee88458eb/cache-a791cf68d9739c69.arrow
|
|
05/30/2022 18:00:06 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/librispeech_asr/all/2.1.0/14c8bffddb861b4b3a4fcdff648a56980dbb808f3fc56f5a3d56b18ee88458eb/cache-94bc2d5136fdbae7.arrow
|
|
05/30/2022 18:00:06 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/librispeech_asr/all/2.1.0/14c8bffddb861b4b3a4fcdff648a56980dbb808f3fc56f5a3d56b18ee88458eb/cache-61413d2b04061247.arrow
|
|
05/30/2022 18:00:06 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/librispeech_asr/all/2.1.0/14c8bffddb861b4b3a4fcdff648a56980dbb808f3fc56f5a3d56b18ee88458eb/cache-5b531145a5727e3e.arrow
|
|
05/30/2022 18:00:06 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/librispeech_asr/all/2.1.0/14c8bffddb861b4b3a4fcdff648a56980dbb808f3fc56f5a3d56b18ee88458eb/cache-eef5cb2925240576.arrow
|
|
05/30/2022 18:00:06 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /home/sanchitgandhi/cache/huggingface/datasets/librispeech_asr/all/2.1.0/14c8bffddb861b4b3a4fcdff648a56980dbb808f3fc56f5a3d56b18ee88458eb/cache-dc7710d750f9cc97.arrow
|
|
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
|
|
Model config SpeechEncoderDecoderConfig {
|
|
"_name_or_path": "./",
|
|
"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,
|
|
"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": "4.18.0.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,
|
|
"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": true,
|
|
"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
|
|
05/30/2022 18:00:07 - WARNING - __main__ - Unable to display metrics through TensorBoard because the package is not installed: Please run `pip install tensorboard` to enable.
|
|
/home/sanchitgandhi/flax-wav2vec2-2-bart-large-ls-960h-feature-encoder/./ is already a clone of https://huggingface.co/sanchit-gandhi/flax-wav2vec2-2-bart-large-ls-960h-feature-encoder. Make sure you pull the latest changes with `repo.git_pull()`.
|
|
05/30/2022 18:00:11 - WARNING - huggingface_hub.repository - /home/sanchitgandhi/flax-wav2vec2-2-bart-large-ls-960h-feature-encoder/./ is already a clone of https://huggingface.co/sanchit-gandhi/flax-wav2vec2-2-bart-large-ls-960h-feature-encoder. Make sure you pull the latest changes with `repo.git_pull()`.
|
|
05/30/2022 18:00:14 - INFO - __main__ - ***** Running training *****
|
|
05/30/2022 18:00:14 - INFO - __main__ - Num examples = 281186
|
|
05/30/2022 18:00:14 - INFO - __main__ - Num Epochs = 12
|
|
05/30/2022 18:00:14 - INFO - __main__ - Instantaneous batch size per device = 4
|
|
05/30/2022 18:00:14 - INFO - __main__ - Num gradient accumulation steps = 2
|
|
05/30/2022 18:00:14 - INFO - __main__ - Total train batch size (w. parallel & distributed) = 64
|
|
05/30/2022 18:00:14 - INFO - __main__ - Total optimization steps = 50000
|
|
05/30/2022 18:00:14 - INFO - __main__ - Gradient checkpointing: True
|
|
05/30/2022 18:00:14 - INFO - __main__ - Use scan: True
|
|
05/30/2022 18:00:14 - INFO - __main__ - Fuse matmuls: False
|
|
Epoch ... (1/12): 0% 0/12 [00:00<?, ?it/s]
|
|
Training...: 0% 0/4393 [00:00<?, ?it/s][A
Training...: 0% 0/4393 [00:07<?, ?it/s]
|
|
Epoch ... (1/12): 0% 0/12 [00:15<?, ?it/s]
|
|
Traceback (most recent call last): |
|
File "run_flax_speech_recognition_seq2seq.py", line 1507, in <module> |
|
main() |
|
File "run_flax_speech_recognition_seq2seq.py", line 1400, in main |
|
state, train_metric = p_train_step(state, batch) |
|
File "/home/sanchitgandhi/hf/lib/python3.8/site-packages/jax/_src/traceback_util.py", line 162, in reraise_with_filtered_traceback |
|
return fun(*args, **kwargs) |
|
File "/home/sanchitgandhi/hf/lib/python3.8/site-packages/jax/_src/api.py", line 2013, in cache_miss |
|
out_tree, out_flat = f_pmapped_(*args, **kwargs) |
|
File "/home/sanchitgandhi/hf/lib/python3.8/site-packages/jax/_src/api.py", line 1889, in pmap_f |
|
out = pxla.xla_pmap( |
|
File "/home/sanchitgandhi/hf/lib/python3.8/site-packages/jax/core.py", line 1863, in bind |
|
return map_bind(self, fun, *args, **params) |
|
File "/home/sanchitgandhi/hf/lib/python3.8/site-packages/jax/core.py", line 1895, in map_bind |
|
outs = primitive.process(top_trace, fun, tracers, params) |
|
File "/home/sanchitgandhi/hf/lib/python3.8/site-packages/jax/core.py", line 1866, in process |
|
return trace.process_map(self, fun, tracers, params) |
|
File "/home/sanchitgandhi/hf/lib/python3.8/site-packages/jax/core.py", line 660, in process_call |
|
return primitive.impl(f, *tracers, **params) |
|
File "/home/sanchitgandhi/hf/lib/python3.8/site-packages/jax/interpreters/pxla.py", line 801, in xla_pmap_impl |
|
compiled_fun, fingerprint = parallel_callable( |
|
File "/home/sanchitgandhi/hf/lib/python3.8/site-packages/jax/linear_util.py", line 285, in memoized_fun |
|
ans = call(fun, *args) |
|
File "/home/sanchitgandhi/hf/lib/python3.8/site-packages/jax/interpreters/pxla.py", line 829, in parallel_callable |
|
pmap_computation = lower_parallel_callable( |
|
File "/home/sanchitgandhi/hf/lib/python3.8/site-packages/jax/_src/profiler.py", line 206, in wrapper |
|
return func(*args, **kwargs) |
|
File "/home/sanchitgandhi/hf/lib/python3.8/site-packages/jax/interpreters/pxla.py", line 1002, in lower_parallel_callable |
|
jaxpr, consts, replicas, parts, shards = stage_parallel_callable( |
|
File "/home/sanchitgandhi/hf/lib/python3.8/site-packages/jax/interpreters/pxla.py", line 909, in stage_parallel_callable |
|
jaxpr, out_sharded_avals, consts = pe.trace_to_jaxpr_final( |
|
File "/home/sanchitgandhi/hf/lib/python3.8/site-packages/jax/_src/profiler.py", line 206, in wrapper |
|
return func(*args, **kwargs) |
|
File "/home/sanchitgandhi/hf/lib/python3.8/site-packages/jax/interpreters/partial_eval.py", line 1844, in trace_to_jaxpr_final |
|
jaxpr, out_avals, consts = trace_to_subjaxpr_dynamic( |
|
File "/home/sanchitgandhi/hf/lib/python3.8/site-packages/jax/interpreters/partial_eval.py", line 1816, in trace_to_subjaxpr_dynamic |
|
ans = fun.call_wrapped(*in_tracers_) |
|
File "/home/sanchitgandhi/hf/lib/python3.8/site-packages/jax/linear_util.py", line 168, in call_wrapped |
|
ans = self.f(*args, **dict(self.params, **kwargs)) |
|
File "run_flax_speech_recognition_seq2seq.py", line 1174, in train_step |
|
if gradient_accumulation_steps == 1 or training_args.multisteps: |
|
jax._src.traceback_util.UnfilteredStackTrace: AttributeError: 'FlaxSeq2SeqTrainingArguments' object has no attribute 'multisteps' |
|
|
|
The stack trace below excludes JAX-internal frames. |
|
The preceding is the original exception that occurred, unmodified. |
|
|
|
-------------------- |
|
|
|
The above exception was the direct cause of the following exception: |
|
|
|
Traceback (most recent call last): |
|
File "run_flax_speech_recognition_seq2seq.py", line 1507, in <module> |
|
main() |
|
File "run_flax_speech_recognition_seq2seq.py", line 1400, in main |
|
state, train_metric = p_train_step(state, batch) |
|
File "run_flax_speech_recognition_seq2seq.py", line 1174, in train_step |
|
if gradient_accumulation_steps == 1 or training_args.multisteps: |
|
AttributeError: 'FlaxSeq2SeqTrainingArguments' object has no attribute 'multisteps' |
|
wandb: Waiting for W&B process to finish... (failed 1). Press Control-C to abort syncing. |
|
wandb: - 0.002 MB of 0.002 MB uploaded (0.000 MB deduped)
wandb: \ 0.002 MB of 0.002 MB uploaded (0.000 MB deduped)
wandb: | 0.002 MB of 0.034 MB uploaded (0.000 MB deduped)
wandb: / 0.002 MB of 0.034 MB uploaded (0.000 MB deduped)
wandb: - 0.034 MB of 0.034 MB uploaded (0.000 MB deduped)
wandb: \ 0.034 MB of 0.034 MB uploaded (0.000 MB deduped)
wandb: | 0.034 MB of 0.034 MB uploaded (0.000 MB deduped)
wandb: / 0.034 MB of 0.034 MB uploaded (0.000 MB deduped)
wandb: - 0.034 MB of 0.034 MB uploaded (0.000 MB deduped)
wandb: \ 0.034 MB of 0.034 MB uploaded (0.000 MB deduped)
wandb: | 0.034 MB of 0.034 MB uploaded (0.000 MB deduped)
wandb: / 0.034 MB of 0.034 MB uploaded (0.000 MB deduped)
wandb: |
|
wandb: Synced flax-wav2vec2-2-bart-large-ls-960h-feature-encoder: https://wandb.ai/sanchit-gandhi/librispeech_960h/runs/2nzi0chc |
|
wandb: Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s) |
|
wandb: Find logs at: ./wandb/run-20220530_175928-2nzi0chc/logs |
|
|