wandb: Currently logged in as: priyanshi-pal (priyanshipal). Use `wandb login --relogin` to force relogin
wandb: wandb version 0.17.7 is available!  To upgrade, please run:
wandb:  $ pip install wandb --upgrade
wandb: Tracking run with wandb version 0.17.6
wandb: Run data is saved locally in /scratch/elec/t405-puhe/p/palp3/MUCS/wandb/run-20240821_145646-o660b9lv
wandb: Run `wandb offline` to turn off syncing.
wandb: Syncing run iconic-capybara-25
wandb: ⭐️ View project at https://wandb.ai/priyanshipal/huggingface
wandb: 🚀 View run at https://wandb.ai/priyanshipal/huggingface/runs/o660b9lv
/scratch/work/palp3/myenv/lib/python3.11/site-packages/transformers/training_args.py:1525: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of 🤗 Transformers. Use `eval_strategy` instead
  warnings.warn(
08/21/2024 14:56:50 - WARNING - __main__ - device: cuda:0, n_gpu: 116-bits training: True

Generating train split: 0 examples [00:00, ? examples/s]
Generating train split: 52825 examples [00:00, 151020.17 examples/s]
Generating train split: 52825 examples [00:00, 147333.22 examples/s]

Generating train split: 0 examples [00:00, ? examples/s]
Generating train split: 3136 examples [00:00, 31226.84 examples/s]
Generating train split: 3136 examples [00:00, 30668.04 examples/s]
/scratch/work/palp3/myenv/lib/python3.11/site-packages/transformers/models/auto/configuration_auto.py:957: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
  warnings.warn(
/scratch/work/palp3/myenv/lib/python3.11/site-packages/transformers/configuration_utils.py:364: 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(
/scratch/work/palp3/myenv/lib/python3.11/site-packages/transformers/models/auto/feature_extraction_auto.py:329: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
  warnings.warn(
/scratch/elec/puhe/p/palp3/MUCS/finetune_script_indicw2v_partdata.py:508: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
  state_dict = torch.load(f"{model_args.model_name_or_path}/pytorch_model.bin")
Some weights of the model checkpoint at /m/triton/scratch/elec/puhe/p/palp3/MUCS/indicwav2vec-hindi were not used when initializing Wav2Vec2ForCTC: ['wav2vec2.encoder.pos_conv_embed.conv.weight_g', 'wav2vec2.encoder.pos_conv_embed.conv.weight_v']
- This IS expected if you are initializing Wav2Vec2ForCTC from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing Wav2Vec2ForCTC from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
Some weights of Wav2Vec2ForCTC were not initialized from the model checkpoint at /m/triton/scratch/elec/puhe/p/palp3/MUCS/indicwav2vec-hindi and are newly initialized: ['lm_head.bias', 'lm_head.weight', 'wav2vec2.encoder.pos_conv_embed.conv.parametrizations.weight.original0', 'wav2vec2.encoder.pos_conv_embed.conv.parametrizations.weight.original1']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
Wav2Vec2CTCTokenizer(name_or_path='', vocab_size=149, model_max_length=1000000000000000019884624838656, is_fast=False, padding_side='right', truncation_side='right', special_tokens={'bos_token': '<s>', 'eos_token': '</s>', 'unk_token': '[UNK]', 'pad_token': '[PAD]'}, clean_up_tokenization_spaces=True),  added_tokens_decoder={
	147: AddedToken("[UNK]", rstrip=True, lstrip=True, single_word=False, normalized=False, special=False),
	148: AddedToken("[PAD]", rstrip=True, lstrip=True, single_word=False, normalized=False, special=False),
	149: AddedToken("<s>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
	150: AddedToken("</s>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
}
CHECK MODEL PARAMS Wav2Vec2ForCTC(
  (wav2vec2): Wav2Vec2Model(
    (feature_extractor): Wav2Vec2FeatureEncoder(
      (conv_layers): ModuleList(
        (0): Wav2Vec2LayerNormConvLayer(
          (conv): Conv1d(1, 512, kernel_size=(10,), stride=(5,))
          (layer_norm): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
          (activation): GELUActivation()
        )
        (1-4): 4 x Wav2Vec2LayerNormConvLayer(
          (conv): Conv1d(512, 512, kernel_size=(3,), stride=(2,))
          (layer_norm): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
          (activation): GELUActivation()
        )
        (5-6): 2 x Wav2Vec2LayerNormConvLayer(
          (conv): Conv1d(512, 512, kernel_size=(2,), stride=(2,))
          (layer_norm): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
          (activation): GELUActivation()
        )
      )
    )
    (feature_projection): Wav2Vec2FeatureProjection(
      (layer_norm): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
      (projection): Linear(in_features=512, out_features=1024, bias=True)
      (dropout): Dropout(p=0.3, inplace=False)
    )
    (encoder): Wav2Vec2EncoderStableLayerNorm(
      (pos_conv_embed): Wav2Vec2PositionalConvEmbedding(
        (conv): ParametrizedConv1d(
          1024, 1024, kernel_size=(128,), stride=(1,), padding=(64,), groups=16
          (parametrizations): ModuleDict(
            (weight): ParametrizationList(
              (0): _WeightNorm()
            )
          )
        )
        (padding): Wav2Vec2SamePadLayer()
        (activation): GELUActivation()
      )
      (layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
      (dropout): Dropout(p=0.2, inplace=False)
      (layers): ModuleList(
        (0-23): 24 x Wav2Vec2EncoderLayerStableLayerNorm(
          (attention): Wav2Vec2SdpaAttention(
            (k_proj): Linear(in_features=1024, out_features=1024, bias=True)
            (v_proj): Linear(in_features=1024, out_features=1024, bias=True)
            (q_proj): Linear(in_features=1024, out_features=1024, bias=True)
            (out_proj): Linear(in_features=1024, out_features=1024, bias=True)
          )
          (dropout): Dropout(p=0.2, inplace=False)
          (layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
          (feed_forward): Wav2Vec2FeedForward(
            (intermediate_dropout): Dropout(p=0.0, inplace=False)
            (intermediate_dense): Linear(in_features=1024, out_features=4096, bias=True)
            (intermediate_act_fn): GELUActivation()
            (output_dense): Linear(in_features=4096, out_features=1024, bias=True)
            (output_dropout): Dropout(p=0.2, inplace=False)
          )
          (final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
        )
      )
    )
  )
  (dropout): Dropout(p=0.0, inplace=False)
  (lm_head): Linear(in_features=1024, out_features=151, bias=True)
)

preprocess datasets:   0%|          | 0/20000 [00:00<?, ? examples/s]
preprocess datasets:   0%|          | 1/20000 [00:05<32:45:52,  5.90s/ examples]
preprocess datasets:   0%|          | 8/20000 [00:06<3:04:25,  1.81 examples/s] 
preprocess datasets:   0%|          | 17/20000 [00:06<1:11:57,  4.63 examples/s]
preprocess datasets:   0%|          | 26/20000 [00:06<40:10,  8.28 examples/s]  
preprocess datasets:   0%|          | 33/20000 [00:06<28:13, 11.79 examples/s]
preprocess datasets:   0%|          | 42/20000 [00:06<19:02, 17.46 examples/s]
preprocess datasets:   0%|          | 49/20000 [00:06<14:49, 22.42 examples/s]
preprocess datasets:   0%|          | 60/20000 [00:06<10:13, 32.49 examples/s]
preprocess datasets:   0%|          | 68/20000 [00:06<08:32, 38.89 examples/s]
preprocess datasets:   0%|          | 78/20000 [00:07<07:25, 44.69 examples/s]
preprocess datasets:   0%|          | 90/20000 [00:07<06:29, 51.11 examples/s]
preprocess datasets:   0%|          | 98/20000 [00:07<06:02, 54.90 examples/s]
preprocess datasets:   1%|          | 105/20000 [00:07<05:59, 55.40 examples/s]
preprocess datasets:   1%|          | 112/20000 [00:07<05:49, 56.85 examples/s]
preprocess datasets:   1%|          | 122/20000 [00:07<05:12, 63.56 examples/s]
preprocess datasets:   1%|          | 130/20000 [00:07<04:57, 66.77 examples/s]
preprocess datasets:   1%|          | 139/20000 [00:07<04:39, 71.08 examples/s]
preprocess datasets:   1%|          | 150/20000 [00:08<05:06, 64.77 examples/s]
preprocess datasets:   1%|          | 159/20000 [00:08<04:43, 69.94 examples/s]
preprocess datasets:   1%|          | 170/20000 [00:08<04:49, 68.57 examples/s]
preprocess datasets:   1%|          | 181/20000 [00:08<04:50, 68.32 examples/s]
preprocess datasets:   1%|          | 189/20000 [00:08<04:50, 68.17 examples/s]
preprocess datasets:   1%|          | 196/20000 [00:08<04:52, 67.78 examples/s]
preprocess datasets:   1%|          | 203/20000 [00:08<04:50, 68.22 examples/s]
preprocess datasets:   1%|          | 213/20000 [00:08<04:29, 73.52 examples/s]
preprocess datasets:   1%|          | 222/20000 [00:09<04:21, 75.53 examples/s]
preprocess datasets:   1%|          | 231/20000 [00:09<06:12, 53.01 examples/s]
preprocess datasets:   1%|          | 239/20000 [00:09<05:57, 55.27 examples/s]
preprocess datasets:   1%|          | 248/20000 [00:09<05:30, 59.74 examples/s]
preprocess datasets:   1%|▏         | 258/20000 [00:09<04:58, 66.22 examples/s]
preprocess datasets:   1%|▏         | 267/20000 [00:09<06:06, 53.90 examples/s]
preprocess datasets:   1%|▏         | 275/20000 [00:10<05:55, 55.55 examples/s]
preprocess datasets:   1%|▏         | 284/20000 [00:10<06:02, 54.41 examples/s]
preprocess datasets:   1%|▏         | 292/20000 [00:10<05:43, 57.39 examples/s]
preprocess datasets:   2%|▏         | 300/20000 [00:10<05:24, 60.75 examples/s]
preprocess datasets:   2%|▏         | 308/20000 [00:10<05:54, 55.61 examples/s]
preprocess datasets:   2%|▏         | 317/20000 [00:10<05:16, 62.11 examples/s]
preprocess datasets:   2%|▏         | 325/20000 [00:10<05:10, 63.35 examples/s]
preprocess datasets:   2%|▏         | 332/20000 [00:11<05:09, 63.52 examples/s]
preprocess datasets:   2%|▏         | 340/20000 [00:11<04:54, 66.84 examples/s]
preprocess datasets:   2%|▏         | 349/20000 [00:11<05:35, 58.52 examples/s]
preprocess datasets:   2%|▏         | 358/20000 [00:11<05:05, 64.33 examples/s]
preprocess datasets:   2%|▏         | 369/20000 [00:11<05:09, 63.52 examples/s]
preprocess datasets:   2%|▏         | 379/20000 [00:11<05:19, 61.46 examples/s]
preprocess datasets:   2%|▏         | 387/20000 [00:11<05:11, 63.03 examples/s]
preprocess datasets:   2%|▏         | 394/20000 [00:11<05:14, 62.30 examples/s]
preprocess datasets:   2%|▏         | 401/20000 [00:12<05:10, 63.22 examples/s]
preprocess datasets:   2%|▏         | 409/20000 [00:12<05:03, 64.60 examples/s]
preprocess datasets:   2%|▏         | 417/20000 [00:12<05:08, 63.52 examples/s]
preprocess datasets:   2%|▏         | 428/20000 [00:12<05:11, 62.78 examples/s]
preprocess datasets:   2%|▏         | 439/20000 [00:12<04:42, 69.35 examples/s]
preprocess datasets:   2%|▏         | 447/20000 [00:12<04:44, 68.61 examples/s]
preprocess datasets:   2%|▏         | 458/20000 [00:12<04:51, 67.13 examples/s]
preprocess datasets:   2%|▏         | 466/20000 [00:13<04:43, 68.88 examples/s]
preprocess datasets:   2%|▏         | 474/20000 [00:13<04:45, 68.49 examples/s]
preprocess datasets:   2%|▏         | 484/20000 [00:13<04:19, 75.16 examples/s]
preprocess datasets:   2%|▏         | 492/20000 [00:13<04:24, 73.65 examples/s]
preprocess datasets:   3%|▎         | 501/20000 [00:13<04:26, 73.21 examples/s]
preprocess datasets:   3%|▎         | 509/20000 [00:13<04:27, 72.81 examples/s]
preprocess datasets:   3%|▎         | 519/20000 [00:13<04:11, 77.33 examples/s]
preprocess datasets:   3%|▎         | 527/20000 [00:13<04:30, 72.01 examples/s]
preprocess datasets:   3%|▎         | 535/20000 [00:13<04:39, 69.70 examples/s]
preprocess datasets:   3%|▎         | 543/20000 [00:14<04:52, 66.55 examples/s]
preprocess datasets:   3%|▎         | 550/20000 [00:14<04:55, 65.75 examples/s]
preprocess datasets:   3%|▎         | 558/20000 [00:14<04:52, 66.58 examples/s]
preprocess datasets:   3%|▎         | 568/20000 [00:14<04:35, 70.65 examples/s]
preprocess datasets:   3%|▎         | 577/20000 [00:14<04:27, 72.54 examples/s]
preprocess datasets:   3%|▎         | 585/20000 [00:14<04:31, 71.62 examples/s]
preprocess datasets:   3%|▎         | 593/20000 [00:14<04:32, 71.33 examples/s]
preprocess datasets:   3%|▎         | 604/20000 [00:15<05:10, 62.44 examples/s]
preprocess datasets:   3%|▎         | 613/20000 [00:15<04:59, 64.82 examples/s]
preprocess datasets:   3%|▎         | 622/20000 [00:15<04:40, 69.10 examples/s]
preprocess datasets:   3%|▎         | 633/20000 [00:15<04:45, 67.84 examples/s]
preprocess datasets:   3%|▎         | 642/20000 [00:15<04:46, 67.50 examples/s]
preprocess datasets:   3%|▎         | 652/20000 [00:15<05:02, 63.99 examples/s]
preprocess datasets:   3%|▎         | 661/20000 [00:15<04:45, 67.77 examples/s]
preprocess datasets:   3%|▎         | 669/20000 [00:15<04:40, 69.02 examples/s]
preprocess datasets:   3%|▎         | 677/20000 [00:16<05:04, 63.43 examples/s]
preprocess datasets:   3%|▎         | 686/20000 [00:16<04:53, 65.80 examples/s]
preprocess datasets:   3%|▎         | 696/20000 [00:16<04:40, 68.78 examples/s]
preprocess datasets:   4%|▎         | 705/20000 [00:16<04:24, 73.06 examples/s]
preprocess datasets:   4%|▎         | 716/20000 [00:16<04:38, 69.35 examples/s]
preprocess datasets:   4%|▎         | 727/20000 [00:16<04:15, 75.33 examples/s]
preprocess datasets:   4%|▎         | 736/20000 [00:16<04:22, 73.45 examples/s]
preprocess datasets:   4%|▎         | 745/20000 [00:17<04:15, 75.37 examples/s]
preprocess datasets:   4%|▍         | 753/20000 [00:17<04:16, 75.04 examples/s]
preprocess datasets:   4%|▍         | 764/20000 [00:17<04:30, 71.18 examples/s]
preprocess datasets:   4%|▍         | 774/20000 [00:17<05:00, 64.07 examples/s]
preprocess datasets:   4%|▍         | 784/20000 [00:17<05:08, 62.24 examples/s]
preprocess datasets:   4%|▍         | 792/20000 [00:17<04:54, 65.20 examples/s]
preprocess datasets:   4%|▍         | 799/20000 [00:17<04:55, 65.08 examples/s]
preprocess datasets:   4%|▍         | 807/20000 [00:17<04:45, 67.22 examples/s]
preprocess datasets:   4%|▍         | 816/20000 [00:18<04:35, 69.58 examples/s]
preprocess datasets:   4%|▍         | 827/20000 [00:18<04:15, 74.91 examples/s]
preprocess datasets:   4%|▍         | 836/20000 [00:18<04:15, 74.92 examples/s]
preprocess datasets:   4%|▍         | 849/20000 [00:18<04:19, 73.73 examples/s]
preprocess datasets:   4%|▍         | 857/20000 [00:18<04:25, 72.16 examples/s]
preprocess datasets:   4%|▍         | 868/20000 [00:18<04:11, 75.95 examples/s]
preprocess datasets:   4%|▍         | 876/20000 [00:18<04:18, 73.97 examples/s]
preprocess datasets:   4%|▍         | 885/20000 [00:19<04:08, 76.98 examples/s]
preprocess datasets:   4%|▍         | 894/20000 [00:19<04:36, 69.01 examples/s]
preprocess datasets:   5%|▍         | 902/20000 [00:19<04:33, 69.78 examples/s]
preprocess datasets:   5%|▍         | 911/20000 [00:19<04:59, 63.81 examples/s]
preprocess datasets:   5%|▍         | 919/20000 [00:19<04:56, 64.27 examples/s]
preprocess datasets:   5%|▍         | 926/20000 [00:19<05:07, 62.12 examples/s]
preprocess datasets:   5%|▍         | 933/20000 [00:19<05:03, 62.72 examples/s]
preprocess datasets:   5%|▍         | 944/20000 [00:19<04:55, 64.40 examples/s]
preprocess datasets:   5%|▍         | 954/20000 [00:20<05:50, 54.32 examples/s]
preprocess datasets:   5%|▍         | 962/20000 [00:20<05:37, 56.47 examples/s]
preprocess datasets:   5%|▍         | 970/20000 [00:20<05:14, 60.53 examples/s]
preprocess datasets:   5%|▍         | 977/20000 [00:20<05:11, 61.09 examples/s]
preprocess datasets:   5%|▍         | 986/20000 [00:20<04:51, 65.25 examples/s]
preprocess datasets:   5%|▍         | 993/20000 [00:20<04:53, 64.82 examples/s]
preprocess datasets:   5%|▌         | 1000/20000 [00:21<14:39, 21.61 examples/s]
preprocess datasets:   5%|▌         | 1011/20000 [00:21<10:13, 30.94 examples/s]
preprocess datasets:   5%|▌         | 1021/20000 [00:21<08:25, 37.54 examples/s]
preprocess datasets:   5%|▌         | 1030/20000 [00:22<07:13, 43.74 examples/s]
preprocess datasets:   5%|▌         | 1038/20000 [00:22<06:31, 48.46 examples/s]
preprocess datasets:   5%|▌         | 1046/20000 [00:22<06:00, 52.59 examples/s]
preprocess datasets:   5%|▌         | 1056/20000 [00:22<05:20, 59.17 examples/s]
preprocess datasets:   5%|▌         | 1065/20000 [00:22<04:51, 64.92 examples/s]
preprocess datasets:   5%|▌         | 1074/20000 [00:22<04:33, 69.17 examples/s]
preprocess datasets:   5%|▌         | 1082/20000 [00:22<04:28, 70.56 examples/s]
preprocess datasets:   5%|▌         | 1091/20000 [00:22<04:17, 73.37 examples/s]
preprocess datasets:   6%|▌         | 1100/20000 [00:22<04:13, 74.58 examples/s]
preprocess datasets:   6%|▌         | 1109/20000 [00:23<05:07, 61.38 examples/s]
preprocess datasets:   6%|▌         | 1119/20000 [00:23<04:32, 69.30 examples/s]
preprocess datasets:   6%|▌         | 1131/20000 [00:23<04:31, 69.45 examples/s]
preprocess datasets:   6%|▌         | 1140/20000 [00:23<04:34, 68.68 examples/s]
preprocess datasets:   6%|▌         | 1149/20000 [00:23<04:19, 72.69 examples/s]
preprocess datasets:   6%|▌         | 1157/20000 [00:23<04:25, 70.92 examples/s]
preprocess datasets:   6%|▌         | 1166/20000 [00:23<04:18, 72.82 examples/s]
preprocess datasets:   6%|▌         | 1175/20000 [00:24<04:15, 73.80 examples/s]
preprocess datasets:   6%|▌         | 1187/20000 [00:24<03:46, 82.94 examples/s]
preprocess datasets:   6%|▌         | 1198/20000 [00:24<04:01, 77.84 examples/s]
preprocess datasets:   6%|▌         | 1208/20000 [00:24<05:11, 60.28 examples/s]
preprocess datasets:   6%|▌         | 1215/20000 [00:24<05:07, 61.06 examples/s]
preprocess datasets:   6%|▌         | 1224/20000 [00:25<11:45, 26.62 examples/s]
preprocess datasets:   6%|▌         | 1234/20000 [00:25<09:12, 33.94 examples/s]
preprocess datasets:   6%|▌         | 1243/20000 [00:25<07:44, 40.34 examples/s]
preprocess datasets:   6%|▋         | 1253/20000 [00:25<07:37, 40.94 examples/s]
preprocess datasets:   6%|▋         | 1260/20000 [00:26<07:04, 44.14 examples/s]
preprocess datasets:   6%|▋         | 1271/20000 [00:26<05:50, 53.42 examples/s]
preprocess datasets:   6%|▋         | 1278/20000 [00:26<05:35, 55.76 examples/s]
preprocess datasets:   6%|▋         | 1288/20000 [00:26<04:52, 64.00 examples/s]
preprocess datasets:   6%|▋         | 1296/20000 [00:26<04:48, 64.75 examples/s]
preprocess datasets:   7%|▋         | 1305/20000 [00:26<04:37, 67.48 examples/s]
preprocess datasets:   7%|▋         | 1315/20000 [00:26<04:17, 72.69 examples/s]
preprocess datasets:   7%|▋         | 1323/20000 [00:26<04:14, 73.41 examples/s]
preprocess datasets:   7%|▋         | 1331/20000 [00:27<04:09, 74.93 examples/s]
preprocess datasets:   7%|▋         | 1343/20000 [00:27<04:13, 73.70 examples/s]
preprocess datasets:   7%|▋         | 1354/20000 [00:27<04:17, 72.37 examples/s]
preprocess datasets:   7%|▋         | 1363/20000 [00:27<04:13, 73.51 examples/s]
preprocess datasets:   7%|▋         | 1375/20000 [00:27<04:24, 70.34 examples/s]
preprocess datasets:   7%|▋         | 1387/20000 [00:27<04:25, 70.20 examples/s]
preprocess datasets:   7%|▋         | 1396/20000 [00:27<04:18, 71.92 examples/s]
preprocess datasets:   7%|▋         | 1408/20000 [00:28<03:55, 78.88 examples/s]
preprocess datasets:   7%|▋         | 1417/20000 [00:28<04:00, 77.42 examples/s]
preprocess datasets:   7%|▋         | 1426/20000 [00:28<04:00, 77.22 examples/s]
preprocess datasets:   7%|▋         | 1438/20000 [00:28<03:40, 84.25 examples/s]
preprocess datasets:   7%|▋         | 1449/20000 [00:28<04:00, 77.15 examples/s]
preprocess datasets:   7%|▋         | 1459/20000 [00:28<03:55, 78.74 examples/s]
preprocess datasets:   7%|▋         | 1468/20000 [00:28<03:48, 81.25 examples/s]
preprocess datasets:   7%|▋         | 1481/20000 [00:28<03:53, 79.15 examples/s]
preprocess datasets:   7%|▋         | 1495/20000 [00:29<03:28, 88.78 examples/s]
preprocess datasets:   8%|▊         | 1507/20000 [00:29<04:05, 75.28 examples/s]
preprocess datasets:   8%|▊         | 1520/20000 [00:29<04:11, 73.55 examples/s]
preprocess datasets:   8%|▊         | 1529/20000 [00:29<04:05, 75.17 examples/s]
preprocess datasets:   8%|▊         | 1537/20000 [00:29<04:11, 73.49 examples/s]
preprocess datasets:   8%|▊         | 1546/20000 [00:29<04:04, 75.51 examples/s]
preprocess datasets:   8%|▊         | 1554/20000 [00:29<04:14, 72.43 examples/s]
preprocess datasets:   8%|▊         | 1565/20000 [00:30<04:29, 68.40 examples/s]
preprocess datasets:   8%|▊         | 1574/20000 [00:30<04:14, 72.48 examples/s]
preprocess datasets:   8%|▊         | 1583/20000 [00:30<04:12, 72.85 examples/s]
preprocess datasets:   8%|▊         | 1594/20000 [00:30<03:57, 77.50 examples/s]
preprocess datasets:   8%|▊         | 1603/20000 [00:30<03:55, 78.00 examples/s]
preprocess datasets:   8%|▊         | 1612/20000 [00:30<03:51, 79.42 examples/s]
preprocess datasets:   8%|▊         | 1625/20000 [00:30<04:02, 75.89 examples/s]
preprocess datasets:   8%|▊         | 1635/20000 [00:30<03:51, 79.42 examples/s]
preprocess datasets:   8%|▊         | 1644/20000 [00:31<03:57, 77.18 examples/s]
preprocess datasets:   8%|▊         | 1654/20000 [00:31<08:46, 34.88 examples/s]
preprocess datasets:   8%|▊         | 1663/20000 [00:31<07:23, 41.37 examples/s]
preprocess datasets:   8%|▊         | 1673/20000 [00:32<06:17, 48.53 examples/s]
preprocess datasets:   8%|▊         | 1680/20000 [00:32<05:55, 51.60 examples/s]
preprocess datasets:   8%|▊         | 1689/20000 [00:32<05:54, 51.60 examples/s]
preprocess datasets:   8%|▊         | 1696/20000 [00:32<05:37, 54.24 examples/s]
preprocess datasets:   9%|▊         | 1708/20000 [00:32<05:09, 59.10 examples/s]
preprocess datasets:   9%|▊         | 1718/20000 [00:32<05:18, 57.32 examples/s]
preprocess datasets:   9%|▊         | 1725/20000 [00:32<05:20, 57.10 examples/s]
preprocess datasets:   9%|▊         | 1736/20000 [00:33<05:13, 58.26 examples/s]
preprocess datasets:   9%|▊         | 1746/20000 [00:33<04:35, 66.29 examples/s]
preprocess datasets:   9%|▉         | 1754/20000 [00:33<04:41, 64.82 examples/s]
preprocess datasets:   9%|▉         | 1762/20000 [00:33<04:31, 67.10 examples/s]
preprocess datasets:   9%|▉         | 1770/20000 [00:33<04:34, 66.43 examples/s]
preprocess datasets:   9%|▉         | 1781/20000 [00:33<04:13, 71.90 examples/s]
preprocess datasets:   9%|▉         | 1790/20000 [00:33<04:05, 74.28 examples/s]
preprocess datasets:   9%|▉         | 1798/20000 [00:33<04:14, 71.51 examples/s]
preprocess datasets:   9%|▉         | 1807/20000 [00:34<04:14, 71.55 examples/s]
preprocess datasets:   9%|▉         | 1817/20000 [00:34<03:55, 77.34 examples/s]
preprocess datasets:   9%|▉         | 1827/20000 [00:34<03:47, 79.93 examples/s]
preprocess datasets:   9%|▉         | 1836/20000 [00:34<03:57, 76.47 examples/s]
preprocess datasets:   9%|▉         | 1846/20000 [00:34<04:32, 66.53 examples/s]
preprocess datasets:   9%|▉         | 1858/20000 [00:34<03:54, 77.24 examples/s]
preprocess datasets:   9%|▉         | 1867/20000 [00:34<03:49, 78.84 examples/s]
preprocess datasets:   9%|▉         | 1877/20000 [00:34<03:46, 80.12 examples/s]
preprocess datasets:   9%|▉         | 1886/20000 [00:35<03:51, 78.23 examples/s]
preprocess datasets:   9%|▉         | 1894/20000 [00:35<03:58, 75.97 examples/s]
preprocess datasets:  10%|▉         | 1903/20000 [00:35<03:54, 77.29 examples/s]
preprocess datasets:  10%|▉         | 1914/20000 [00:35<04:11, 72.05 examples/s]
preprocess datasets:  10%|▉         | 1925/20000 [00:35<04:14, 70.99 examples/s]
preprocess datasets:  10%|▉         | 1937/20000 [00:35<04:15, 70.66 examples/s]
preprocess datasets:  10%|▉         | 1949/20000 [00:35<04:15, 70.74 examples/s]
preprocess datasets:  10%|▉         | 1959/20000 [00:36<04:07, 72.81 examples/s]
preprocess datasets:  10%|▉         | 1972/20000 [00:36<03:59, 75.13 examples/s]
preprocess datasets:  10%|▉         | 1981/20000 [00:36<03:52, 77.41 examples/s]
preprocess datasets:  10%|▉         | 1990/20000 [00:36<03:53, 77.14 examples/s]
preprocess datasets:  10%|█         | 2000/20000 [00:37<10:30, 28.55 examples/s]
preprocess datasets:  10%|█         | 2010/20000 [00:37<08:24, 35.64 examples/s]
preprocess datasets:  10%|█         | 2020/20000 [00:37<06:59, 42.84 examples/s]
preprocess datasets:  10%|█         | 2028/20000 [00:37<06:21, 47.13 examples/s]
preprocess datasets:  10%|█         | 2037/20000 [00:37<05:38, 53.04 examples/s]
preprocess datasets:  10%|█         | 2047/20000 [00:37<04:57, 60.35 examples/s]
preprocess datasets:  10%|█         | 2056/20000 [00:38<04:37, 64.57 examples/s]
preprocess datasets:  10%|█         | 2068/20000 [00:38<04:02, 73.98 examples/s]
preprocess datasets:  10%|█         | 2079/20000 [00:38<03:47, 78.76 examples/s]
preprocess datasets:  10%|█         | 2089/20000 [00:38<04:08, 72.17 examples/s]
preprocess datasets:  10%|█         | 2098/20000 [00:38<04:06, 72.70 examples/s]
preprocess datasets:  11%|█         | 2108/20000 [00:38<03:53, 76.70 examples/s]
preprocess datasets:  11%|█         | 2118/20000 [00:38<03:42, 80.46 examples/s]
preprocess datasets:  11%|█         | 2128/20000 [00:38<04:11, 70.98 examples/s]
preprocess datasets:  11%|█         | 2136/20000 [00:39<04:12, 70.88 examples/s]
preprocess datasets:  11%|█         | 2151/20000 [00:39<03:24, 87.46 examples/s]
preprocess datasets:  11%|█         | 2163/20000 [00:39<03:39, 81.26 examples/s]
preprocess datasets:  11%|█         | 2175/20000 [00:39<03:28, 85.49 examples/s]
preprocess datasets:  11%|█         | 2186/20000 [00:39<03:45, 79.03 examples/s]
preprocess datasets:  11%|█         | 2196/20000 [00:39<03:42, 80.04 examples/s]
preprocess datasets:  11%|█         | 2207/20000 [00:39<03:35, 82.58 examples/s]
preprocess datasets:  11%|█         | 2217/20000 [00:40<04:07, 71.95 examples/s]
preprocess datasets:  11%|█         | 2225/20000 [00:40<04:16, 69.35 examples/s]
preprocess datasets:  11%|█         | 2234/20000 [00:40<04:09, 71.34 examples/s]
preprocess datasets:  11%|█         | 2243/20000 [00:40<04:10, 70.79 examples/s]
preprocess datasets:  11%|█▏        | 2251/20000 [00:41<14:04, 21.01 examples/s]
preprocess datasets:  11%|█▏        | 2259/20000 [00:41<11:22, 25.99 examples/s]
preprocess datasets:  11%|█▏        | 2268/20000 [00:41<09:01, 32.74 examples/s]
preprocess datasets:  11%|█▏        | 2275/20000 [00:41<08:10, 36.17 examples/s]
preprocess datasets:  11%|█▏        | 2282/20000 [00:42<07:25, 39.78 examples/s]
preprocess datasets:  11%|█▏        | 2290/20000 [00:42<06:24, 46.07 examples/s]
preprocess datasets:  11%|█▏        | 2298/20000 [00:42<06:03, 48.76 examples/s]
preprocess datasets:  12%|█▏        | 2305/20000 [00:42<05:42, 51.64 examples/s]
preprocess datasets:  12%|█▏        | 2316/20000 [00:42<04:44, 62.25 examples/s]
preprocess datasets:  12%|█▏        | 2324/20000 [00:42<04:28, 65.79 examples/s]
preprocess datasets:  12%|█▏        | 2332/20000 [00:42<04:25, 66.60 examples/s]
preprocess datasets:  12%|█▏        | 2342/20000 [00:42<04:04, 72.20 examples/s]
preprocess datasets:  12%|█▏        | 2350/20000 [00:42<04:03, 72.34 examples/s]
preprocess datasets:  12%|█▏        | 2361/20000 [00:43<03:45, 78.10 examples/s]
preprocess datasets:  12%|█▏        | 2370/20000 [00:43<03:56, 74.42 examples/s]
preprocess datasets:  12%|█▏        | 2382/20000 [00:43<03:36, 81.36 examples/s]
preprocess datasets:  12%|█▏        | 2392/20000 [00:43<03:31, 83.13 examples/s]
preprocess datasets:  12%|█▏        | 2401/20000 [00:43<03:29, 84.18 examples/s]
preprocess datasets:  12%|█▏        | 2410/20000 [00:43<03:36, 81.10 examples/s]
preprocess datasets:  12%|█▏        | 2422/20000 [00:43<03:59, 73.41 examples/s]
preprocess datasets:  12%|█▏        | 2434/20000 [00:44<03:33, 82.22 examples/s]
preprocess datasets:  12%|█▏        | 2445/20000 [00:44<03:21, 87.27 examples/s]
preprocess datasets:  12%|█▏        | 2455/20000 [00:44<03:19, 87.81 examples/s]
preprocess datasets:  12%|█▏        | 2468/20000 [00:44<03:35, 81.31 examples/s]
preprocess datasets:  12%|█▏        | 2478/20000 [00:44<03:36, 81.00 examples/s]
preprocess datasets:  12%|█▏        | 2490/20000 [00:44<03:24, 85.67 examples/s]
preprocess datasets:  13%|█▎        | 2502/20000 [00:44<03:09, 92.34 examples/s]
preprocess datasets:  13%|█▎        | 2513/20000 [00:44<03:28, 83.87 examples/s]
preprocess datasets:  13%|█▎        | 2522/20000 [00:45<03:32, 82.21 examples/s]
preprocess datasets:  13%|█▎        | 2531/20000 [00:45<03:32, 82.35 examples/s]
preprocess datasets:  13%|█▎        | 2546/20000 [00:45<03:35, 80.94 examples/s]
preprocess datasets:  13%|█▎        | 2555/20000 [00:45<03:37, 80.29 examples/s]
preprocess datasets:  13%|█▎        | 2565/20000 [00:45<03:32, 81.97 examples/s]
preprocess datasets:  13%|█▎        | 2575/20000 [00:45<03:31, 82.26 examples/s]
preprocess datasets:  13%|█▎        | 2586/20000 [00:45<03:18, 87.52 examples/s]
preprocess datasets:  13%|█▎        | 2599/20000 [00:45<03:01, 95.93 examples/s]
preprocess datasets:  13%|█▎        | 2613/20000 [00:46<03:05, 93.68 examples/s]
preprocess datasets:  13%|█▎        | 2624/20000 [00:46<03:29, 82.93 examples/s]
preprocess datasets:  13%|█▎        | 2633/20000 [00:46<03:35, 80.44 examples/s]
preprocess datasets:  13%|█▎        | 2643/20000 [00:46<03:34, 80.93 examples/s]
preprocess datasets:  13%|█▎        | 2654/20000 [00:46<03:32, 81.44 examples/s]
preprocess datasets:  13%|█▎        | 2664/20000 [00:46<03:28, 82.99 examples/s]
preprocess datasets:  13%|█▎        | 2674/20000 [00:46<03:31, 81.77 examples/s]
preprocess datasets:  13%|█▎        | 2683/20000 [00:46<03:27, 83.45 examples/s]
preprocess datasets:  13%|█▎        | 2692/20000 [00:47<03:37, 79.49 examples/s]
preprocess datasets:  14%|█▎        | 2701/20000 [00:47<03:46, 76.21 examples/s]
preprocess datasets:  14%|█▎        | 2710/20000 [00:47<03:46, 76.24 examples/s]
preprocess datasets:  14%|█▎        | 2718/20000 [00:47<03:58, 72.45 examples/s]
preprocess datasets:  14%|█▎        | 2730/20000 [00:47<03:32, 81.46 examples/s]
preprocess datasets:  14%|█▎        | 2742/20000 [00:47<03:42, 77.61 examples/s]
preprocess datasets:  14%|█▍        | 2751/20000 [00:47<04:11, 68.62 examples/s]
preprocess datasets:  14%|█▍        | 2760/20000 [00:48<04:01, 71.43 examples/s]
preprocess datasets:  14%|█▍        | 2768/20000 [00:48<04:05, 70.08 examples/s]
preprocess datasets:  14%|█▍        | 2777/20000 [00:48<04:09, 69.16 examples/s]
preprocess datasets:  14%|█▍        | 2787/20000 [00:48<03:47, 75.60 examples/s]
preprocess datasets:  14%|█▍        | 2797/20000 [00:48<03:38, 78.84 examples/s]
preprocess datasets:  14%|█▍        | 2807/20000 [00:48<03:35, 79.97 examples/s]
preprocess datasets:  14%|█▍        | 2820/20000 [00:48<03:34, 79.92 examples/s]
preprocess datasets:  14%|█▍        | 2834/20000 [00:48<03:43, 76.81 examples/s]
preprocess datasets:  14%|█▍        | 2844/20000 [00:49<03:59, 71.66 examples/s]
preprocess datasets:  14%|█▍        | 2854/20000 [00:49<04:25, 64.55 examples/s]
preprocess datasets:  14%|█▍        | 2864/20000 [00:49<04:06, 69.52 examples/s]
preprocess datasets:  14%|█▍        | 2872/20000 [00:49<04:10, 68.35 examples/s]
preprocess datasets:  14%|█▍        | 2880/20000 [00:49<04:02, 70.52 examples/s]
preprocess datasets:  14%|█▍        | 2890/20000 [00:49<03:50, 74.33 examples/s]
preprocess datasets:  14%|█▍        | 2899/20000 [00:49<03:45, 75.92 examples/s]
preprocess datasets:  15%|█▍        | 2910/20000 [00:50<03:47, 75.18 examples/s]
preprocess datasets:  15%|█▍        | 2919/20000 [00:50<03:52, 73.54 examples/s]
preprocess datasets:  15%|█▍        | 2931/20000 [00:50<03:58, 71.56 examples/s]
preprocess datasets:  15%|█▍        | 2941/20000 [00:50<03:45, 75.56 examples/s]
preprocess datasets:  15%|█▍        | 2951/20000 [00:50<03:33, 79.83 examples/s]
preprocess datasets:  15%|█▍        | 2964/20000 [00:50<03:52, 73.12 examples/s]
preprocess datasets:  15%|█▍        | 2972/20000 [00:50<03:55, 72.33 examples/s]
preprocess datasets:  15%|█▍        | 2980/20000 [00:51<04:04, 69.75 examples/s]
preprocess datasets:  15%|█▍        | 2988/20000 [00:51<04:01, 70.41 examples/s]
preprocess datasets:  15%|█▍        | 2997/20000 [00:51<03:57, 71.60 examples/s]
preprocess datasets:  15%|█▌        | 3005/20000 [00:52<13:18, 21.29 examples/s]
preprocess datasets:  15%|█▌        | 3015/20000 [00:52<09:58, 28.36 examples/s]
preprocess datasets:  15%|█▌        | 3025/20000 [00:52<08:02, 35.15 examples/s]
preprocess datasets:  15%|█▌        | 3038/20000 [00:52<05:57, 47.48 examples/s]
preprocess datasets:  15%|█▌        | 3052/20000 [00:52<05:01, 56.21 examples/s]
preprocess datasets:  15%|█▌        | 3062/20000 [00:53<04:52, 57.86 examples/s]
preprocess datasets:  15%|█▌        | 3070/20000 [00:53<04:49, 58.44 examples/s]
preprocess datasets:  15%|█▌        | 3079/20000 [00:53<04:30, 62.55 examples/s]
preprocess datasets:  15%|█▌        | 3090/20000 [00:53<03:59, 70.52 examples/s]
preprocess datasets:  15%|█▌        | 3099/20000 [00:53<04:02, 69.72 examples/s]
preprocess datasets:  16%|█▌        | 3111/20000 [00:53<03:36, 77.92 examples/s]
preprocess datasets:  16%|█▌        | 3121/20000 [00:53<03:30, 80.00 examples/s]
preprocess datasets:  16%|█▌        | 3131/20000 [00:53<03:22, 83.39 examples/s]
preprocess datasets:  16%|█▌        | 3141/20000 [00:54<03:26, 81.46 examples/s]
preprocess datasets:  16%|█▌        | 3156/20000 [00:54<03:17, 85.09 examples/s]
preprocess datasets:  16%|█▌        | 3168/20000 [00:54<03:36, 77.61 examples/s]
preprocess datasets:  16%|█▌        | 3179/20000 [00:54<03:24, 82.38 examples/s]
preprocess datasets:  16%|█▌        | 3189/20000 [00:54<03:25, 81.78 examples/s]
preprocess datasets:  16%|█▌        | 3200/20000 [00:54<03:39, 76.67 examples/s]
preprocess datasets:  16%|█▌        | 3213/20000 [00:54<03:16, 85.25 examples/s]
preprocess datasets:  16%|█▌        | 3225/20000 [00:55<03:25, 81.83 examples/s]
preprocess datasets:  16%|█▌        | 3237/20000 [00:55<03:38, 76.61 examples/s]
preprocess datasets:  16%|█▌        | 3247/20000 [00:55<03:34, 78.13 examples/s]
preprocess datasets:  16%|█▋        | 3259/20000 [00:55<03:52, 71.93 examples/s]
preprocess datasets:  16%|█▋        | 3269/20000 [00:55<03:41, 75.47 examples/s]
preprocess datasets:  16%|█▋        | 3277/20000 [00:55<03:45, 74.22 examples/s]
preprocess datasets:  16%|█▋        | 3287/20000 [00:55<03:33, 78.19 examples/s]
preprocess datasets:  16%|█▋        | 3298/20000 [00:55<03:17, 84.78 examples/s]
preprocess datasets:  17%|█▋        | 3312/20000 [00:56<03:21, 82.81 examples/s]
preprocess datasets:  17%|█▋        | 3326/20000 [00:56<03:01, 91.98 examples/s]
preprocess datasets:  17%|█▋        | 3338/20000 [00:56<03:21, 82.78 examples/s]
preprocess datasets:  17%|█▋        | 3350/20000 [00:56<03:29, 79.57 examples/s]
preprocess datasets:  17%|█▋        | 3360/20000 [00:56<03:51, 71.76 examples/s]
preprocess datasets:  17%|█▋        | 3369/20000 [00:56<03:45, 73.89 examples/s]
preprocess datasets:  17%|█▋        | 3378/20000 [00:57<03:38, 76.19 examples/s]
preprocess datasets:  17%|█▋        | 3387/20000 [00:57<03:39, 75.57 examples/s]
preprocess datasets:  17%|█▋        | 3399/20000 [00:57<03:55, 70.48 examples/s]
preprocess datasets:  17%|█▋        | 3408/20000 [00:57<03:51, 71.54 examples/s]
preprocess datasets:  17%|█▋        | 3421/20000 [00:57<03:42, 74.42 examples/s]
preprocess datasets:  17%|█▋        | 3429/20000 [00:57<03:46, 73.10 examples/s]
preprocess datasets:  17%|█▋        | 3441/20000 [00:57<03:24, 80.80 examples/s]
preprocess datasets:  17%|█▋        | 3451/20000 [00:57<03:18, 83.33 examples/s]
preprocess datasets:  17%|█▋        | 3460/20000 [00:58<03:19, 83.09 examples/s]
preprocess datasets:  17%|█▋        | 3472/20000 [00:58<03:26, 80.02 examples/s]
preprocess datasets:  17%|█▋        | 3485/20000 [00:58<05:20, 51.60 examples/s]
preprocess datasets:  17%|█▋        | 3494/20000 [00:58<04:52, 56.41 examples/s]
preprocess datasets:  18%|█▊        | 3501/20000 [00:58<04:48, 57.28 examples/s]
preprocess datasets:  18%|█▊        | 3509/20000 [00:59<04:42, 58.41 examples/s]
preprocess datasets:  18%|█▊        | 3518/20000 [00:59<04:22, 62.82 examples/s]
preprocess datasets:  18%|█▊        | 3526/20000 [00:59<04:10, 65.75 examples/s]
preprocess datasets:  18%|█▊        | 3535/20000 [00:59<03:59, 68.87 examples/s]
preprocess datasets:  18%|█▊        | 3543/20000 [00:59<03:54, 70.25 examples/s]
preprocess datasets:  18%|█▊        | 3554/20000 [00:59<03:39, 74.98 examples/s]
preprocess datasets:  18%|█▊        | 3562/20000 [00:59<03:37, 75.41 examples/s]
preprocess datasets:  18%|█▊        | 3574/20000 [00:59<03:09, 86.85 examples/s]
preprocess datasets:  18%|█▊        | 3584/20000 [00:59<03:09, 86.69 examples/s]
preprocess datasets:  18%|█▊        | 3596/20000 [01:00<03:21, 81.53 examples/s]
preprocess datasets:  18%|█▊        | 3609/20000 [01:00<03:28, 78.78 examples/s]
preprocess datasets:  18%|█▊        | 3618/20000 [01:00<03:25, 79.54 examples/s]
preprocess datasets:  18%|█▊        | 3627/20000 [01:00<03:23, 80.61 examples/s]
preprocess datasets:  18%|█▊        | 3636/20000 [01:00<03:29, 78.05 examples/s]
preprocess datasets:  18%|█▊        | 3646/20000 [01:00<03:23, 80.48 examples/s]
preprocess datasets:  18%|█▊        | 3657/20000 [01:00<03:40, 74.14 examples/s]
preprocess datasets:  18%|█▊        | 3670/20000 [01:00<03:13, 84.49 examples/s]
preprocess datasets:  18%|█▊        | 3680/20000 [01:01<03:10, 85.66 examples/s]
preprocess datasets:  18%|█▊        | 3692/20000 [01:01<03:25, 79.49 examples/s]
preprocess datasets:  19%|█▊        | 3701/20000 [01:01<03:22, 80.31 examples/s]
preprocess datasets:  19%|█▊        | 3714/20000 [01:01<03:32, 76.67 examples/s]
preprocess datasets:  19%|█▊        | 3726/20000 [01:01<03:17, 82.56 examples/s]
preprocess datasets:  19%|█▊        | 3736/20000 [01:01<03:10, 85.31 examples/s]
preprocess datasets:  19%|█▊        | 3748/20000 [01:01<03:23, 79.80 examples/s]
preprocess datasets:  19%|█▉        | 3760/20000 [01:02<03:07, 86.77 examples/s]
preprocess datasets:  19%|█▉        | 3773/20000 [01:02<02:51, 94.58 examples/s]
preprocess datasets:  19%|█▉        | 3785/20000 [01:02<03:10, 85.06 examples/s]
preprocess datasets:  19%|█▉        | 3795/20000 [01:02<03:09, 85.49 examples/s]
preprocess datasets:  19%|█▉        | 3804/20000 [01:02<03:14, 83.43 examples/s]
preprocess datasets:  19%|█▉        | 3813/20000 [01:02<03:17, 81.94 examples/s]
preprocess datasets:  19%|█▉        | 3829/20000 [01:02<03:09, 85.39 examples/s]
preprocess datasets:  19%|█▉        | 3838/20000 [01:03<03:14, 83.19 examples/s]
preprocess datasets:  19%|█▉        | 3853/20000 [01:03<03:11, 84.18 examples/s]
preprocess datasets:  19%|█▉        | 3863/20000 [01:03<03:31, 76.30 examples/s]
preprocess datasets:  19%|█▉        | 3874/20000 [01:03<03:32, 75.81 examples/s]
preprocess datasets:  19%|█▉        | 3887/20000 [01:03<03:39, 73.55 examples/s]
preprocess datasets:  19%|█▉        | 3898/20000 [01:03<03:27, 77.55 examples/s]
preprocess datasets:  20%|█▉        | 3908/20000 [01:03<03:22, 79.51 examples/s]
preprocess datasets:  20%|█▉        | 3918/20000 [01:04<03:21, 79.82 examples/s]
preprocess datasets:  20%|█▉        | 3930/20000 [01:04<03:07, 85.70 examples/s]
preprocess datasets:  20%|█▉        | 3943/20000 [01:04<03:12, 83.38 examples/s]
preprocess datasets:  20%|█▉        | 3954/20000 [01:04<03:35, 74.50 examples/s]
preprocess datasets:  20%|█▉        | 3963/20000 [01:04<03:33, 75.18 examples/s]
preprocess datasets:  20%|█▉        | 3972/20000 [01:04<03:31, 75.92 examples/s]
preprocess datasets:  20%|█▉        | 3983/20000 [01:04<03:24, 78.36 examples/s]
preprocess datasets:  20%|█▉        | 3996/20000 [01:05<03:32, 75.35 examples/s]
preprocess datasets:  20%|██        | 4005/20000 [01:05<09:38, 27.63 examples/s]
preprocess datasets:  20%|██        | 4014/20000 [01:06<07:58, 33.40 examples/s]
preprocess datasets:  20%|██        | 4023/20000 [01:06<06:46, 39.27 examples/s]
preprocess datasets:  20%|██        | 4031/20000 [01:06<05:59, 44.46 examples/s]
preprocess datasets:  20%|██        | 4040/20000 [01:06<05:14, 50.71 examples/s]
preprocess datasets:  20%|██        | 4051/20000 [01:06<04:25, 60.16 examples/s]
preprocess datasets:  20%|██        | 4060/20000 [01:06<04:13, 62.91 examples/s]
preprocess datasets:  20%|██        | 4069/20000 [01:06<03:57, 67.13 examples/s]
preprocess datasets:  20%|██        | 4079/20000 [01:06<03:42, 71.68 examples/s]
preprocess datasets:  20%|██        | 4093/20000 [01:07<03:06, 85.35 examples/s]
preprocess datasets:  21%|██        | 4107/20000 [01:07<03:05, 85.71 examples/s]
preprocess datasets:  21%|██        | 4117/20000 [01:07<03:02, 87.06 examples/s]
preprocess datasets:  21%|██        | 4127/20000 [01:07<03:08, 84.17 examples/s]
preprocess datasets:  21%|██        | 4136/20000 [01:07<03:08, 84.10 examples/s]
preprocess datasets:  21%|██        | 4145/20000 [01:07<03:06, 84.95 examples/s]
preprocess datasets:  21%|██        | 4154/20000 [01:07<03:07, 84.37 examples/s]
preprocess datasets:  21%|██        | 4164/20000 [01:07<03:27, 76.37 examples/s]
preprocess datasets:  21%|██        | 4174/20000 [01:08<03:56, 66.85 examples/s]
preprocess datasets:  21%|██        | 4182/20000 [01:08<03:57, 66.70 examples/s]
preprocess datasets:  21%|██        | 4191/20000 [01:08<03:45, 70.20 examples/s]
preprocess datasets:  21%|██        | 4204/20000 [01:08<03:10, 82.75 examples/s]
preprocess datasets:  21%|██        | 4213/20000 [01:08<05:27, 48.13 examples/s]
preprocess datasets:  21%|██        | 4224/20000 [01:08<04:38, 56.72 examples/s]
preprocess datasets:  21%|██        | 4232/20000 [01:09<04:30, 58.37 examples/s]
preprocess datasets:  21%|██        | 4243/20000 [01:09<04:14, 61.86 examples/s]
preprocess datasets:  21%|██▏       | 4254/20000 [01:09<03:49, 68.62 examples/s]
preprocess datasets:  21%|██▏       | 4266/20000 [01:09<03:27, 75.92 examples/s]
preprocess datasets:  21%|██▏       | 4277/20000 [01:09<03:09, 82.75 examples/s]
preprocess datasets:  21%|██▏       | 4290/20000 [01:09<03:21, 77.80 examples/s]
preprocess datasets:  22%|██▏       | 4302/20000 [01:09<03:09, 83.01 examples/s]
preprocess datasets:  22%|██▏       | 4313/20000 [01:10<03:03, 85.40 examples/s]
preprocess datasets:  22%|██▏       | 4322/20000 [01:10<07:42, 33.90 examples/s]
preprocess datasets:  22%|██▏       | 4332/20000 [01:10<06:20, 41.19 examples/s]
preprocess datasets:  22%|██▏       | 4341/20000 [01:11<05:32, 47.08 examples/s]
preprocess datasets:  22%|██▏       | 4354/20000 [01:11<04:48, 54.28 examples/s]
preprocess datasets:  22%|██▏       | 4362/20000 [01:11<04:28, 58.32 examples/s]
preprocess datasets:  22%|██▏       | 4370/20000 [01:11<04:13, 61.58 examples/s]
preprocess datasets:  22%|██▏       | 4379/20000 [01:11<03:57, 65.84 examples/s]
preprocess datasets:  22%|██▏       | 4390/20000 [01:11<03:56, 66.11 examples/s]
preprocess datasets:  22%|██▏       | 4399/20000 [01:12<05:35, 46.49 examples/s]
preprocess datasets:  22%|██▏       | 4409/20000 [01:12<04:48, 54.11 examples/s]
preprocess datasets:  22%|██▏       | 4421/20000 [01:12<03:56, 65.93 examples/s]
preprocess datasets:  22%|██▏       | 4431/20000 [01:12<03:44, 69.25 examples/s]
preprocess datasets:  22%|██▏       | 4442/20000 [01:12<03:32, 73.36 examples/s]
preprocess datasets:  22%|██▏       | 4451/20000 [01:12<03:28, 74.65 examples/s]
preprocess datasets:  22%|██▏       | 4462/20000 [01:12<03:31, 73.41 examples/s]
preprocess datasets:  22%|██▏       | 4471/20000 [01:12<03:52, 66.73 examples/s]
preprocess datasets:  22%|██▏       | 4481/20000 [01:13<03:40, 70.44 examples/s]
preprocess datasets:  22%|██▏       | 4489/20000 [01:13<03:51, 66.99 examples/s]
preprocess datasets:  22%|██▏       | 4498/20000 [01:13<03:43, 69.38 examples/s]
preprocess datasets:  23%|██▎       | 4508/20000 [01:13<03:27, 74.81 examples/s]
preprocess datasets:  23%|██▎       | 4518/20000 [01:13<03:22, 76.62 examples/s]
preprocess datasets:  23%|██▎       | 4526/20000 [01:13<03:22, 76.55 examples/s]
preprocess datasets:  23%|██▎       | 4538/20000 [01:13<03:05, 83.47 examples/s]
preprocess datasets:  23%|██▎       | 4547/20000 [01:13<03:18, 77.79 examples/s]
preprocess datasets:  23%|██▎       | 4556/20000 [01:14<03:17, 78.39 examples/s]
preprocess datasets:  23%|██▎       | 4565/20000 [01:14<03:14, 79.52 examples/s]
preprocess datasets:  23%|██▎       | 4574/20000 [01:14<03:12, 80.12 examples/s]
preprocess datasets:  23%|██▎       | 4585/20000 [01:14<03:24, 75.50 examples/s]
preprocess datasets:  23%|██▎       | 4593/20000 [01:14<03:27, 74.24 examples/s]
preprocess datasets:  23%|██▎       | 4601/20000 [01:14<03:33, 72.27 examples/s]
preprocess datasets:  23%|██▎       | 4612/20000 [01:14<03:18, 77.66 examples/s]
preprocess datasets:  23%|██▎       | 4623/20000 [01:14<03:05, 82.85 examples/s]
preprocess datasets:  23%|██▎       | 4635/20000 [01:15<03:19, 76.89 examples/s]
preprocess datasets:  23%|██▎       | 4648/20000 [01:15<03:02, 84.16 examples/s]
preprocess datasets:  23%|██▎       | 4659/20000 [01:15<02:57, 86.39 examples/s]
preprocess datasets:  23%|██▎       | 4670/20000 [01:15<02:56, 86.88 examples/s]
preprocess datasets:  23%|██▎       | 4680/20000 [01:15<02:56, 86.82 examples/s]
preprocess datasets:  23%|██▎       | 4692/20000 [01:15<03:09, 80.73 examples/s]
preprocess datasets:  24%|██▎       | 4702/20000 [01:15<03:06, 81.95 examples/s]
preprocess datasets:  24%|██▎       | 4713/20000 [01:15<02:58, 85.45 examples/s]
preprocess datasets:  24%|██▎       | 4722/20000 [01:16<03:02, 83.92 examples/s]
preprocess datasets:  24%|██▎       | 4732/20000 [01:16<03:01, 83.94 examples/s]
preprocess datasets:  24%|██▎       | 4743/20000 [01:16<02:57, 86.07 examples/s]
preprocess datasets:  24%|██▍       | 4756/20000 [01:16<02:47, 91.22 examples/s]
preprocess datasets:  24%|██▍       | 4771/20000 [01:16<02:47, 91.06 examples/s]
preprocess datasets:  24%|██▍       | 4782/20000 [01:16<02:47, 90.87 examples/s]
preprocess datasets:  24%|██▍       | 4792/20000 [01:16<02:49, 89.84 examples/s]
preprocess datasets:  24%|██▍       | 4803/20000 [01:16<02:46, 91.22 examples/s]
preprocess datasets:  24%|██▍       | 4821/20000 [01:17<02:38, 95.62 examples/s]
preprocess datasets:  24%|██▍       | 4833/20000 [01:17<02:58, 84.85 examples/s]
preprocess datasets:  24%|██▍       | 4845/20000 [01:17<03:07, 80.99 examples/s]
preprocess datasets:  24%|██▍       | 4855/20000 [01:17<03:05, 81.56 examples/s]
preprocess datasets:  24%|██▍       | 4866/20000 [01:18<06:23, 39.48 examples/s]
preprocess datasets:  24%|██▍       | 4874/20000 [01:18<08:23, 30.02 examples/s]
preprocess datasets:  24%|██▍       | 4887/20000 [01:18<06:14, 40.34 examples/s]
preprocess datasets:  24%|██▍       | 4895/20000 [01:18<05:34, 45.11 examples/s]
preprocess datasets:  25%|██▍       | 4906/20000 [01:19<04:37, 54.32 examples/s]
preprocess datasets:  25%|██▍       | 4919/20000 [01:19<03:46, 66.55 examples/s]
preprocess datasets:  25%|██▍       | 4932/20000 [01:19<03:43, 67.32 examples/s]
preprocess datasets:  25%|██▍       | 4941/20000 [01:19<03:36, 69.50 examples/s]
preprocess datasets:  25%|██▍       | 4950/20000 [01:19<03:28, 72.08 examples/s]
preprocess datasets:  25%|██▍       | 4961/20000 [01:19<03:11, 78.48 examples/s]
preprocess datasets:  25%|██▍       | 4972/20000 [01:19<03:25, 73.02 examples/s]
preprocess datasets:  25%|██▍       | 4981/20000 [01:19<03:19, 75.18 examples/s]
preprocess datasets:  25%|██▍       | 4991/20000 [01:20<03:10, 78.59 examples/s]
preprocess datasets:  25%|██▌       | 5000/20000 [01:20<08:55, 27.99 examples/s]
preprocess datasets:  25%|██▌       | 5008/20000 [01:21<07:27, 33.47 examples/s]
preprocess datasets:  25%|██▌       | 5018/20000 [01:21<06:04, 41.05 examples/s]
preprocess datasets:  25%|██▌       | 5029/20000 [01:21<04:51, 51.40 examples/s]
preprocess datasets:  25%|██▌       | 5038/20000 [01:21<04:30, 55.30 examples/s]
preprocess datasets:  25%|██▌       | 5047/20000 [01:21<04:09, 60.02 examples/s]
preprocess datasets:  25%|██▌       | 5059/20000 [01:21<03:35, 69.19 examples/s]
preprocess datasets:  25%|██▌       | 5070/20000 [01:21<03:41, 67.31 examples/s]
preprocess datasets:  25%|██▌       | 5081/20000 [01:21<03:22, 73.80 examples/s]
preprocess datasets:  25%|██▌       | 5090/20000 [01:22<03:14, 76.46 examples/s]
preprocess datasets:  26%|██▌       | 5103/20000 [01:22<03:17, 75.60 examples/s]
preprocess datasets:  26%|██▌       | 5114/20000 [01:22<03:03, 81.03 examples/s]
preprocess datasets:  26%|██▌       | 5125/20000 [01:22<03:23, 73.15 examples/s]
preprocess datasets:  26%|██▌       | 5136/20000 [01:22<03:16, 75.71 examples/s]
preprocess datasets:  26%|██▌       | 5145/20000 [01:22<03:14, 76.52 examples/s]
preprocess datasets:  26%|██▌       | 5156/20000 [01:22<03:03, 81.01 examples/s]
preprocess datasets:  26%|██▌       | 5167/20000 [01:22<02:48, 87.85 examples/s]
preprocess datasets:  26%|██▌       | 5179/20000 [01:23<03:04, 80.22 examples/s]
preprocess datasets:  26%|██▌       | 5188/20000 [01:23<03:06, 79.58 examples/s]
preprocess datasets:  26%|██▌       | 5200/20000 [01:23<03:18, 74.55 examples/s]
preprocess datasets:  26%|██▌       | 5209/20000 [01:23<03:22, 72.98 examples/s]
preprocess datasets:  26%|██▌       | 5217/20000 [01:23<03:20, 73.87 examples/s]
preprocess datasets:  26%|██▌       | 5227/20000 [01:23<03:12, 76.90 examples/s]
preprocess datasets:  26%|██▌       | 5237/20000 [01:23<03:15, 75.69 examples/s]
preprocess datasets:  26%|██▌       | 5247/20000 [01:24<03:08, 78.19 examples/s]
preprocess datasets:  26%|██▋       | 5257/20000 [01:24<03:10, 77.35 examples/s]
preprocess datasets:  26%|██▋       | 5265/20000 [01:24<03:14, 75.57 examples/s]
preprocess datasets:  26%|██▋       | 5273/20000 [01:24<03:23, 72.41 examples/s]
preprocess datasets:  26%|██▋       | 5283/20000 [01:24<03:21, 73.02 examples/s]
preprocess datasets:  26%|██▋       | 5292/20000 [01:24<03:18, 74.03 examples/s]
preprocess datasets:  26%|██▋       | 5300/20000 [01:24<03:19, 73.58 examples/s]
preprocess datasets:  27%|██▋       | 5309/20000 [01:24<03:09, 77.44 examples/s]
preprocess datasets:  27%|██▋       | 5320/20000 [01:25<02:54, 83.90 examples/s]
preprocess datasets:  27%|██▋       | 5329/20000 [01:25<02:54, 84.25 examples/s]
preprocess datasets:  27%|██▋       | 5340/20000 [01:25<03:14, 75.19 examples/s]
preprocess datasets:  27%|██▋       | 5353/20000 [01:25<03:18, 73.63 examples/s]
preprocess datasets:  27%|██▋       | 5364/20000 [01:25<03:02, 80.26 examples/s]
preprocess datasets:  27%|██▋       | 5379/20000 [01:25<02:38, 92.21 examples/s]
preprocess datasets:  27%|██▋       | 5394/20000 [01:25<02:44, 89.00 examples/s]
preprocess datasets:  27%|██▋       | 5406/20000 [01:26<03:00, 80.74 examples/s]
preprocess datasets:  27%|██▋       | 5419/20000 [01:26<02:47, 87.09 examples/s]
preprocess datasets:  27%|██▋       | 5429/20000 [01:26<02:49, 86.04 examples/s]
preprocess datasets:  27%|██▋       | 5438/20000 [01:26<02:57, 82.16 examples/s]
preprocess datasets:  27%|██▋       | 5447/20000 [01:26<03:00, 80.80 examples/s]
preprocess datasets:  27%|██▋       | 5460/20000 [01:26<03:08, 77.15 examples/s]
preprocess datasets:  27%|██▋       | 5468/20000 [01:26<03:13, 75.06 examples/s]
preprocess datasets:  27%|██▋       | 5481/20000 [01:27<03:20, 72.43 examples/s]
preprocess datasets:  27%|██▋       | 5490/20000 [01:27<03:14, 74.51 examples/s]
preprocess datasets:  28%|██▊       | 5501/20000 [01:27<03:11, 75.91 examples/s]
preprocess datasets:  28%|██▊       | 5512/20000 [01:27<03:23, 71.26 examples/s]
preprocess datasets:  28%|██▊       | 5522/20000 [01:27<03:12, 75.09 examples/s]
preprocess datasets:  28%|██▊       | 5530/20000 [01:27<03:18, 72.74 examples/s]
preprocess datasets:  28%|██▊       | 5539/20000 [01:27<03:08, 76.58 examples/s]
preprocess datasets:  28%|██▊       | 5550/20000 [01:27<03:23, 70.88 examples/s]
preprocess datasets:  28%|██▊       | 5560/20000 [01:28<04:24, 54.65 examples/s]
preprocess datasets:  28%|██▊       | 5571/20000 [01:28<03:54, 61.54 examples/s]
preprocess datasets:  28%|██▊       | 5579/20000 [01:28<04:20, 55.46 examples/s]
preprocess datasets:  28%|██▊       | 5586/20000 [01:28<04:18, 55.77 examples/s]
preprocess datasets:  28%|██▊       | 5597/20000 [01:28<03:46, 63.72 examples/s]
preprocess datasets:  28%|██▊       | 5606/20000 [01:28<03:28, 68.97 examples/s]
preprocess datasets:  28%|██▊       | 5616/20000 [01:29<03:15, 73.43 examples/s]
preprocess datasets:  28%|██▊       | 5629/20000 [01:29<02:49, 84.68 examples/s]
preprocess datasets:  28%|██▊       | 5640/20000 [01:29<03:14, 73.95 examples/s]
preprocess datasets:  28%|██▊       | 5650/20000 [01:29<03:06, 76.96 examples/s]
preprocess datasets:  28%|██▊       | 5664/20000 [01:29<03:04, 77.80 examples/s]
preprocess datasets:  28%|██▊       | 5673/20000 [01:29<03:04, 77.73 examples/s]
preprocess datasets:  28%|██▊       | 5681/20000 [01:29<03:05, 77.13 examples/s]
preprocess datasets:  28%|██▊       | 5694/20000 [01:29<02:46, 86.02 examples/s]
preprocess datasets:  29%|██▊       | 5706/20000 [01:30<02:40, 89.22 examples/s]
preprocess datasets:  29%|██▊       | 5717/20000 [01:30<02:55, 81.34 examples/s]
preprocess datasets:  29%|██▊       | 5726/20000 [01:30<02:58, 79.96 examples/s]
preprocess datasets:  29%|██▊       | 5736/20000 [01:30<02:55, 81.20 examples/s]
preprocess datasets:  29%|██▊       | 5748/20000 [01:30<02:42, 87.59 examples/s]
preprocess datasets:  29%|██▉       | 5763/20000 [01:30<02:46, 85.50 examples/s]
preprocess datasets:  29%|██▉       | 5777/20000 [01:30<02:29, 95.28 examples/s]
preprocess datasets:  29%|██▉       | 5789/20000 [01:31<02:45, 85.73 examples/s]
preprocess datasets:  29%|██▉       | 5800/20000 [01:31<02:41, 87.85 examples/s]
preprocess datasets:  29%|██▉       | 5812/20000 [01:31<02:38, 89.59 examples/s]
preprocess datasets:  29%|██▉       | 5825/20000 [01:31<02:48, 83.96 examples/s]
preprocess datasets:  29%|██▉       | 5836/20000 [01:31<02:43, 86.78 examples/s]
preprocess datasets:  29%|██▉       | 5846/20000 [01:31<02:46, 85.24 examples/s]
preprocess datasets:  29%|██▉       | 5856/20000 [01:31<02:42, 86.84 examples/s]
preprocess datasets:  29%|██▉       | 5866/20000 [01:31<02:42, 86.82 examples/s]
preprocess datasets:  29%|██▉       | 5875/20000 [01:32<02:48, 83.73 examples/s]
preprocess datasets:  29%|██▉       | 5886/20000 [01:32<03:06, 75.75 examples/s]
preprocess datasets:  29%|██▉       | 5897/20000 [01:32<03:16, 71.91 examples/s]
preprocess datasets:  30%|██▉       | 5908/20000 [01:32<03:02, 77.30 examples/s]
preprocess datasets:  30%|██▉       | 5917/20000 [01:32<02:57, 79.23 examples/s]
preprocess datasets:  30%|██▉       | 5926/20000 [01:32<02:55, 80.08 examples/s]
preprocess datasets:  30%|██▉       | 5935/20000 [01:32<02:54, 80.41 examples/s]
preprocess datasets:  30%|██▉       | 5952/20000 [01:33<02:22, 98.51 examples/s]
preprocess datasets:  30%|██▉       | 5963/20000 [01:33<02:27, 95.18 examples/s]
preprocess datasets:  30%|██▉       | 5974/20000 [01:33<02:50, 82.14 examples/s]
preprocess datasets:  30%|██▉       | 5984/20000 [01:33<02:50, 82.32 examples/s]
preprocess datasets:  30%|██▉       | 5993/20000 [01:33<02:54, 80.17 examples/s]
preprocess datasets:  30%|███       | 6005/20000 [01:34<07:58, 29.22 examples/s]
preprocess datasets:  30%|███       | 6018/20000 [01:34<06:02, 38.54 examples/s]
preprocess datasets:  30%|███       | 6030/20000 [01:34<05:08, 45.25 examples/s]
preprocess datasets:  30%|███       | 6042/20000 [01:34<04:34, 50.77 examples/s]
preprocess datasets:  30%|███       | 6050/20000 [01:35<05:32, 42.01 examples/s]
preprocess datasets:  30%|███       | 6062/20000 [01:35<04:26, 52.34 examples/s]
preprocess datasets:  30%|███       | 6072/20000 [01:35<03:54, 59.43 examples/s]
preprocess datasets:  30%|███       | 6082/20000 [01:35<03:34, 64.78 examples/s]
preprocess datasets:  30%|███       | 6093/20000 [01:35<03:11, 72.51 examples/s]
preprocess datasets:  31%|███       | 6106/20000 [01:35<02:52, 80.44 examples/s]
preprocess datasets:  31%|███       | 6117/20000 [01:35<02:50, 81.29 examples/s]
preprocess datasets:  31%|███       | 6127/20000 [01:36<02:47, 82.75 examples/s]
preprocess datasets:  31%|███       | 6138/20000 [01:36<02:44, 84.49 examples/s]
preprocess datasets:  31%|███       | 6148/20000 [01:36<02:46, 82.97 examples/s]
preprocess datasets:  31%|███       | 6159/20000 [01:36<02:41, 85.59 examples/s]
preprocess datasets:  31%|███       | 6172/20000 [01:36<02:51, 80.71 examples/s]
preprocess datasets:  31%|███       | 6186/20000 [01:36<02:32, 90.35 examples/s]
preprocess datasets:  31%|███       | 6196/20000 [01:36<02:33, 90.16 examples/s]
preprocess datasets:  31%|███       | 6209/20000 [01:37<02:44, 83.70 examples/s]
preprocess datasets:  31%|███       | 6219/20000 [01:37<02:39, 86.38 examples/s]
preprocess datasets:  31%|███       | 6229/20000 [01:37<02:40, 85.91 examples/s]
preprocess datasets:  31%|███       | 6239/20000 [01:37<02:41, 85.29 examples/s]
preprocess datasets:  31%|███       | 6248/20000 [01:37<02:46, 82.50 examples/s]
preprocess datasets:  31%|███▏      | 6258/20000 [01:37<02:50, 80.62 examples/s]
preprocess datasets:  31%|███▏      | 6267/20000 [01:37<02:51, 79.90 examples/s]
preprocess datasets:  31%|███▏      | 6277/20000 [01:37<02:47, 82.15 examples/s]
preprocess datasets:  31%|███▏      | 6286/20000 [01:37<02:54, 78.59 examples/s]
preprocess datasets:  32%|███▏      | 6300/20000 [01:38<02:32, 89.76 examples/s]
preprocess datasets:  32%|███▏      | 6313/20000 [01:38<02:45, 82.62 examples/s]
preprocess datasets:  32%|███▏      | 6324/20000 [01:38<02:37, 86.87 examples/s]
preprocess datasets:  32%|███▏      | 6333/20000 [01:38<02:52, 79.09 examples/s]
preprocess datasets:  32%|███▏      | 6343/20000 [01:38<02:46, 81.93 examples/s]
preprocess datasets:  32%|███▏      | 6352/20000 [01:38<03:00, 75.46 examples/s]
preprocess datasets:  32%|███▏      | 6362/20000 [01:38<02:57, 76.95 examples/s]
preprocess datasets:  32%|███▏      | 6373/20000 [01:39<02:54, 78.29 examples/s]
preprocess datasets:  32%|███▏      | 6385/20000 [01:39<02:42, 83.55 examples/s]
preprocess datasets:  32%|███▏      | 6396/20000 [01:39<02:36, 86.98 examples/s]
preprocess datasets:  32%|███▏      | 6409/20000 [01:39<02:38, 85.83 examples/s]
preprocess datasets:  32%|███▏      | 6420/20000 [01:39<02:29, 91.11 examples/s]
preprocess datasets:  32%|███▏      | 6431/20000 [01:39<02:31, 89.53 examples/s]
preprocess datasets:  32%|███▏      | 6447/20000 [01:39<02:28, 91.28 examples/s]
preprocess datasets:  32%|███▏      | 6457/20000 [01:39<02:34, 87.45 examples/s]
preprocess datasets:  32%|███▏      | 6467/20000 [01:40<02:44, 82.27 examples/s]
preprocess datasets:  32%|███▏      | 6478/20000 [01:40<02:35, 86.85 examples/s]
preprocess datasets:  32%|███▏      | 6492/20000 [01:40<02:44, 81.88 examples/s]
preprocess datasets:  33%|███▎      | 6501/20000 [01:40<02:48, 80.31 examples/s]
preprocess datasets:  33%|███▎      | 6510/20000 [01:40<02:47, 80.50 examples/s]
preprocess datasets:  33%|███▎      | 6520/20000 [01:40<02:43, 82.43 examples/s]
preprocess datasets:  33%|███▎      | 6533/20000 [01:40<02:31, 88.65 examples/s]
preprocess datasets:  33%|███▎      | 6543/20000 [01:41<02:32, 88.22 examples/s]
preprocess datasets:  33%|███▎      | 6557/20000 [01:41<02:40, 84.00 examples/s]
preprocess datasets:  33%|███▎      | 6567/20000 [01:41<02:39, 84.30 examples/s]
preprocess datasets:  33%|███▎      | 6576/20000 [01:41<02:45, 81.25 examples/s]
preprocess datasets:  33%|███▎      | 6589/20000 [01:41<02:49, 79.08 examples/s]
preprocess datasets:  33%|███▎      | 6597/20000 [01:42<04:50, 46.08 examples/s]
preprocess datasets:  33%|███▎      | 6608/20000 [01:42<04:02, 55.15 examples/s]
preprocess datasets:  33%|███▎      | 6618/20000 [01:42<03:34, 62.43 examples/s]
preprocess datasets:  33%|███▎      | 6628/20000 [01:42<03:20, 66.72 examples/s]
preprocess datasets:  33%|███▎      | 6641/20000 [01:42<02:57, 75.34 examples/s]
preprocess datasets:  33%|███▎      | 6651/20000 [01:42<02:50, 78.07 examples/s]
preprocess datasets:  33%|███▎      | 6662/20000 [01:42<02:52, 77.48 examples/s]
preprocess datasets:  33%|███▎      | 6671/20000 [01:42<03:16, 67.90 examples/s]
preprocess datasets:  33%|███▎      | 6680/20000 [01:43<03:08, 70.70 examples/s]
preprocess datasets:  33%|███▎      | 6693/20000 [01:43<03:06, 71.36 examples/s]
preprocess datasets:  34%|███▎      | 6703/20000 [01:43<03:03, 72.41 examples/s]
preprocess datasets:  34%|███▎      | 6713/20000 [01:43<02:57, 74.65 examples/s]
preprocess datasets:  34%|███▎      | 6724/20000 [01:43<02:41, 82.30 examples/s]
preprocess datasets:  34%|███▎      | 6733/20000 [01:43<02:39, 83.01 examples/s]
preprocess datasets:  34%|███▎      | 6743/20000 [01:43<02:46, 79.44 examples/s]
preprocess datasets:  34%|███▍      | 6754/20000 [01:44<03:42, 59.58 examples/s]
preprocess datasets:  34%|███▍      | 6763/20000 [01:44<03:37, 60.79 examples/s]
preprocess datasets:  34%|███▍      | 6776/20000 [01:44<02:58, 73.90 examples/s]
preprocess datasets:  34%|███▍      | 6786/20000 [01:44<02:49, 77.75 examples/s]
preprocess datasets:  34%|███▍      | 6797/20000 [01:44<02:59, 73.54 examples/s]
preprocess datasets:  34%|███▍      | 6808/20000 [01:44<02:44, 80.43 examples/s]
preprocess datasets:  34%|███▍      | 6818/20000 [01:44<02:40, 81.89 examples/s]
preprocess datasets:  34%|███▍      | 6832/20000 [01:44<02:19, 94.13 examples/s]
preprocess datasets:  34%|███▍      | 6847/20000 [01:45<02:22, 92.49 examples/s]
preprocess datasets:  34%|███▍      | 6859/20000 [01:45<02:34, 84.99 examples/s]
preprocess datasets:  34%|███▍      | 6874/20000 [01:45<02:16, 96.18 examples/s]
preprocess datasets:  34%|███▍      | 6890/20000 [01:45<02:20, 93.61 examples/s]
preprocess datasets:  35%|███▍      | 6902/20000 [01:45<02:29, 87.60 examples/s]
preprocess datasets:  35%|███▍      | 6912/20000 [01:45<02:29, 87.75 examples/s]
preprocess datasets:  35%|███▍      | 6923/20000 [01:46<02:26, 89.02 examples/s]
preprocess datasets:  35%|███▍      | 6934/20000 [01:46<02:42, 80.32 examples/s]
preprocess datasets:  35%|███▍      | 6947/20000 [01:46<02:46, 78.49 examples/s]
preprocess datasets:  35%|███▍      | 6960/20000 [01:46<02:47, 77.76 examples/s]
preprocess datasets:  35%|███▍      | 6969/20000 [01:46<02:43, 79.71 examples/s]
preprocess datasets:  35%|███▍      | 6979/20000 [01:46<02:58, 73.04 examples/s]
preprocess datasets:  35%|███▍      | 6991/20000 [01:46<02:39, 81.31 examples/s]
preprocess datasets:  35%|███▌      | 7000/20000 [01:47<07:47, 27.80 examples/s]
preprocess datasets:  35%|███▌      | 7011/20000 [01:47<06:05, 35.58 examples/s]
preprocess datasets:  35%|███▌      | 7023/20000 [01:48<05:02, 42.91 examples/s]
preprocess datasets:  35%|███▌      | 7033/20000 [01:48<04:41, 46.09 examples/s]
preprocess datasets:  35%|███▌      | 7040/20000 [01:48<04:32, 47.56 examples/s]
preprocess datasets:  35%|███▌      | 7048/20000 [01:48<04:06, 52.49 examples/s]
preprocess datasets:  35%|███▌      | 7057/20000 [01:48<03:40, 58.70 examples/s]
preprocess datasets:  35%|███▌      | 7074/20000 [01:48<02:47, 77.37 examples/s]
preprocess datasets:  35%|███▌      | 7087/20000 [01:48<02:47, 76.93 examples/s]
preprocess datasets:  35%|███▌      | 7096/20000 [01:49<02:46, 77.55 examples/s]
preprocess datasets:  36%|███▌      | 7110/20000 [01:49<02:47, 76.89 examples/s]
preprocess datasets:  36%|███▌      | 7122/20000 [01:49<02:32, 84.41 examples/s]
preprocess datasets:  36%|███▌      | 7131/20000 [01:49<02:34, 83.55 examples/s]
preprocess datasets:  36%|███▌      | 7148/20000 [01:49<02:22, 90.05 examples/s]
preprocess datasets:  36%|███▌      | 7158/20000 [01:49<02:26, 87.92 examples/s]
preprocess datasets:  36%|███▌      | 7168/20000 [01:49<02:43, 78.28 examples/s]
preprocess datasets:  36%|███▌      | 7181/20000 [01:50<02:43, 78.29 examples/s]
preprocess datasets:  36%|███▌      | 7190/20000 [01:50<02:42, 78.81 examples/s]
preprocess datasets:  36%|███▌      | 7201/20000 [01:50<02:57, 72.24 examples/s]
preprocess datasets:  36%|███▌      | 7209/20000 [01:50<03:05, 69.11 examples/s]
preprocess datasets:  36%|███▌      | 7217/20000 [01:50<03:06, 68.39 examples/s]
preprocess datasets:  36%|███▌      | 7229/20000 [01:50<02:39, 80.09 examples/s]
preprocess datasets:  36%|███▌      | 7240/20000 [01:50<03:00, 70.60 examples/s]
preprocess datasets:  36%|███▌      | 7248/20000 [01:51<03:02, 70.02 examples/s]
preprocess datasets:  36%|███▋      | 7256/20000 [01:51<02:59, 71.15 examples/s]
preprocess datasets:  36%|███▋      | 7267/20000 [01:51<02:45, 76.92 examples/s]
preprocess datasets:  36%|███▋      | 7276/20000 [01:51<02:44, 77.43 examples/s]
preprocess datasets:  36%|███▋      | 7287/20000 [01:51<02:34, 82.27 examples/s]
preprocess datasets:  36%|███▋      | 7299/20000 [01:51<02:22, 89.07 examples/s]
preprocess datasets:  37%|███▋      | 7312/20000 [01:51<02:16, 93.08 examples/s]
preprocess datasets:  37%|███▋      | 7324/20000 [01:51<02:13, 94.86 examples/s]
preprocess datasets:  37%|███▋      | 7335/20000 [01:51<02:10, 97.09 examples/s]
preprocess datasets:  37%|███▋      | 7349/20000 [01:52<02:04, 102.01 examples/s]
preprocess datasets:  37%|███▋      | 7362/20000 [01:52<02:01, 104.28 examples/s]
preprocess datasets:  37%|███▋      | 7380/20000 [01:52<01:57, 107.41 examples/s]
preprocess datasets:  37%|███▋      | 7393/20000 [01:52<01:53, 111.26 examples/s]
preprocess datasets:  37%|███▋      | 7405/20000 [01:52<01:53, 111.44 examples/s]
preprocess datasets:  37%|███▋      | 7418/20000 [01:52<02:06, 99.10 examples/s] 
preprocess datasets:  37%|███▋      | 7431/20000 [01:52<02:16, 91.77 examples/s]
preprocess datasets:  37%|███▋      | 7441/20000 [01:53<02:21, 88.95 examples/s]
preprocess datasets:  37%|███▋      | 7457/20000 [01:53<02:17, 91.25 examples/s]
preprocess datasets:  37%|███▋      | 7470/20000 [01:53<02:06, 99.11 examples/s]
preprocess datasets:  37%|███▋      | 7481/20000 [01:53<02:23, 87.01 examples/s]
preprocess datasets:  37%|███▋      | 7494/20000 [01:53<02:35, 80.63 examples/s]
preprocess datasets:  38%|███▊      | 7505/20000 [01:53<02:24, 86.38 examples/s]
preprocess datasets:  38%|███▊      | 7521/20000 [01:53<02:18, 90.41 examples/s]
preprocess datasets:  38%|███▊      | 7533/20000 [01:54<02:16, 91.63 examples/s]
preprocess datasets:  38%|███▊      | 7544/20000 [01:54<02:12, 93.76 examples/s]
preprocess datasets:  38%|███▊      | 7558/20000 [01:54<02:22, 87.10 examples/s]
preprocess datasets:  38%|███▊      | 7569/20000 [01:54<02:20, 88.17 examples/s]
preprocess datasets:  38%|███▊      | 7581/20000 [01:54<02:11, 94.71 examples/s]
preprocess datasets:  38%|███▊      | 7594/20000 [01:54<02:06, 98.28 examples/s]
preprocess datasets:  38%|███▊      | 7606/20000 [01:54<02:20, 88.38 examples/s]
preprocess datasets:  38%|███▊      | 7617/20000 [01:55<02:37, 78.84 examples/s]
preprocess datasets:  38%|███▊      | 7626/20000 [01:55<02:55, 70.62 examples/s]
preprocess datasets:  38%|███▊      | 7635/20000 [01:55<02:52, 71.85 examples/s]
preprocess datasets:  38%|███▊      | 7645/20000 [01:55<02:42, 76.25 examples/s]
preprocess datasets:  38%|███▊      | 7655/20000 [01:55<02:56, 70.05 examples/s]
preprocess datasets:  38%|███▊      | 7664/20000 [01:55<02:52, 71.34 examples/s]
preprocess datasets:  38%|███▊      | 7673/20000 [01:55<02:51, 72.03 examples/s]
preprocess datasets:  38%|███▊      | 7681/20000 [01:55<02:47, 73.62 examples/s]
preprocess datasets:  38%|███▊      | 7690/20000 [01:56<03:06, 66.04 examples/s]
preprocess datasets:  38%|███▊      | 7697/20000 [01:56<03:09, 64.77 examples/s]
preprocess datasets:  39%|███▊      | 7706/20000 [01:56<02:59, 68.30 examples/s]
preprocess datasets:  39%|███▊      | 7715/20000 [01:56<02:54, 70.47 examples/s]
preprocess datasets:  39%|███▊      | 7726/20000 [01:56<02:36, 78.19 examples/s]
preprocess datasets:  39%|███▊      | 7735/20000 [01:56<02:40, 76.54 examples/s]
preprocess datasets:  39%|███▊      | 7744/20000 [01:56<02:39, 76.63 examples/s]
preprocess datasets:  39%|███▉      | 7753/20000 [01:56<02:41, 75.83 examples/s]
preprocess datasets:  39%|███▉      | 7764/20000 [01:57<02:30, 81.10 examples/s]
preprocess datasets:  39%|███▉      | 7776/20000 [01:57<02:37, 77.80 examples/s]
preprocess datasets:  39%|███▉      | 7786/20000 [01:57<02:30, 81.14 examples/s]
preprocess datasets:  39%|███▉      | 7799/20000 [01:57<02:21, 86.32 examples/s]
preprocess datasets:  39%|███▉      | 7809/20000 [01:57<02:19, 87.36 examples/s]
preprocess datasets:  39%|███▉      | 7822/20000 [01:57<02:11, 92.29 examples/s]
preprocess datasets:  39%|███▉      | 7832/20000 [01:57<02:16, 88.94 examples/s]
preprocess datasets:  39%|███▉      | 7841/20000 [01:57<02:24, 84.11 examples/s]
preprocess datasets:  39%|███▉      | 7850/20000 [01:58<02:27, 82.23 examples/s]
preprocess datasets:  39%|███▉      | 7860/20000 [01:58<02:29, 81.27 examples/s]
preprocess datasets:  39%|███▉      | 7872/20000 [01:58<02:23, 84.74 examples/s]
preprocess datasets:  39%|███▉      | 7883/20000 [01:58<02:21, 85.67 examples/s]
preprocess datasets:  39%|███▉      | 7892/20000 [01:58<02:27, 81.96 examples/s]
preprocess datasets:  40%|███▉      | 7905/20000 [01:58<02:14, 89.70 examples/s]
preprocess datasets:  40%|███▉      | 7914/20000 [01:58<02:21, 85.58 examples/s]
preprocess datasets:  40%|███▉      | 7928/20000 [01:58<02:07, 94.90 examples/s]
preprocess datasets:  40%|███▉      | 7942/20000 [01:59<02:13, 90.12 examples/s]
preprocess datasets:  40%|███▉      | 7954/20000 [01:59<02:28, 81.26 examples/s]
preprocess datasets:  40%|███▉      | 7965/20000 [01:59<02:39, 75.54 examples/s]
preprocess datasets:  40%|███▉      | 7973/20000 [01:59<02:39, 75.19 examples/s]
preprocess datasets:  40%|███▉      | 7982/20000 [01:59<02:40, 74.92 examples/s]
preprocess datasets:  40%|███▉      | 7994/20000 [01:59<02:42, 73.89 examples/s]
preprocess datasets:  40%|████      | 8002/20000 [02:00<07:45, 25.75 examples/s]
preprocess datasets:  40%|████      | 8012/20000 [02:00<06:08, 32.57 examples/s]
preprocess datasets:  40%|████      | 8020/20000 [02:01<05:23, 37.00 examples/s]
preprocess datasets:  40%|████      | 8027/20000 [02:01<04:54, 40.64 examples/s]
preprocess datasets:  40%|████      | 8038/20000 [02:01<03:58, 50.25 examples/s]
preprocess datasets:  40%|████      | 8048/20000 [02:01<03:28, 57.45 examples/s]
preprocess datasets:  40%|████      | 8057/20000 [02:01<03:09, 63.03 examples/s]
preprocess datasets:  40%|████      | 8066/20000 [02:01<02:59, 66.50 examples/s]
preprocess datasets:  40%|████      | 8076/20000 [02:01<02:47, 71.37 examples/s]
preprocess datasets:  40%|████      | 8084/20000 [02:01<02:51, 69.46 examples/s]
preprocess datasets:  40%|████      | 8093/20000 [02:02<02:52, 69.05 examples/s]
preprocess datasets:  41%|████      | 8104/20000 [02:02<02:31, 78.61 examples/s]
preprocess datasets:  41%|████      | 8117/20000 [02:02<02:36, 75.75 examples/s]
preprocess datasets:  41%|████      | 8126/20000 [02:02<02:37, 75.56 examples/s]
preprocess datasets:  41%|████      | 8135/20000 [02:02<02:33, 77.17 examples/s]
preprocess datasets:  41%|████      | 8146/20000 [02:02<02:49, 69.73 examples/s]
preprocess datasets:  41%|████      | 8156/20000 [02:02<02:40, 73.74 examples/s]
preprocess datasets:  41%|████      | 8166/20000 [02:02<02:34, 76.45 examples/s]
preprocess datasets:  41%|████      | 8177/20000 [02:03<02:28, 79.87 examples/s]
preprocess datasets:  41%|████      | 8191/20000 [02:03<02:25, 81.34 examples/s]
preprocess datasets:  41%|████      | 8205/20000 [02:03<02:23, 82.17 examples/s]
preprocess datasets:  41%|████      | 8220/20000 [02:03<02:23, 82.17 examples/s]
preprocess datasets:  41%|████      | 8230/20000 [02:04<04:09, 47.10 examples/s]
preprocess datasets:  41%|████      | 8242/20000 [02:04<03:30, 55.75 examples/s]
preprocess datasets:  41%|████▏     | 8250/20000 [02:04<04:02, 48.45 examples/s]
preprocess datasets:  41%|████▏     | 8261/20000 [02:04<03:30, 55.83 examples/s]
preprocess datasets:  41%|████▏     | 8269/20000 [02:04<03:15, 60.02 examples/s]
preprocess datasets:  41%|████▏     | 8279/20000 [02:04<02:55, 66.63 examples/s]
preprocess datasets:  41%|████▏     | 8290/20000 [02:04<02:35, 75.11 examples/s]
preprocess datasets:  41%|████▏     | 8299/20000 [02:05<02:40, 73.08 examples/s]
preprocess datasets:  42%|████▏     | 8311/20000 [02:05<02:21, 82.38 examples/s]
preprocess datasets:  42%|████▏     | 8322/20000 [02:05<02:16, 85.43 examples/s]
preprocess datasets:  42%|████▏     | 8332/20000 [02:05<02:13, 87.35 examples/s]
preprocess datasets:  42%|████▏     | 8347/20000 [02:05<02:17, 84.81 examples/s]
preprocess datasets:  42%|████▏     | 8361/20000 [02:05<02:16, 85.56 examples/s]
preprocess datasets:  42%|████▏     | 8376/20000 [02:05<01:59, 97.25 examples/s]
preprocess datasets:  42%|████▏     | 8387/20000 [02:05<02:01, 95.67 examples/s]
preprocess datasets:  42%|████▏     | 8398/20000 [02:06<02:05, 92.22 examples/s]
preprocess datasets:  42%|████▏     | 8414/20000 [02:06<01:53, 101.69 examples/s]
preprocess datasets:  42%|████▏     | 8428/20000 [02:06<02:01, 95.06 examples/s] 
preprocess datasets:  42%|████▏     | 8440/20000 [02:06<02:21, 81.50 examples/s]
preprocess datasets:  42%|████▏     | 8450/20000 [02:06<02:17, 84.00 examples/s]
preprocess datasets:  42%|████▏     | 8464/20000 [02:06<02:04, 92.41 examples/s]
preprocess datasets:  42%|████▏     | 8474/20000 [02:06<02:09, 89.14 examples/s]
preprocess datasets:  42%|████▏     | 8485/20000 [02:07<02:05, 91.69 examples/s]
preprocess datasets:  42%|████▏     | 8498/20000 [02:07<02:01, 94.35 examples/s]
preprocess datasets:  43%|████▎     | 8513/20000 [02:07<02:05, 91.58 examples/s]
preprocess datasets:  43%|████▎     | 8523/20000 [02:07<02:08, 89.53 examples/s]
preprocess datasets:  43%|████▎     | 8538/20000 [02:07<02:06, 90.30 examples/s]
preprocess datasets:  43%|████▎     | 8552/20000 [02:07<01:55, 99.54 examples/s]
preprocess datasets:  43%|████▎     | 8565/20000 [02:07<02:09, 88.07 examples/s]
preprocess datasets:  43%|████▎     | 8580/20000 [02:08<02:10, 87.47 examples/s]
preprocess datasets:  43%|████▎     | 8594/20000 [02:08<02:14, 84.97 examples/s]
preprocess datasets:  43%|████▎     | 8607/20000 [02:08<02:01, 93.53 examples/s]
preprocess datasets:  43%|████▎     | 8618/20000 [02:08<02:01, 93.75 examples/s]
preprocess datasets:  43%|████▎     | 8632/20000 [02:08<02:03, 91.80 examples/s]
preprocess datasets:  43%|████▎     | 8642/20000 [02:08<02:22, 79.76 examples/s]
preprocess datasets:  43%|████▎     | 8652/20000 [02:08<02:18, 81.68 examples/s]
preprocess datasets:  43%|████▎     | 8663/20000 [02:09<02:13, 84.89 examples/s]
preprocess datasets:  43%|████▎     | 8676/20000 [02:09<02:18, 81.78 examples/s]
preprocess datasets:  43%|████▎     | 8688/20000 [02:09<02:09, 87.43 examples/s]
preprocess datasets:  44%|████▎     | 8701/20000 [02:09<02:03, 91.30 examples/s]
preprocess datasets:  44%|████▎     | 8715/20000 [02:09<02:11, 85.97 examples/s]
preprocess datasets:  44%|████▎     | 8724/20000 [02:09<02:18, 81.21 examples/s]
preprocess datasets:  44%|████▎     | 8738/20000 [02:09<02:17, 81.65 examples/s]
preprocess datasets:  44%|████▎     | 8748/20000 [02:10<02:14, 83.49 examples/s]
preprocess datasets:  44%|████▍     | 8759/20000 [02:10<02:36, 71.61 examples/s]
preprocess datasets:  44%|████▍     | 8773/20000 [02:10<02:32, 73.71 examples/s]
preprocess datasets:  44%|████▍     | 8786/20000 [02:10<02:20, 79.90 examples/s]
preprocess datasets:  44%|████▍     | 8797/20000 [02:10<02:20, 79.66 examples/s]
preprocess datasets:  44%|████▍     | 8810/20000 [02:10<02:21, 78.95 examples/s]
preprocess datasets:  44%|████▍     | 8819/20000 [02:11<02:21, 78.99 examples/s]
preprocess datasets:  44%|████▍     | 8828/20000 [02:11<02:23, 77.72 examples/s]
preprocess datasets:  44%|████▍     | 8838/20000 [02:11<02:17, 81.18 examples/s]
preprocess datasets:  44%|████▍     | 8847/20000 [02:11<02:15, 82.25 examples/s]
preprocess datasets:  44%|████▍     | 8856/20000 [02:11<02:13, 83.28 examples/s]
preprocess datasets:  44%|████▍     | 8868/20000 [02:11<02:19, 79.64 examples/s]
preprocess datasets:  44%|████▍     | 8880/20000 [02:11<02:21, 78.47 examples/s]
preprocess datasets:  44%|████▍     | 8892/20000 [02:11<02:25, 76.26 examples/s]
preprocess datasets:  45%|████▍     | 8901/20000 [02:12<02:25, 76.42 examples/s]
preprocess datasets:  45%|████▍     | 8914/20000 [02:12<02:09, 85.63 examples/s]
preprocess datasets:  45%|████▍     | 8927/20000 [02:12<02:00, 92.16 examples/s]
preprocess datasets:  45%|████▍     | 8938/20000 [02:12<02:13, 82.95 examples/s]
preprocess datasets:  45%|████▍     | 8951/20000 [02:12<02:03, 89.54 examples/s]
preprocess datasets:  45%|████▍     | 8961/20000 [02:12<02:02, 90.29 examples/s]
preprocess datasets:  45%|████▍     | 8972/20000 [02:12<02:12, 82.94 examples/s]
preprocess datasets:  45%|████▍     | 8988/20000 [02:13<02:07, 86.08 examples/s]
preprocess datasets:  45%|████▍     | 8999/20000 [02:13<02:04, 88.34 examples/s]
preprocess datasets:  45%|████▌     | 9009/20000 [02:14<05:46, 31.75 examples/s]
preprocess datasets:  45%|████▌     | 9019/20000 [02:14<04:45, 38.44 examples/s]
preprocess datasets:  45%|████▌     | 9029/20000 [02:14<04:07, 44.28 examples/s]
preprocess datasets:  45%|████▌     | 9038/20000 [02:14<03:41, 49.59 examples/s]
preprocess datasets:  45%|████▌     | 9050/20000 [02:14<03:05, 59.12 examples/s]
preprocess datasets:  45%|████▌     | 9062/20000 [02:14<02:55, 62.50 examples/s]
preprocess datasets:  45%|████▌     | 9071/20000 [02:14<03:36, 50.58 examples/s]
preprocess datasets:  45%|████▌     | 9083/20000 [02:15<02:56, 61.91 examples/s]
preprocess datasets:  45%|████▌     | 9095/20000 [02:15<06:12, 29.29 examples/s]
preprocess datasets:  46%|████▌     | 9104/20000 [02:16<05:14, 34.70 examples/s]
preprocess datasets:  46%|████▌     | 9113/20000 [02:16<04:28, 40.49 examples/s]
preprocess datasets:  46%|████▌     | 9121/20000 [02:16<04:02, 44.87 examples/s]
preprocess datasets:  46%|████▌     | 9134/20000 [02:16<03:06, 58.14 examples/s]
preprocess datasets:  46%|████▌     | 9145/20000 [02:16<02:46, 65.34 examples/s]
preprocess datasets:  46%|████▌     | 9159/20000 [02:16<02:14, 80.51 examples/s]
preprocess datasets:  46%|████▌     | 9173/20000 [02:16<02:13, 81.38 examples/s]
preprocess datasets:  46%|████▌     | 9183/20000 [02:16<02:12, 81.45 examples/s]
preprocess datasets:  46%|████▌     | 9195/20000 [02:17<02:04, 86.60 examples/s]
preprocess datasets:  46%|████▌     | 9209/20000 [02:17<02:16, 78.81 examples/s]
preprocess datasets:  46%|████▌     | 9224/20000 [02:17<01:56, 92.43 examples/s]
preprocess datasets:  46%|████▌     | 9237/20000 [02:17<02:03, 87.12 examples/s]
preprocess datasets:  46%|████▌     | 9248/20000 [02:17<02:00, 89.07 examples/s]
preprocess datasets:  46%|████▋     | 9265/20000 [02:17<01:55, 92.90 examples/s]
preprocess datasets:  46%|████▋     | 9277/20000 [02:17<01:56, 92.23 examples/s]
preprocess datasets:  46%|████▋     | 9289/20000 [02:18<02:06, 84.51 examples/s]
preprocess datasets:  46%|████▋     | 9299/20000 [02:18<02:09, 82.48 examples/s]
preprocess datasets:  47%|████▋     | 9308/20000 [02:18<02:08, 83.26 examples/s]
preprocess datasets:  47%|████▋     | 9321/20000 [02:18<02:02, 87.04 examples/s]
preprocess datasets:  47%|████▋     | 9330/20000 [02:18<02:06, 84.47 examples/s]
preprocess datasets:  47%|████▋     | 9339/20000 [02:18<02:08, 83.02 examples/s]
preprocess datasets:  47%|████▋     | 9353/20000 [02:18<01:55, 92.58 examples/s]
preprocess datasets:  47%|████▋     | 9364/20000 [02:18<01:55, 91.75 examples/s]
preprocess datasets:  47%|████▋     | 9375/20000 [02:19<02:08, 82.64 examples/s]
preprocess datasets:  47%|████▋     | 9388/20000 [02:19<02:00, 87.94 examples/s]
preprocess datasets:  47%|████▋     | 9400/20000 [02:19<01:55, 92.15 examples/s]
preprocess datasets:  47%|████▋     | 9411/20000 [02:19<01:51, 94.64 examples/s]
preprocess datasets:  47%|████▋     | 9422/20000 [02:19<02:07, 83.29 examples/s]
preprocess datasets:  47%|████▋     | 9435/20000 [02:19<01:53, 93.46 examples/s]
preprocess datasets:  47%|████▋     | 9449/20000 [02:19<01:55, 91.54 examples/s]
preprocess datasets:  47%|████▋     | 9459/20000 [02:20<02:02, 86.14 examples/s]
preprocess datasets:  47%|████▋     | 9472/20000 [02:20<02:06, 83.13 examples/s]
preprocess datasets:  47%|████▋     | 9482/20000 [02:20<02:03, 85.19 examples/s]
preprocess datasets:  47%|████▋     | 9492/20000 [02:20<02:01, 86.59 examples/s]
preprocess datasets:  48%|████▊     | 9503/20000 [02:20<01:59, 88.03 examples/s]
preprocess datasets:  48%|████▊     | 9517/20000 [02:20<02:00, 86.89 examples/s]
preprocess datasets:  48%|████▊     | 9529/20000 [02:20<01:53, 92.34 examples/s]
preprocess datasets:  48%|████▊     | 9540/20000 [02:20<01:55, 90.94 examples/s]
preprocess datasets:  48%|████▊     | 9552/20000 [02:21<02:08, 81.35 examples/s]
preprocess datasets:  48%|████▊     | 9563/20000 [02:21<02:04, 83.70 examples/s]
preprocess datasets:  48%|████▊     | 9573/20000 [02:21<02:05, 82.83 examples/s]
preprocess datasets:  48%|████▊     | 9583/20000 [02:21<02:05, 82.84 examples/s]
preprocess datasets:  48%|████▊     | 9598/20000 [02:21<02:02, 84.65 examples/s]
preprocess datasets:  48%|████▊     | 9608/20000 [02:21<02:02, 84.65 examples/s]
preprocess datasets:  48%|████▊     | 9622/20000 [02:21<01:48, 95.23 examples/s]
preprocess datasets:  48%|████▊     | 9635/20000 [02:22<02:00, 86.35 examples/s]
preprocess datasets:  48%|████▊     | 9649/20000 [02:22<01:45, 98.13 examples/s]
preprocess datasets:  48%|████▊     | 9662/20000 [02:22<01:56, 88.60 examples/s]
preprocess datasets:  48%|████▊     | 9673/20000 [02:22<01:57, 88.22 examples/s]
preprocess datasets:  48%|████▊     | 9686/20000 [02:22<01:58, 86.92 examples/s]
preprocess datasets:  48%|████▊     | 9696/20000 [02:22<02:11, 78.21 examples/s]
preprocess datasets:  49%|████▊     | 9705/20000 [02:23<02:25, 70.88 examples/s]
preprocess datasets:  49%|████▊     | 9714/20000 [02:23<02:19, 73.91 examples/s]
preprocess datasets:  49%|████▊     | 9722/20000 [02:23<02:23, 71.86 examples/s]
preprocess datasets:  49%|████▊     | 9735/20000 [02:23<02:02, 84.00 examples/s]
preprocess datasets:  49%|████▊     | 9745/20000 [02:23<02:01, 84.27 examples/s]
preprocess datasets:  49%|████▉     | 9759/20000 [02:23<02:01, 84.11 examples/s]
preprocess datasets:  49%|████▉     | 9772/20000 [02:23<02:30, 68.05 examples/s]
preprocess datasets:  49%|████▉     | 9782/20000 [02:24<02:32, 66.99 examples/s]
preprocess datasets:  49%|████▉     | 9795/20000 [02:24<02:10, 78.12 examples/s]
preprocess datasets:  49%|████▉     | 9805/20000 [02:24<02:14, 76.04 examples/s]
preprocess datasets:  49%|████▉     | 9818/20000 [02:24<01:59, 84.89 examples/s]
preprocess datasets:  49%|████▉     | 9828/20000 [02:24<01:57, 86.23 examples/s]
preprocess datasets:  49%|████▉     | 9839/20000 [02:24<01:56, 87.40 examples/s]
preprocess datasets:  49%|████▉     | 9849/20000 [02:24<01:58, 85.75 examples/s]
preprocess datasets:  49%|████▉     | 9863/20000 [02:24<01:43, 97.69 examples/s]
preprocess datasets:  49%|████▉     | 9876/20000 [02:25<01:40, 100.76 examples/s]
preprocess datasets:  49%|████▉     | 9890/20000 [02:25<01:47, 93.96 examples/s] 
preprocess datasets:  50%|████▉     | 9902/20000 [02:25<01:45, 95.61 examples/s]
preprocess datasets:  50%|████▉     | 9914/20000 [02:25<01:57, 86.14 examples/s]
preprocess datasets:  50%|████▉     | 9923/20000 [02:25<01:56, 86.27 examples/s]
preprocess datasets:  50%|████▉     | 9932/20000 [02:25<02:04, 80.91 examples/s]
preprocess datasets:  50%|████▉     | 9943/20000 [02:25<01:55, 86.72 examples/s]
preprocess datasets:  50%|████▉     | 9955/20000 [02:25<01:51, 90.25 examples/s]
preprocess datasets:  50%|████▉     | 9970/20000 [02:26<01:51, 90.27 examples/s]
preprocess datasets:  50%|████▉     | 9984/20000 [02:26<01:55, 86.89 examples/s]
preprocess datasets:  50%|████▉     | 9999/20000 [02:26<01:46, 94.32 examples/s]
preprocess datasets:  50%|█████     | 10009/20000 [02:27<05:13, 31.92 examples/s]
preprocess datasets:  50%|█████     | 10021/20000 [02:27<04:07, 40.28 examples/s]
preprocess datasets:  50%|█████     | 10033/20000 [02:27<03:24, 48.74 examples/s]
preprocess datasets:  50%|█████     | 10042/20000 [02:27<03:06, 53.27 examples/s]
preprocess datasets:  50%|█████     | 10053/20000 [02:27<02:45, 59.97 examples/s]
preprocess datasets:  50%|█████     | 10065/20000 [02:28<02:39, 62.42 examples/s]
preprocess datasets:  50%|█████     | 10073/20000 [02:28<02:32, 65.12 examples/s]
preprocess datasets:  50%|█████     | 10084/20000 [02:28<02:18, 71.73 examples/s]
preprocess datasets:  50%|█████     | 10094/20000 [02:28<02:45, 59.79 examples/s]
preprocess datasets:  51%|█████     | 10103/20000 [02:28<02:34, 63.96 examples/s]
preprocess datasets:  51%|█████     | 10115/20000 [02:28<02:15, 73.21 examples/s]
preprocess datasets:  51%|█████     | 10124/20000 [02:28<02:08, 76.93 examples/s]
preprocess datasets:  51%|█████     | 10136/20000 [02:28<01:57, 84.16 examples/s]
preprocess datasets:  51%|█████     | 10145/20000 [02:29<01:59, 82.72 examples/s]
preprocess datasets:  51%|█████     | 10155/20000 [02:29<02:00, 81.69 examples/s]
preprocess datasets:  51%|█████     | 10166/20000 [02:29<01:55, 85.09 examples/s]
preprocess datasets:  51%|█████     | 10177/20000 [02:29<01:51, 87.77 examples/s]
preprocess datasets:  51%|█████     | 10190/20000 [02:29<01:41, 96.55 examples/s]
preprocess datasets:  51%|█████     | 10201/20000 [02:29<01:44, 93.54 examples/s]
preprocess datasets:  51%|█████     | 10212/20000 [02:29<01:41, 96.79 examples/s]
preprocess datasets:  51%|█████     | 10222/20000 [02:29<01:40, 96.94 examples/s]
preprocess datasets:  51%|█████     | 10232/20000 [02:29<01:43, 94.77 examples/s]
preprocess datasets:  51%|█████     | 10242/20000 [02:30<01:45, 92.44 examples/s]
preprocess datasets:  51%|█████▏    | 10252/20000 [02:30<01:44, 92.90 examples/s]
preprocess datasets:  51%|█████▏    | 10263/20000 [02:30<01:45, 92.67 examples/s]
preprocess datasets:  51%|█████▏    | 10277/20000 [02:30<01:55, 84.54 examples/s]
preprocess datasets:  51%|█████▏    | 10288/20000 [02:30<02:03, 78.80 examples/s]
preprocess datasets:  51%|█████▏    | 10298/20000 [02:30<02:00, 80.28 examples/s]
preprocess datasets:  52%|█████▏    | 10308/20000 [02:30<01:59, 81.09 examples/s]
preprocess datasets:  52%|█████▏    | 10321/20000 [02:31<01:48, 88.96 examples/s]
preprocess datasets:  52%|█████▏    | 10333/20000 [02:31<01:53, 85.31 examples/s]
preprocess datasets:  52%|█████▏    | 10342/20000 [02:31<01:57, 82.44 examples/s]
preprocess datasets:  52%|█████▏    | 10351/20000 [02:31<01:59, 80.54 examples/s]
preprocess datasets:  52%|█████▏    | 10363/20000 [02:31<01:49, 87.76 examples/s]
preprocess datasets:  52%|█████▏    | 10373/20000 [02:31<01:49, 88.01 examples/s]
preprocess datasets:  52%|█████▏    | 10382/20000 [02:31<01:53, 84.89 examples/s]
preprocess datasets:  52%|█████▏    | 10395/20000 [02:31<02:05, 76.61 examples/s]
preprocess datasets:  52%|█████▏    | 10403/20000 [02:32<02:07, 75.45 examples/s]
preprocess datasets:  52%|█████▏    | 10412/20000 [02:32<02:07, 75.12 examples/s]
preprocess datasets:  52%|█████▏    | 10423/20000 [02:32<01:57, 81.44 examples/s]
preprocess datasets:  52%|█████▏    | 10436/20000 [02:32<01:58, 80.80 examples/s]
preprocess datasets:  52%|█████▏    | 10445/20000 [02:32<01:59, 79.91 examples/s]
preprocess datasets:  52%|█████▏    | 10454/20000 [02:32<01:56, 81.88 examples/s]
preprocess datasets:  52%|█████▏    | 10469/20000 [02:32<01:39, 95.45 examples/s]
preprocess datasets:  52%|█████▏    | 10479/20000 [02:32<01:44, 91.12 examples/s]
preprocess datasets:  52%|█████▏    | 10490/20000 [02:33<01:54, 82.87 examples/s]
preprocess datasets:  52%|█████▎    | 10500/20000 [02:33<01:56, 81.49 examples/s]
preprocess datasets:  53%|█████▎    | 10511/20000 [02:33<01:50, 85.76 examples/s]
preprocess datasets:  53%|█████▎    | 10523/20000 [02:33<01:48, 87.31 examples/s]
preprocess datasets:  53%|█████▎    | 10536/20000 [02:33<01:41, 92.80 examples/s]
preprocess datasets:  53%|█████▎    | 10549/20000 [02:33<01:50, 85.16 examples/s]
preprocess datasets:  53%|█████▎    | 10560/20000 [02:33<01:49, 86.46 examples/s]
preprocess datasets:  53%|█████▎    | 10574/20000 [02:33<01:39, 94.35 examples/s]
preprocess datasets:  53%|█████▎    | 10586/20000 [02:34<01:54, 82.12 examples/s]
preprocess datasets:  53%|█████▎    | 10599/20000 [02:34<01:58, 79.10 examples/s]
preprocess datasets:  53%|█████▎    | 10612/20000 [02:34<01:51, 84.21 examples/s]
preprocess datasets:  53%|█████▎    | 10622/20000 [02:34<01:48, 86.55 examples/s]
preprocess datasets:  53%|█████▎    | 10632/20000 [02:34<01:47, 86.87 examples/s]
preprocess datasets:  53%|█████▎    | 10642/20000 [02:34<01:49, 85.41 examples/s]
preprocess datasets:  53%|█████▎    | 10655/20000 [02:34<01:41, 92.47 examples/s]
preprocess datasets:  53%|█████▎    | 10665/20000 [02:35<01:56, 79.86 examples/s]
preprocess datasets:  53%|█████▎    | 10675/20000 [02:35<02:02, 76.42 examples/s]
preprocess datasets:  53%|█████▎    | 10685/20000 [02:35<02:09, 71.96 examples/s]
preprocess datasets:  53%|█████▎    | 10694/20000 [02:35<02:08, 72.66 examples/s]
preprocess datasets:  54%|█████▎    | 10704/20000 [02:35<02:03, 75.48 examples/s]
preprocess datasets:  54%|█████▎    | 10713/20000 [02:35<02:01, 76.32 examples/s]
preprocess datasets:  54%|█████▎    | 10726/20000 [02:35<01:46, 86.80 examples/s]
preprocess datasets:  54%|█████▎    | 10737/20000 [02:36<01:46, 86.93 examples/s]
preprocess datasets:  54%|█████▎    | 10746/20000 [02:36<01:49, 84.75 examples/s]
preprocess datasets:  54%|█████▍    | 10758/20000 [02:36<01:43, 88.88 examples/s]
preprocess datasets:  54%|█████▍    | 10769/20000 [02:36<01:40, 92.23 examples/s]
preprocess datasets:  54%|█████▍    | 10783/20000 [02:36<01:44, 88.41 examples/s]
preprocess datasets:  54%|█████▍    | 10795/20000 [02:36<01:52, 81.61 examples/s]
preprocess datasets:  54%|█████▍    | 10804/20000 [02:36<01:53, 81.08 examples/s]
preprocess datasets:  54%|█████▍    | 10815/20000 [02:36<01:46, 85.89 examples/s]
preprocess datasets:  54%|█████▍    | 10826/20000 [02:37<01:44, 88.00 examples/s]
preprocess datasets:  54%|█████▍    | 10836/20000 [02:37<01:43, 88.42 examples/s]
preprocess datasets:  54%|█████▍    | 10848/20000 [02:37<01:39, 92.09 examples/s]
preprocess datasets:  54%|█████▍    | 10858/20000 [02:37<01:39, 91.82 examples/s]
preprocess datasets:  54%|█████▍    | 10872/20000 [02:37<01:47, 84.79 examples/s]
preprocess datasets:  54%|█████▍    | 10881/20000 [02:37<02:05, 72.61 examples/s]
preprocess datasets:  54%|█████▍    | 10889/20000 [02:37<02:03, 73.95 examples/s]
preprocess datasets:  55%|█████▍    | 10900/20000 [02:37<01:54, 79.65 examples/s]
preprocess datasets:  55%|█████▍    | 10909/20000 [02:38<02:06, 72.14 examples/s]
preprocess datasets:  55%|█████▍    | 10922/20000 [02:38<01:50, 81.97 examples/s]
preprocess datasets:  55%|█████▍    | 10934/20000 [02:38<01:41, 89.68 examples/s]
preprocess datasets:  55%|█████▍    | 10946/20000 [02:38<01:36, 93.45 examples/s]
preprocess datasets:  55%|█████▍    | 10960/20000 [02:38<01:29, 100.46 examples/s]
preprocess datasets:  55%|█████▍    | 10974/20000 [02:38<01:22, 109.86 examples/s]
preprocess datasets:  55%|█████▍    | 10990/20000 [02:38<01:28, 102.35 examples/s]
preprocess datasets:  55%|█████▌    | 11005/20000 [02:39<04:06, 36.47 examples/s] 
preprocess datasets:  55%|█████▌    | 11015/20000 [02:39<03:31, 42.57 examples/s]
preprocess datasets:  55%|█████▌    | 11026/20000 [02:40<02:58, 50.23 examples/s]
preprocess datasets:  55%|█████▌    | 11035/20000 [02:40<02:43, 54.98 examples/s]
preprocess datasets:  55%|█████▌    | 11046/20000 [02:40<02:22, 62.92 examples/s]
preprocess datasets:  55%|█████▌    | 11056/20000 [02:40<02:11, 67.83 examples/s]
preprocess datasets:  55%|█████▌    | 11071/20000 [02:40<01:58, 75.58 examples/s]
preprocess datasets:  55%|█████▌    | 11080/20000 [02:40<01:57, 75.90 examples/s]
preprocess datasets:  55%|█████▌    | 11091/20000 [02:40<01:48, 81.90 examples/s]
preprocess datasets:  56%|█████▌    | 11103/20000 [02:40<01:52, 78.99 examples/s]
preprocess datasets:  56%|█████▌    | 11117/20000 [02:41<01:39, 89.21 examples/s]
preprocess datasets:  56%|█████▌    | 11130/20000 [02:41<01:43, 86.05 examples/s]
preprocess datasets:  56%|█████▌    | 11143/20000 [02:41<01:45, 84.01 examples/s]
preprocess datasets:  56%|█████▌    | 11155/20000 [02:41<01:54, 77.23 examples/s]
preprocess datasets:  56%|█████▌    | 11166/20000 [02:41<01:47, 82.46 examples/s]
preprocess datasets:  56%|█████▌    | 11176/20000 [02:41<01:46, 82.99 examples/s]
preprocess datasets:  56%|█████▌    | 11186/20000 [02:42<02:02, 71.98 examples/s]
preprocess datasets:  56%|█████▌    | 11203/20000 [02:42<01:37, 90.12 examples/s]
preprocess datasets:  56%|█████▌    | 11214/20000 [02:42<01:50, 79.80 examples/s]
preprocess datasets:  56%|█████▌    | 11223/20000 [02:42<01:48, 80.56 examples/s]
preprocess datasets:  56%|█████▌    | 11232/20000 [02:42<01:49, 79.80 examples/s]
preprocess datasets:  56%|█████▌    | 11241/20000 [02:42<01:50, 79.33 examples/s]
preprocess datasets:  56%|█████▋    | 11252/20000 [02:42<01:48, 80.53 examples/s]
preprocess datasets:  56%|█████▋    | 11261/20000 [02:42<01:49, 80.12 examples/s]
preprocess datasets:  56%|█████▋    | 11273/20000 [02:43<01:39, 87.97 examples/s]
preprocess datasets:  56%|█████▋    | 11283/20000 [02:43<01:41, 85.92 examples/s]
preprocess datasets:  56%|█████▋    | 11294/20000 [02:43<01:35, 90.86 examples/s]
preprocess datasets:  57%|█████▋    | 11311/20000 [02:43<01:22, 105.87 examples/s]
preprocess datasets:  57%|█████▋    | 11325/20000 [02:43<01:32, 93.84 examples/s] 
preprocess datasets:  57%|█████▋    | 11339/20000 [02:43<01:37, 88.99 examples/s]
preprocess datasets:  57%|█████▋    | 11349/20000 [02:43<01:38, 88.25 examples/s]
preprocess datasets:  57%|█████▋    | 11365/20000 [02:44<01:38, 87.89 examples/s]
preprocess datasets:  57%|█████▋    | 11374/20000 [02:44<01:41, 85.14 examples/s]
preprocess datasets:  57%|█████▋    | 11386/20000 [02:44<01:38, 87.87 examples/s]
preprocess datasets:  57%|█████▋    | 11398/20000 [02:44<01:33, 91.79 examples/s]
preprocess datasets:  57%|█████▋    | 11409/20000 [02:44<01:36, 89.13 examples/s]
preprocess datasets:  57%|█████▋    | 11418/20000 [02:44<01:43, 82.73 examples/s]
preprocess datasets:  57%|█████▋    | 11429/20000 [02:44<01:39, 86.46 examples/s]
preprocess datasets:  57%|█████▋    | 11441/20000 [02:44<01:34, 90.56 examples/s]
preprocess datasets:  57%|█████▋    | 11453/20000 [02:45<01:51, 76.68 examples/s]
preprocess datasets:  57%|█████▋    | 11463/20000 [02:45<01:57, 72.40 examples/s]
preprocess datasets:  57%|█████▋    | 11473/20000 [02:45<01:53, 75.15 examples/s]
preprocess datasets:  57%|█████▋    | 11487/20000 [02:45<01:35, 89.54 examples/s]
preprocess datasets:  58%|█████▊    | 11503/20000 [02:45<01:22, 103.07 examples/s]
preprocess datasets:  58%|█████▊    | 11515/20000 [02:45<01:25, 99.81 examples/s] 
preprocess datasets:  58%|█████▊    | 11532/20000 [02:45<01:25, 98.67 examples/s]
preprocess datasets:  58%|█████▊    | 11544/20000 [02:45<01:23, 101.58 examples/s]
preprocess datasets:  58%|█████▊    | 11557/20000 [02:46<01:21, 104.04 examples/s]
preprocess datasets:  58%|█████▊    | 11573/20000 [02:46<01:38, 85.68 examples/s] 
preprocess datasets:  58%|█████▊    | 11583/20000 [02:46<01:38, 85.35 examples/s]
preprocess datasets:  58%|█████▊    | 11596/20000 [02:46<01:45, 79.94 examples/s]
preprocess datasets:  58%|█████▊    | 11608/20000 [02:46<01:36, 86.61 examples/s]
preprocess datasets:  58%|█████▊    | 11618/20000 [02:46<01:36, 86.55 examples/s]
preprocess datasets:  58%|█████▊    | 11628/20000 [02:47<01:41, 82.84 examples/s]
preprocess datasets:  58%|█████▊    | 11637/20000 [02:47<01:44, 80.17 examples/s]
preprocess datasets:  58%|█████▊    | 11648/20000 [02:47<01:39, 83.56 examples/s]
preprocess datasets:  58%|█████▊    | 11659/20000 [02:47<01:36, 86.48 examples/s]
preprocess datasets:  58%|█████▊    | 11670/20000 [02:47<01:50, 75.42 examples/s]
preprocess datasets:  58%|█████▊    | 11678/20000 [02:47<01:50, 75.02 examples/s]
preprocess datasets:  58%|█████▊    | 11689/20000 [02:47<01:54, 72.52 examples/s]
preprocess datasets:  59%|█████▊    | 11705/20000 [02:47<01:32, 89.59 examples/s]
preprocess datasets:  59%|█████▊    | 11717/20000 [02:48<01:28, 93.68 examples/s]
preprocess datasets:  59%|█████▊    | 11728/20000 [02:48<01:27, 94.18 examples/s]
preprocess datasets:  59%|█████▊    | 11739/20000 [02:48<01:27, 94.90 examples/s]
preprocess datasets:  59%|█████▊    | 11749/20000 [02:48<01:30, 91.63 examples/s]
preprocess datasets:  59%|█████▉    | 11762/20000 [02:48<01:24, 97.43 examples/s]
preprocess datasets:  59%|█████▉    | 11779/20000 [02:48<01:27, 93.99 examples/s]
preprocess datasets:  59%|█████▉    | 11792/20000 [02:48<01:33, 87.56 examples/s]
preprocess datasets:  59%|█████▉    | 11805/20000 [02:49<01:37, 83.82 examples/s]
preprocess datasets:  59%|█████▉    | 11818/20000 [02:49<01:29, 90.94 examples/s]
preprocess datasets:  59%|█████▉    | 11829/20000 [02:49<01:27, 93.09 examples/s]
preprocess datasets:  59%|█████▉    | 11842/20000 [02:49<01:23, 97.73 examples/s]
preprocess datasets:  59%|█████▉    | 11858/20000 [02:49<01:14, 109.28 examples/s]
preprocess datasets:  59%|█████▉    | 11872/20000 [02:49<01:09, 116.15 examples/s]
preprocess datasets:  59%|█████▉    | 11887/20000 [02:49<01:15, 107.79 examples/s]
preprocess datasets:  60%|█████▉    | 11901/20000 [02:49<01:22, 98.36 examples/s] 
preprocess datasets:  60%|█████▉    | 11917/20000 [02:50<01:17, 104.94 examples/s]
preprocess datasets:  60%|█████▉    | 11931/20000 [02:50<01:21, 99.08 examples/s] 
preprocess datasets:  60%|█████▉    | 11942/20000 [02:50<01:31, 87.80 examples/s]
preprocess datasets:  60%|█████▉    | 11953/20000 [02:50<01:30, 88.57 examples/s]
preprocess datasets:  60%|█████▉    | 11967/20000 [02:50<01:44, 76.56 examples/s]
preprocess datasets:  60%|█████▉    | 11981/20000 [02:50<01:34, 84.79 examples/s]
preprocess datasets:  60%|█████▉    | 11993/20000 [02:51<01:32, 86.85 examples/s]
preprocess datasets:  60%|██████    | 12005/20000 [02:51<03:55, 33.97 examples/s]
preprocess datasets:  60%|██████    | 12014/20000 [02:52<03:23, 39.30 examples/s]
preprocess datasets:  60%|██████    | 12025/20000 [02:52<02:46, 47.86 examples/s]
preprocess datasets:  60%|██████    | 12037/20000 [02:52<02:16, 58.37 examples/s]
preprocess datasets:  60%|██████    | 12051/20000 [02:52<02:01, 65.57 examples/s]
preprocess datasets:  60%|██████    | 12065/20000 [02:52<01:54, 69.07 examples/s]
preprocess datasets:  60%|██████    | 12074/20000 [02:52<01:51, 70.97 examples/s]
preprocess datasets:  60%|██████    | 12088/20000 [02:52<01:38, 80.68 examples/s]
preprocess datasets:  61%|██████    | 12103/20000 [02:52<01:27, 89.81 examples/s]
preprocess datasets:  61%|██████    | 12114/20000 [02:53<01:24, 93.02 examples/s]
preprocess datasets:  61%|██████    | 12126/20000 [02:53<01:22, 95.00 examples/s]
preprocess datasets:  61%|██████    | 12139/20000 [02:53<01:19, 98.72 examples/s]
preprocess datasets:  61%|██████    | 12154/20000 [02:53<01:24, 92.58 examples/s]
preprocess datasets:  61%|██████    | 12167/20000 [02:53<01:31, 85.50 examples/s]
preprocess datasets:  61%|██████    | 12179/20000 [02:53<01:27, 89.34 examples/s]
preprocess datasets:  61%|██████    | 12192/20000 [02:53<01:33, 83.38 examples/s]
preprocess datasets:  61%|██████    | 12203/20000 [02:54<01:29, 86.68 examples/s]
preprocess datasets:  61%|██████    | 12214/20000 [02:54<01:27, 89.03 examples/s]
preprocess datasets:  61%|██████    | 12227/20000 [02:54<01:31, 85.29 examples/s]
preprocess datasets:  61%|██████    | 12242/20000 [02:54<01:19, 98.16 examples/s]
preprocess datasets:  61%|██████▏   | 12257/20000 [02:54<01:22, 93.33 examples/s]
preprocess datasets:  61%|██████▏   | 12273/20000 [02:54<01:22, 93.58 examples/s]
preprocess datasets:  61%|██████▏   | 12284/20000 [02:54<01:22, 93.91 examples/s]
preprocess datasets:  61%|██████▏   | 12295/20000 [02:55<01:47, 71.62 examples/s]
preprocess datasets:  62%|██████▏   | 12309/20000 [02:55<01:32, 83.18 examples/s]
preprocess datasets:  62%|██████▏   | 12319/20000 [02:55<01:31, 83.66 examples/s]
preprocess datasets:  62%|██████▏   | 12330/20000 [02:55<01:31, 83.74 examples/s]
preprocess datasets:  62%|██████▏   | 12341/20000 [02:55<01:27, 87.64 examples/s]
preprocess datasets:  62%|██████▏   | 12352/20000 [02:55<01:24, 90.98 examples/s]
preprocess datasets:  62%|██████▏   | 12364/20000 [02:55<01:35, 80.11 examples/s]
preprocess datasets:  62%|██████▏   | 12375/20000 [02:56<01:31, 83.52 examples/s]
preprocess datasets:  62%|██████▏   | 12390/20000 [02:56<01:27, 86.83 examples/s]
preprocess datasets:  62%|██████▏   | 12402/20000 [02:56<01:21, 92.82 examples/s]
preprocess datasets:  62%|██████▏   | 12417/20000 [02:56<01:26, 88.09 examples/s]
preprocess datasets:  62%|██████▏   | 12432/20000 [02:56<01:18, 96.67 examples/s]
preprocess datasets:  62%|██████▏   | 12443/20000 [02:56<01:20, 94.00 examples/s]
preprocess datasets:  62%|██████▏   | 12455/20000 [02:56<01:15, 99.90 examples/s]
preprocess datasets:  62%|██████▏   | 12473/20000 [02:57<01:03, 117.74 examples/s]
preprocess datasets:  62%|██████▏   | 12490/20000 [02:57<01:16, 98.51 examples/s] 
preprocess datasets:  63%|██████▎   | 12501/20000 [02:57<01:22, 90.55 examples/s]
preprocess datasets:  63%|██████▎   | 12512/20000 [02:57<01:29, 83.25 examples/s]
preprocess datasets:  63%|██████▎   | 12522/20000 [02:57<01:33, 80.22 examples/s]
preprocess datasets:  63%|██████▎   | 12535/20000 [02:57<01:25, 86.90 examples/s]
preprocess datasets:  63%|██████▎   | 12548/20000 [02:57<01:21, 91.45 examples/s]
preprocess datasets:  63%|██████▎   | 12558/20000 [02:58<01:23, 88.80 examples/s]
preprocess datasets:  63%|██████▎   | 12571/20000 [02:58<01:17, 95.87 examples/s]
preprocess datasets:  63%|██████▎   | 12582/20000 [02:58<01:32, 80.05 examples/s]
preprocess datasets:  63%|██████▎   | 12591/20000 [02:58<01:30, 81.51 examples/s]
preprocess datasets:  63%|██████▎   | 12601/20000 [02:58<01:26, 85.16 examples/s]
preprocess datasets:  63%|██████▎   | 12610/20000 [02:58<01:27, 84.04 examples/s]
preprocess datasets:  63%|██████▎   | 12625/20000 [02:58<01:18, 94.53 examples/s]
preprocess datasets:  63%|██████▎   | 12638/20000 [02:58<01:23, 87.96 examples/s]
preprocess datasets:  63%|██████▎   | 12655/20000 [02:59<01:12, 101.63 examples/s]
preprocess datasets:  63%|██████▎   | 12670/20000 [02:59<01:06, 110.35 examples/s]
preprocess datasets:  63%|██████▎   | 12684/20000 [02:59<01:02, 116.71 examples/s]
preprocess datasets:  63%|██████▎   | 12698/20000 [02:59<01:01, 118.73 examples/s]
preprocess datasets:  64%|██████▎   | 12711/20000 [02:59<01:11, 101.95 examples/s]
preprocess datasets:  64%|██████▎   | 12729/20000 [02:59<01:10, 103.56 examples/s]
preprocess datasets:  64%|██████▎   | 12743/20000 [02:59<01:15, 96.06 examples/s] 
preprocess datasets:  64%|██████▍   | 12754/20000 [03:00<01:17, 93.70 examples/s]
preprocess datasets:  64%|██████▍   | 12766/20000 [03:00<01:14, 97.40 examples/s]
preprocess datasets:  64%|██████▍   | 12779/20000 [03:00<01:20, 89.59 examples/s]
preprocess datasets:  64%|██████▍   | 12789/20000 [03:00<01:21, 88.56 examples/s]
preprocess datasets:  64%|██████▍   | 12800/20000 [03:00<01:23, 85.94 examples/s]
preprocess datasets:  64%|██████▍   | 12811/20000 [03:00<01:32, 77.42 examples/s]
preprocess datasets:  64%|██████▍   | 12825/20000 [03:00<01:22, 87.06 examples/s]
preprocess datasets:  64%|██████▍   | 12837/20000 [03:01<01:32, 77.50 examples/s]
preprocess datasets:  64%|██████▍   | 12847/20000 [03:01<01:29, 80.32 examples/s]
preprocess datasets:  64%|██████▍   | 12859/20000 [03:01<01:25, 83.11 examples/s]
preprocess datasets:  64%|██████▍   | 12872/20000 [03:01<01:17, 91.93 examples/s]
preprocess datasets:  64%|██████▍   | 12885/20000 [03:01<01:14, 95.46 examples/s]
preprocess datasets:  64%|██████▍   | 12895/20000 [03:01<01:17, 91.80 examples/s]
preprocess datasets:  65%|██████▍   | 12907/20000 [03:01<01:24, 84.33 examples/s]
preprocess datasets:  65%|██████▍   | 12918/20000 [03:02<01:24, 83.74 examples/s]
preprocess datasets:  65%|██████▍   | 12927/20000 [03:02<01:26, 81.99 examples/s]
preprocess datasets:  65%|██████▍   | 12938/20000 [03:02<01:22, 85.10 examples/s]
preprocess datasets:  65%|██████▍   | 12950/20000 [03:02<01:27, 80.92 examples/s]
preprocess datasets:  65%|██████▍   | 12964/20000 [03:02<01:32, 76.23 examples/s]
preprocess datasets:  65%|██████▍   | 12974/20000 [03:02<01:28, 79.70 examples/s]
preprocess datasets:  65%|██████▍   | 12988/20000 [03:02<01:30, 77.27 examples/s]
preprocess datasets:  65%|██████▍   | 12999/20000 [03:03<01:24, 83.16 examples/s]
preprocess datasets:  65%|██████▌   | 13010/20000 [03:03<03:42, 31.38 examples/s]
preprocess datasets:  65%|██████▌   | 13020/20000 [03:04<03:08, 37.00 examples/s]
preprocess datasets:  65%|██████▌   | 13032/20000 [03:04<02:31, 45.89 examples/s]
preprocess datasets:  65%|██████▌   | 13043/20000 [03:04<02:07, 54.55 examples/s]
preprocess datasets:  65%|██████▌   | 13054/20000 [03:04<01:50, 62.68 examples/s]
preprocess datasets:  65%|██████▌   | 13065/20000 [03:04<01:48, 64.17 examples/s]
preprocess datasets:  65%|██████▌   | 13077/20000 [03:04<01:36, 72.05 examples/s]
preprocess datasets:  65%|██████▌   | 13092/20000 [03:04<01:21, 85.10 examples/s]
preprocess datasets:  66%|██████▌   | 13102/20000 [03:04<01:21, 84.88 examples/s]
preprocess datasets:  66%|██████▌   | 13112/20000 [03:05<01:21, 84.36 examples/s]
preprocess datasets:  66%|██████▌   | 13122/20000 [03:05<01:19, 86.11 examples/s]
preprocess datasets:  66%|██████▌   | 13134/20000 [03:05<01:14, 92.31 examples/s]
preprocess datasets:  66%|██████▌   | 13150/20000 [03:05<01:14, 92.42 examples/s]
preprocess datasets:  66%|██████▌   | 13161/20000 [03:05<01:13, 93.31 examples/s]
preprocess datasets:  66%|██████▌   | 13171/20000 [03:05<01:16, 89.59 examples/s]
preprocess datasets:  66%|██████▌   | 13183/20000 [03:05<01:22, 82.95 examples/s]
preprocess datasets:  66%|██████▌   | 13196/20000 [03:05<01:13, 92.40 examples/s]
preprocess datasets:  66%|██████▌   | 13207/20000 [03:06<01:10, 96.05 examples/s]
preprocess datasets:  66%|██████▌   | 13222/20000 [03:06<01:10, 95.49 examples/s]
preprocess datasets:  66%|██████▌   | 13236/20000 [03:06<01:05, 103.58 examples/s]
preprocess datasets:  66%|██████▌   | 13249/20000 [03:06<01:04, 104.27 examples/s]
preprocess datasets:  66%|██████▋   | 13262/20000 [03:06<01:12, 92.46 examples/s] 
preprocess datasets:  66%|██████▋   | 13276/20000 [03:06<01:06, 101.12 examples/s]
preprocess datasets:  66%|██████▋   | 13287/20000 [03:06<01:07, 99.13 examples/s] 
preprocess datasets:  67%|██████▋   | 13303/20000 [03:06<01:03, 106.03 examples/s]
preprocess datasets:  67%|██████▋   | 13316/20000 [03:07<01:01, 107.99 examples/s]
preprocess datasets:  67%|██████▋   | 13329/20000 [03:07<01:03, 104.85 examples/s]
preprocess datasets:  67%|██████▋   | 13343/20000 [03:07<01:09, 96.46 examples/s] 
preprocess datasets:  67%|██████▋   | 13360/20000 [03:07<00:59, 112.18 examples/s]
preprocess datasets:  67%|██████▋   | 13373/20000 [03:07<00:57, 116.11 examples/s]
preprocess datasets:  67%|██████▋   | 13387/20000 [03:07<00:56, 116.25 examples/s]
preprocess datasets:  67%|██████▋   | 13404/20000 [03:07<00:59, 111.08 examples/s]
preprocess datasets:  67%|██████▋   | 13418/20000 [03:08<01:12, 90.63 examples/s] 
preprocess datasets:  67%|██████▋   | 13429/20000 [03:08<01:10, 92.97 examples/s]
preprocess datasets:  67%|██████▋   | 13440/20000 [03:08<01:09, 94.97 examples/s]
preprocess datasets:  67%|██████▋   | 13453/20000 [03:08<01:14, 87.56 examples/s]
preprocess datasets:  67%|██████▋   | 13468/20000 [03:08<01:13, 88.48 examples/s]
preprocess datasets:  67%|██████▋   | 13482/20000 [03:08<01:07, 95.91 examples/s]
preprocess datasets:  67%|██████▋   | 13492/20000 [03:08<01:08, 95.35 examples/s]
preprocess datasets:  68%|██████▊   | 13506/20000 [03:09<01:02, 103.97 examples/s]
preprocess datasets:  68%|██████▊   | 13520/20000 [03:09<00:58, 109.90 examples/s]
preprocess datasets:  68%|██████▊   | 13536/20000 [03:09<00:56, 113.89 examples/s]
preprocess datasets:  68%|██████▊   | 13551/20000 [03:09<00:59, 107.79 examples/s]
preprocess datasets:  68%|██████▊   | 13565/20000 [03:09<00:58, 109.45 examples/s]
preprocess datasets:  68%|██████▊   | 13579/20000 [03:09<00:56, 114.30 examples/s]
preprocess datasets:  68%|██████▊   | 13596/20000 [03:09<01:02, 103.24 examples/s]
preprocess datasets:  68%|██████▊   | 13608/20000 [03:09<01:00, 105.21 examples/s]
preprocess datasets:  68%|██████▊   | 13621/20000 [03:10<01:10, 90.88 examples/s] 
preprocess datasets:  68%|██████▊   | 13633/20000 [03:10<01:07, 94.72 examples/s]
preprocess datasets:  68%|██████▊   | 13649/20000 [03:10<01:00, 104.40 examples/s]
preprocess datasets:  68%|██████▊   | 13661/20000 [03:10<00:59, 105.82 examples/s]
preprocess datasets:  68%|██████▊   | 13672/20000 [03:10<01:04, 98.20 examples/s] 
preprocess datasets:  68%|██████▊   | 13685/20000 [03:10<01:11, 88.36 examples/s]
preprocess datasets:  68%|██████▊   | 13696/20000 [03:10<01:10, 89.27 examples/s]
preprocess datasets:  69%|██████▊   | 13707/20000 [03:11<01:10, 89.82 examples/s]
preprocess datasets:  69%|██████▊   | 13720/20000 [03:11<01:05, 95.47 examples/s]
preprocess datasets:  69%|██████▊   | 13731/20000 [03:11<01:05, 96.17 examples/s]
preprocess datasets:  69%|██████▊   | 13742/20000 [03:11<01:19, 79.16 examples/s]
preprocess datasets:  69%|██████▉   | 13754/20000 [03:11<01:11, 87.85 examples/s]
preprocess datasets:  69%|██████▉   | 13768/20000 [03:11<01:20, 77.76 examples/s]
preprocess datasets:  69%|██████▉   | 13778/20000 [03:11<01:17, 80.77 examples/s]
preprocess datasets:  69%|██████▉   | 13790/20000 [03:12<01:15, 81.94 examples/s]
preprocess datasets:  69%|██████▉   | 13805/20000 [03:12<01:15, 82.49 examples/s]
preprocess datasets:  69%|██████▉   | 13815/20000 [03:12<01:19, 78.12 examples/s]
preprocess datasets:  69%|██████▉   | 13830/20000 [03:12<01:09, 88.50 examples/s]
preprocess datasets:  69%|██████▉   | 13842/20000 [03:12<01:07, 91.24 examples/s]
preprocess datasets:  69%|██████▉   | 13857/20000 [03:12<01:03, 97.39 examples/s]
preprocess datasets:  69%|██████▉   | 13870/20000 [03:12<01:00, 101.20 examples/s]
preprocess datasets:  69%|██████▉   | 13881/20000 [03:13<01:03, 95.89 examples/s] 
preprocess datasets:  69%|██████▉   | 13894/20000 [03:13<01:01, 99.63 examples/s]
preprocess datasets:  70%|██████▉   | 13910/20000 [03:13<01:02, 96.92 examples/s]
preprocess datasets:  70%|██████▉   | 13927/20000 [03:13<01:03, 96.06 examples/s]
preprocess datasets:  70%|██████▉   | 13938/20000 [03:13<01:02, 96.76 examples/s]
preprocess datasets:  70%|██████▉   | 13949/20000 [03:13<01:02, 97.01 examples/s]
preprocess datasets:  70%|██████▉   | 13960/20000 [03:13<01:00, 99.13 examples/s]
preprocess datasets:  70%|██████▉   | 13974/20000 [03:13<00:59, 101.86 examples/s]
preprocess datasets:  70%|██████▉   | 13985/20000 [03:14<00:59, 101.53 examples/s]
preprocess datasets:  70%|██████▉   | 13998/20000 [03:14<00:56, 106.49 examples/s]
preprocess datasets:  70%|███████   | 14009/20000 [03:15<02:50, 35.13 examples/s] 
preprocess datasets:  70%|███████   | 14027/20000 [03:15<01:58, 50.49 examples/s]
preprocess datasets:  70%|███████   | 14038/20000 [03:15<01:48, 55.19 examples/s]
preprocess datasets:  70%|███████   | 14050/20000 [03:15<01:35, 62.38 examples/s]
preprocess datasets:  70%|███████   | 14068/20000 [03:15<01:15, 78.47 examples/s]
preprocess datasets:  70%|███████   | 14080/20000 [03:15<01:16, 76.89 examples/s]
preprocess datasets:  70%|███████   | 14093/20000 [03:15<01:10, 84.22 examples/s]
preprocess datasets:  71%|███████   | 14109/20000 [03:15<01:07, 87.18 examples/s]
preprocess datasets:  71%|███████   | 14120/20000 [03:16<01:05, 90.36 examples/s]
preprocess datasets:  71%|███████   | 14132/20000 [03:16<01:02, 93.16 examples/s]
preprocess datasets:  71%|███████   | 14147/20000 [03:16<00:56, 103.94 examples/s]
preprocess datasets:  71%|███████   | 14162/20000 [03:16<00:59, 98.08 examples/s] 
preprocess datasets:  71%|███████   | 14173/20000 [03:16<00:58, 99.47 examples/s]
preprocess datasets:  71%|███████   | 14189/20000 [03:16<00:58, 98.67 examples/s]
preprocess datasets:  71%|███████   | 14205/20000 [03:16<00:53, 108.17 examples/s]
preprocess datasets:  71%|███████   | 14221/20000 [03:17<00:48, 119.54 examples/s]
preprocess datasets:  71%|███████   | 14237/20000 [03:17<01:10, 81.61 examples/s] 
preprocess datasets:  71%|███████▏  | 14250/20000 [03:17<01:16, 75.49 examples/s]
preprocess datasets:  71%|███████▏  | 14259/20000 [03:17<01:15, 76.43 examples/s]
preprocess datasets:  71%|███████▏  | 14270/20000 [03:17<01:11, 80.15 examples/s]
preprocess datasets:  71%|███████▏  | 14281/20000 [03:17<01:08, 83.09 examples/s]
preprocess datasets:  71%|███████▏  | 14292/20000 [03:18<01:05, 87.56 examples/s]
preprocess datasets:  72%|███████▏  | 14305/20000 [03:18<00:58, 96.78 examples/s]
preprocess datasets:  72%|███████▏  | 14320/20000 [03:18<00:53, 105.61 examples/s]
preprocess datasets:  72%|███████▏  | 14332/20000 [03:18<00:53, 105.28 examples/s]
preprocess datasets:  72%|███████▏  | 14345/20000 [03:18<00:51, 109.70 examples/s]
preprocess datasets:  72%|███████▏  | 14364/20000 [03:18<00:57, 98.19 examples/s] 
preprocess datasets:  72%|███████▏  | 14378/20000 [03:18<01:01, 91.70 examples/s]
preprocess datasets:  72%|███████▏  | 14390/20000 [03:19<01:07, 83.43 examples/s]
preprocess datasets:  72%|███████▏  | 14402/20000 [03:19<01:12, 77.48 examples/s]
preprocess datasets:  72%|███████▏  | 14417/20000 [03:19<01:03, 87.67 examples/s]
preprocess datasets:  72%|███████▏  | 14428/20000 [03:19<01:15, 73.68 examples/s]
preprocess datasets:  72%|███████▏  | 14440/20000 [03:19<01:10, 79.42 examples/s]
preprocess datasets:  72%|███████▏  | 14452/20000 [03:19<01:07, 82.41 examples/s]
preprocess datasets:  72%|███████▏  | 14464/20000 [03:19<01:04, 85.21 examples/s]
preprocess datasets:  72%|███████▏  | 14474/20000 [03:20<01:04, 85.37 examples/s]
preprocess datasets:  72%|███████▏  | 14485/20000 [03:20<01:02, 88.43 examples/s]
preprocess datasets:  72%|███████▏  | 14498/20000 [03:20<00:56, 96.95 examples/s]
preprocess datasets:  73%|███████▎  | 14510/20000 [03:20<00:56, 96.76 examples/s]
preprocess datasets:  73%|███████▎  | 14525/20000 [03:20<00:58, 94.36 examples/s]
preprocess datasets:  73%|███████▎  | 14535/20000 [03:20<01:02, 87.86 examples/s]
preprocess datasets:  73%|███████▎  | 14547/20000 [03:20<00:57, 94.12 examples/s]
preprocess datasets:  73%|███████▎  | 14558/20000 [03:20<00:56, 96.64 examples/s]
preprocess datasets:  73%|███████▎  | 14570/20000 [03:21<00:53, 101.08 examples/s]
preprocess datasets:  73%|███████▎  | 14582/20000 [03:21<00:52, 102.48 examples/s]
preprocess datasets:  73%|███████▎  | 14594/20000 [03:21<00:52, 102.01 examples/s]
preprocess datasets:  73%|███████▎  | 14607/20000 [03:21<00:52, 103.07 examples/s]
preprocess datasets:  73%|███████▎  | 14620/20000 [03:21<00:52, 102.12 examples/s]
preprocess datasets:  73%|███████▎  | 14636/20000 [03:21<00:48, 111.58 examples/s]
preprocess datasets:  73%|███████▎  | 14650/20000 [03:21<00:47, 112.02 examples/s]
preprocess datasets:  73%|███████▎  | 14662/20000 [03:21<00:49, 108.74 examples/s]
preprocess datasets:  73%|███████▎  | 14673/20000 [03:21<00:50, 104.92 examples/s]
preprocess datasets:  73%|███████▎  | 14686/20000 [03:22<00:59, 89.74 examples/s] 
preprocess datasets:  74%|███████▎  | 14700/20000 [03:22<00:54, 96.95 examples/s]
preprocess datasets:  74%|███████▎  | 14718/20000 [03:22<00:52, 100.37 examples/s]
preprocess datasets:  74%|███████▎  | 14731/20000 [03:22<00:59, 88.15 examples/s] 
preprocess datasets:  74%|███████▎  | 14746/20000 [03:22<00:58, 89.81 examples/s]
preprocess datasets:  74%|███████▍  | 14761/20000 [03:22<00:58, 90.12 examples/s]
preprocess datasets:  74%|███████▍  | 14773/20000 [03:23<00:55, 94.78 examples/s]
preprocess datasets:  74%|███████▍  | 14785/20000 [03:23<01:01, 85.32 examples/s]
preprocess datasets:  74%|███████▍  | 14801/20000 [03:23<00:59, 87.47 examples/s]
preprocess datasets:  74%|███████▍  | 14814/20000 [03:23<00:55, 94.19 examples/s]
preprocess datasets:  74%|███████▍  | 14825/20000 [03:23<00:54, 94.47 examples/s]
preprocess datasets:  74%|███████▍  | 14838/20000 [03:23<00:53, 95.74 examples/s]
preprocess datasets:  74%|███████▍  | 14853/20000 [03:23<00:50, 102.85 examples/s]
preprocess datasets:  74%|███████▍  | 14870/20000 [03:24<00:54, 94.10 examples/s] 
preprocess datasets:  74%|███████▍  | 14881/20000 [03:24<00:54, 93.68 examples/s]
preprocess datasets:  74%|███████▍  | 14891/20000 [03:24<00:54, 93.62 examples/s]
preprocess datasets:  75%|███████▍  | 14904/20000 [03:24<00:56, 90.21 examples/s]
preprocess datasets:  75%|███████▍  | 14921/20000 [03:24<00:48, 104.44 examples/s]
preprocess datasets:  75%|███████▍  | 14936/20000 [03:24<00:44, 113.01 examples/s]
preprocess datasets:  75%|███████▍  | 14949/20000 [03:24<00:44, 112.84 examples/s]
preprocess datasets:  75%|███████▍  | 14961/20000 [03:24<00:44, 112.46 examples/s]
preprocess datasets:  75%|███████▍  | 14977/20000 [03:25<00:47, 105.16 examples/s]
preprocess datasets:  75%|███████▍  | 14988/20000 [03:25<00:47, 105.92 examples/s]
preprocess datasets:  75%|███████▍  | 14999/20000 [03:25<00:50, 99.79 examples/s] 
preprocess datasets:  75%|███████▌  | 15011/20000 [03:26<02:24, 34.54 examples/s]
preprocess datasets:  75%|███████▌  | 15025/20000 [03:26<01:52, 44.23 examples/s]
preprocess datasets:  75%|███████▌  | 15034/20000 [03:26<01:40, 49.63 examples/s]
preprocess datasets:  75%|███████▌  | 15049/20000 [03:26<01:18, 63.36 examples/s]
preprocess datasets:  75%|███████▌  | 15059/20000 [03:26<01:12, 68.62 examples/s]
preprocess datasets:  75%|███████▌  | 15072/20000 [03:26<01:05, 74.96 examples/s]
preprocess datasets:  75%|███████▌  | 15082/20000 [03:27<01:04, 75.96 examples/s]
preprocess datasets:  75%|███████▌  | 15094/20000 [03:27<00:59, 82.38 examples/s]
preprocess datasets:  76%|███████▌  | 15105/20000 [03:27<01:03, 77.12 examples/s]
preprocess datasets:  76%|███████▌  | 15116/20000 [03:27<00:59, 82.36 examples/s]
preprocess datasets:  76%|███████▌  | 15126/20000 [03:27<00:58, 83.73 examples/s]
preprocess datasets:  76%|███████▌  | 15135/20000 [03:27<00:58, 83.83 examples/s]
preprocess datasets:  76%|███████▌  | 15151/20000 [03:27<00:47, 102.59 examples/s]
preprocess datasets:  76%|███████▌  | 15167/20000 [03:27<00:47, 101.07 examples/s]
preprocess datasets:  76%|███████▌  | 15181/20000 [03:28<00:51, 94.24 examples/s] 
preprocess datasets:  76%|███████▌  | 15196/20000 [03:28<00:51, 92.68 examples/s]
preprocess datasets:  76%|███████▌  | 15210/20000 [03:28<00:47, 99.98 examples/s]
preprocess datasets:  76%|███████▌  | 15225/20000 [03:28<00:51, 92.42 examples/s]
preprocess datasets:  76%|███████▌  | 15235/20000 [03:28<00:52, 91.01 examples/s]
preprocess datasets:  76%|███████▋  | 15251/20000 [03:28<00:51, 91.98 examples/s]
preprocess datasets:  76%|███████▋  | 15264/20000 [03:28<00:47, 99.38 examples/s]
preprocess datasets:  76%|███████▋  | 15280/20000 [03:29<00:47, 98.81 examples/s]
preprocess datasets:  76%|███████▋  | 15293/20000 [03:29<00:45, 103.61 examples/s]
preprocess datasets:  77%|███████▋  | 15307/20000 [03:29<00:44, 106.45 examples/s]
preprocess datasets:  77%|███████▋  | 15320/20000 [03:29<00:42, 111.33 examples/s]
preprocess datasets:  77%|███████▋  | 15333/20000 [03:29<00:50, 92.60 examples/s] 
preprocess datasets:  77%|███████▋  | 15344/20000 [03:29<00:49, 93.23 examples/s]
preprocess datasets:  77%|███████▋  | 15357/20000 [03:29<00:52, 88.25 examples/s]
preprocess datasets:  77%|███████▋  | 15369/20000 [03:30<00:55, 83.28 examples/s]
preprocess datasets:  77%|███████▋  | 15378/20000 [03:30<00:55, 83.43 examples/s]
preprocess datasets:  77%|███████▋  | 15390/20000 [03:30<00:53, 86.48 examples/s]
preprocess datasets:  77%|███████▋  | 15404/20000 [03:30<00:47, 96.68 examples/s]
preprocess datasets:  77%|███████▋  | 15414/20000 [03:30<00:52, 86.59 examples/s]
preprocess datasets:  77%|███████▋  | 15426/20000 [03:30<00:50, 90.74 examples/s]
preprocess datasets:  77%|███████▋  | 15438/20000 [03:30<00:47, 95.63 examples/s]
preprocess datasets:  77%|███████▋  | 15451/20000 [03:30<00:44, 101.33 examples/s]
preprocess datasets:  77%|███████▋  | 15463/20000 [03:31<00:49, 90.82 examples/s] 
preprocess datasets:  77%|███████▋  | 15473/20000 [03:31<00:53, 85.13 examples/s]
preprocess datasets:  77%|███████▋  | 15484/20000 [03:31<00:52, 86.36 examples/s]
preprocess datasets:  77%|███████▋  | 15499/20000 [03:31<00:44, 100.04 examples/s]
preprocess datasets:  78%|███████▊  | 15512/20000 [03:31<00:49, 90.39 examples/s] 
preprocess datasets:  78%|███████▊  | 15526/20000 [03:31<00:52, 85.99 examples/s]
preprocess datasets:  78%|███████▊  | 15543/20000 [03:31<00:44, 99.12 examples/s]
preprocess datasets:  78%|███████▊  | 15556/20000 [03:32<00:43, 102.91 examples/s]
preprocess datasets:  78%|███████▊  | 15567/20000 [03:32<00:43, 102.47 examples/s]
preprocess datasets:  78%|███████▊  | 15582/20000 [03:32<00:44, 99.47 examples/s] 
preprocess datasets:  78%|███████▊  | 15594/20000 [03:32<00:51, 85.87 examples/s]
preprocess datasets:  78%|███████▊  | 15605/20000 [03:32<00:49, 88.13 examples/s]
preprocess datasets:  78%|███████▊  | 15615/20000 [03:32<00:50, 87.63 examples/s]
preprocess datasets:  78%|███████▊  | 15630/20000 [03:32<00:50, 86.88 examples/s]
preprocess datasets:  78%|███████▊  | 15642/20000 [03:33<00:47, 92.13 examples/s]
preprocess datasets:  78%|███████▊  | 15653/20000 [03:33<00:46, 93.54 examples/s]
preprocess datasets:  78%|███████▊  | 15666/20000 [03:33<00:50, 86.00 examples/s]
preprocess datasets:  78%|███████▊  | 15676/20000 [03:33<00:50, 85.13 examples/s]
preprocess datasets:  78%|███████▊  | 15692/20000 [03:33<00:42, 100.59 examples/s]
preprocess datasets:  79%|███████▊  | 15707/20000 [03:33<00:40, 105.24 examples/s]
preprocess datasets:  79%|███████▊  | 15719/20000 [03:33<00:42, 101.88 examples/s]
preprocess datasets:  79%|███████▊  | 15732/20000 [03:33<00:41, 103.56 examples/s]
preprocess datasets:  79%|███████▊  | 15743/20000 [03:34<00:43, 97.28 examples/s] 
preprocess datasets:  79%|███████▉  | 15757/20000 [03:34<00:40, 105.64 examples/s]
preprocess datasets:  79%|███████▉  | 15773/20000 [03:34<00:42, 99.87 examples/s] 
preprocess datasets:  79%|███████▉  | 15785/20000 [03:34<00:40, 103.40 examples/s]
preprocess datasets:  79%|███████▉  | 15804/20000 [03:34<00:39, 106.77 examples/s]
preprocess datasets:  79%|███████▉  | 15823/20000 [03:34<00:38, 108.18 examples/s]
preprocess datasets:  79%|███████▉  | 15835/20000 [03:34<00:39, 105.98 examples/s]
preprocess datasets:  79%|███████▉  | 15852/20000 [03:35<00:39, 104.02 examples/s]
preprocess datasets:  79%|███████▉  | 15863/20000 [03:35<00:40, 102.00 examples/s]
preprocess datasets:  79%|███████▉  | 15877/20000 [03:35<00:44, 93.12 examples/s] 
preprocess datasets:  79%|███████▉  | 15889/20000 [03:35<00:48, 84.34 examples/s]
preprocess datasets:  80%|███████▉  | 15901/20000 [03:35<00:45, 90.35 examples/s]
preprocess datasets:  80%|███████▉  | 15915/20000 [03:35<00:42, 96.86 examples/s]
preprocess datasets:  80%|███████▉  | 15930/20000 [03:35<00:43, 94.15 examples/s]
preprocess datasets:  80%|███████▉  | 15940/20000 [03:36<00:43, 93.25 examples/s]
preprocess datasets:  80%|███████▉  | 15950/20000 [03:36<00:43, 92.92 examples/s]
preprocess datasets:  80%|███████▉  | 15963/20000 [03:36<00:40, 100.78 examples/s]
preprocess datasets:  80%|███████▉  | 15976/20000 [03:36<00:44, 90.22 examples/s] 
preprocess datasets:  80%|███████▉  | 15988/20000 [03:36<00:43, 92.48 examples/s]
preprocess datasets:  80%|████████  | 16000/20000 [03:37<02:26, 27.30 examples/s]
preprocess datasets:  80%|████████  | 16011/20000 [03:37<01:58, 33.78 examples/s]
preprocess datasets:  80%|████████  | 16022/20000 [03:37<01:36, 41.26 examples/s]
preprocess datasets:  80%|████████  | 16035/20000 [03:38<01:15, 52.81 examples/s]
preprocess datasets:  80%|████████  | 16051/20000 [03:38<01:03, 62.46 examples/s]
preprocess datasets:  80%|████████  | 16062/20000 [03:38<00:57, 68.86 examples/s]
preprocess datasets:  80%|████████  | 16075/20000 [03:38<00:51, 76.72 examples/s]
preprocess datasets:  80%|████████  | 16089/20000 [03:38<00:45, 85.87 examples/s]
preprocess datasets:  81%|████████  | 16102/20000 [03:38<00:43, 90.61 examples/s]
preprocess datasets:  81%|████████  | 16114/20000 [03:38<00:42, 91.34 examples/s]
preprocess datasets:  81%|████████  | 16130/20000 [03:39<00:41, 92.59 examples/s]
preprocess datasets:  81%|████████  | 16140/20000 [03:39<00:41, 94.07 examples/s]
preprocess datasets:  81%|████████  | 16153/20000 [03:39<00:43, 87.97 examples/s]
preprocess datasets:  81%|████████  | 16165/20000 [03:39<00:41, 91.84 examples/s]
preprocess datasets:  81%|████████  | 16175/20000 [03:39<00:41, 91.33 examples/s]
preprocess datasets:  81%|████████  | 16186/20000 [03:39<00:40, 94.89 examples/s]
preprocess datasets:  81%|████████  | 16203/20000 [03:39<00:36, 104.46 examples/s]
preprocess datasets:  81%|████████  | 16216/20000 [03:39<00:39, 96.56 examples/s] 
preprocess datasets:  81%|████████  | 16230/20000 [03:40<00:37, 101.57 examples/s]
preprocess datasets:  81%|████████  | 16244/20000 [03:40<00:40, 92.98 examples/s] 
preprocess datasets:  81%|████████▏ | 16262/20000 [03:40<00:37, 100.09 examples/s]
preprocess datasets:  81%|████████▏ | 16274/20000 [03:40<00:36, 102.87 examples/s]
preprocess datasets:  81%|████████▏ | 16289/20000 [03:41<02:16, 27.12 examples/s] 
preprocess datasets:  82%|████████▏ | 16304/20000 [03:42<01:43, 35.88 examples/s]
preprocess datasets:  82%|████████▏ | 16315/20000 [03:42<01:27, 42.12 examples/s]
preprocess datasets:  82%|████████▏ | 16328/20000 [03:42<01:11, 51.34 examples/s]
preprocess datasets:  82%|████████▏ | 16342/20000 [03:42<00:58, 62.23 examples/s]
preprocess datasets:  82%|████████▏ | 16355/20000 [03:42<00:57, 63.50 examples/s]
preprocess datasets:  82%|████████▏ | 16372/20000 [03:42<00:49, 72.57 examples/s]
preprocess datasets:  82%|████████▏ | 16382/20000 [03:42<00:48, 74.84 examples/s]
preprocess datasets:  82%|████████▏ | 16397/20000 [03:43<00:40, 88.19 examples/s]
preprocess datasets:  82%|████████▏ | 16410/20000 [03:43<00:39, 90.83 examples/s]
preprocess datasets:  82%|████████▏ | 16425/20000 [03:43<00:42, 84.55 examples/s]
preprocess datasets:  82%|████████▏ | 16435/20000 [03:43<00:41, 85.03 examples/s]
preprocess datasets:  82%|████████▏ | 16446/20000 [03:43<00:45, 77.94 examples/s]
preprocess datasets:  82%|████████▏ | 16455/20000 [03:43<00:45, 78.66 examples/s]
preprocess datasets:  82%|████████▏ | 16470/20000 [03:43<00:39, 89.43 examples/s]
preprocess datasets:  82%|████████▏ | 16481/20000 [03:43<00:37, 93.15 examples/s]
preprocess datasets:  82%|████████▏ | 16495/20000 [03:44<00:34, 101.12 examples/s]
preprocess datasets:  83%|████████▎ | 16508/20000 [03:44<00:34, 102.58 examples/s]
preprocess datasets:  83%|████████▎ | 16525/20000 [03:44<00:33, 105.22 examples/s]
preprocess datasets:  83%|████████▎ | 16541/20000 [03:44<00:33, 104.67 examples/s]
preprocess datasets:  83%|████████▎ | 16554/20000 [03:44<00:31, 108.96 examples/s]
preprocess datasets:  83%|████████▎ | 16571/20000 [03:44<00:33, 102.52 examples/s]
preprocess datasets:  83%|████████▎ | 16584/20000 [03:44<00:32, 105.21 examples/s]
preprocess datasets:  83%|████████▎ | 16597/20000 [03:45<00:32, 105.92 examples/s]
preprocess datasets:  83%|████████▎ | 16608/20000 [03:45<00:33, 101.96 examples/s]
preprocess datasets:  83%|████████▎ | 16622/20000 [03:45<00:35, 94.10 examples/s] 
preprocess datasets:  83%|████████▎ | 16634/20000 [03:45<00:42, 78.41 examples/s]
preprocess datasets:  83%|████████▎ | 16646/20000 [03:45<00:40, 83.30 examples/s]
preprocess datasets:  83%|████████▎ | 16655/20000 [03:45<00:43, 76.64 examples/s]
preprocess datasets:  83%|████████▎ | 16667/20000 [03:45<00:39, 84.44 examples/s]
preprocess datasets:  83%|████████▎ | 16677/20000 [03:46<00:42, 77.54 examples/s]
preprocess datasets:  83%|████████▎ | 16694/20000 [03:46<00:34, 94.59 examples/s]
preprocess datasets:  84%|████████▎ | 16708/20000 [03:46<00:36, 90.44 examples/s]
preprocess datasets:  84%|████████▎ | 16720/20000 [03:46<00:40, 81.25 examples/s]
preprocess datasets:  84%|████████▎ | 16731/20000 [03:46<00:38, 85.60 examples/s]
preprocess datasets:  84%|████████▎ | 16747/20000 [03:46<00:36, 89.87 examples/s]
preprocess datasets:  84%|████████▍ | 16763/20000 [03:47<00:36, 89.55 examples/s]
preprocess datasets:  84%|████████▍ | 16774/20000 [03:47<00:37, 86.55 examples/s]
preprocess datasets:  84%|████████▍ | 16786/20000 [03:47<00:35, 90.51 examples/s]
preprocess datasets:  84%|████████▍ | 16797/20000 [03:47<00:38, 82.93 examples/s]
preprocess datasets:  84%|████████▍ | 16810/20000 [03:47<00:35, 90.73 examples/s]
preprocess datasets:  84%|████████▍ | 16820/20000 [03:47<00:34, 91.83 examples/s]
preprocess datasets:  84%|████████▍ | 16834/20000 [03:47<00:32, 97.81 examples/s]
preprocess datasets:  84%|████████▍ | 16849/20000 [03:47<00:29, 108.54 examples/s]
preprocess datasets:  84%|████████▍ | 16864/20000 [03:48<00:33, 93.51 examples/s] 
preprocess datasets:  84%|████████▍ | 16877/20000 [03:48<00:31, 97.87 examples/s]
preprocess datasets:  84%|████████▍ | 16891/20000 [03:48<00:33, 93.26 examples/s]
preprocess datasets:  85%|████████▍ | 16906/20000 [03:48<00:30, 100.26 examples/s]
preprocess datasets:  85%|████████▍ | 16920/20000 [03:48<00:34, 90.54 examples/s] 
preprocess datasets:  85%|████████▍ | 16934/20000 [03:48<00:32, 95.22 examples/s]
preprocess datasets:  85%|████████▍ | 16951/20000 [03:48<00:27, 110.83 examples/s]
preprocess datasets:  85%|████████▍ | 16964/20000 [03:49<00:31, 95.58 examples/s] 
preprocess datasets:  85%|████████▍ | 16975/20000 [03:49<00:31, 95.91 examples/s]
preprocess datasets:  85%|████████▍ | 16988/20000 [03:49<00:50, 59.31 examples/s]
preprocess datasets:  85%|████████▌ | 17000/20000 [03:50<01:35, 31.43 examples/s]
preprocess datasets:  85%|████████▌ | 17008/20000 [03:50<01:23, 35.62 examples/s]
preprocess datasets:  85%|████████▌ | 17019/20000 [03:50<01:07, 44.02 examples/s]
preprocess datasets:  85%|████████▌ | 17032/20000 [03:50<00:55, 53.95 examples/s]
preprocess datasets:  85%|████████▌ | 17041/20000 [03:50<00:50, 58.58 examples/s]
preprocess datasets:  85%|████████▌ | 17050/20000 [03:51<00:46, 63.45 examples/s]
preprocess datasets:  85%|████████▌ | 17059/20000 [03:51<00:46, 63.89 examples/s]
preprocess datasets:  85%|████████▌ | 17071/20000 [03:51<00:39, 74.81 examples/s]
preprocess datasets:  85%|████████▌ | 17080/20000 [03:51<00:37, 77.52 examples/s]
preprocess datasets:  85%|████████▌ | 17089/20000 [03:51<00:37, 77.41 examples/s]
preprocess datasets:  85%|████████▌ | 17099/20000 [03:51<00:35, 82.05 examples/s]
preprocess datasets:  86%|████████▌ | 17112/20000 [03:51<00:32, 90.06 examples/s]
preprocess datasets:  86%|████████▌ | 17124/20000 [03:51<00:35, 81.31 examples/s]
preprocess datasets:  86%|████████▌ | 17134/20000 [03:52<00:34, 83.57 examples/s]
preprocess datasets:  86%|████████▌ | 17144/20000 [03:52<00:34, 83.90 examples/s]
preprocess datasets:  86%|████████▌ | 17158/20000 [03:52<00:32, 87.48 examples/s]
preprocess datasets:  86%|████████▌ | 17170/20000 [03:52<00:35, 80.35 examples/s]
preprocess datasets:  86%|████████▌ | 17180/20000 [03:52<00:35, 78.52 examples/s]
preprocess datasets:  86%|████████▌ | 17192/20000 [03:52<00:32, 85.24 examples/s]
preprocess datasets:  86%|████████▌ | 17201/20000 [03:52<00:32, 85.74 examples/s]
preprocess datasets:  86%|████████▌ | 17211/20000 [03:52<00:31, 87.70 examples/s]
preprocess datasets:  86%|████████▌ | 17221/20000 [03:53<00:31, 88.29 examples/s]
preprocess datasets:  86%|████████▌ | 17230/20000 [03:53<00:32, 84.05 examples/s]
preprocess datasets:  86%|████████▌ | 17241/20000 [03:53<00:31, 87.74 examples/s]
preprocess datasets:  86%|████████▋ | 17250/20000 [03:53<00:31, 88.00 examples/s]
preprocess datasets:  86%|████████▋ | 17264/20000 [03:53<00:28, 95.03 examples/s]
preprocess datasets:  86%|████████▋ | 17276/20000 [03:53<00:28, 97.02 examples/s]
preprocess datasets:  86%|████████▋ | 17287/20000 [03:53<00:28, 96.27 examples/s]
preprocess datasets:  86%|████████▋ | 17299/20000 [03:53<00:27, 97.55 examples/s]
preprocess datasets:  87%|████████▋ | 17315/20000 [03:54<00:24, 108.15 examples/s]
preprocess datasets:  87%|████████▋ | 17326/20000 [03:54<00:29, 89.88 examples/s] 
preprocess datasets:  87%|████████▋ | 17337/20000 [03:54<00:29, 91.18 examples/s]
preprocess datasets:  87%|████████▋ | 17349/20000 [03:54<00:31, 83.70 examples/s]
preprocess datasets:  87%|████████▋ | 17360/20000 [03:54<00:30, 85.33 examples/s]
preprocess datasets:  87%|████████▋ | 17369/20000 [03:54<00:31, 83.73 examples/s]
preprocess datasets:  87%|████████▋ | 17381/20000 [03:54<00:29, 88.46 examples/s]
preprocess datasets:  87%|████████▋ | 17390/20000 [03:54<00:30, 85.73 examples/s]
preprocess datasets:  87%|████████▋ | 17401/20000 [03:55<00:29, 87.77 examples/s]
preprocess datasets:  87%|████████▋ | 17411/20000 [03:55<00:28, 90.03 examples/s]
preprocess datasets:  87%|████████▋ | 17426/20000 [03:55<00:29, 87.41 examples/s]
preprocess datasets:  87%|████████▋ | 17436/20000 [03:55<00:34, 75.04 examples/s]
preprocess datasets:  87%|████████▋ | 17449/20000 [03:55<00:30, 83.20 examples/s]
preprocess datasets:  87%|████████▋ | 17459/20000 [03:55<00:30, 82.93 examples/s]
preprocess datasets:  87%|████████▋ | 17471/20000 [03:55<00:28, 87.34 examples/s]
preprocess datasets:  87%|████████▋ | 17482/20000 [03:56<00:31, 79.01 examples/s]
preprocess datasets:  87%|████████▋ | 17496/20000 [03:56<00:28, 88.52 examples/s]
preprocess datasets:  88%|████████▊ | 17506/20000 [03:56<00:28, 86.37 examples/s]
preprocess datasets:  88%|████████▊ | 17516/20000 [03:56<00:28, 86.84 examples/s]
preprocess datasets:  88%|████████▊ | 17528/20000 [03:56<00:31, 79.05 examples/s]
preprocess datasets:  88%|████████▊ | 17540/20000 [03:56<00:28, 84.95 examples/s]
preprocess datasets:  88%|████████▊ | 17551/20000 [03:56<00:28, 87.17 examples/s]
preprocess datasets:  88%|████████▊ | 17563/20000 [03:56<00:25, 94.99 examples/s]
preprocess datasets:  88%|████████▊ | 17575/20000 [03:57<00:24, 98.48 examples/s]
preprocess datasets:  88%|████████▊ | 17590/20000 [03:57<00:22, 109.53 examples/s]
preprocess datasets:  88%|████████▊ | 17602/20000 [03:57<00:22, 104.83 examples/s]
preprocess datasets:  88%|████████▊ | 17616/20000 [03:57<00:21, 113.31 examples/s]
preprocess datasets:  88%|████████▊ | 17629/20000 [03:57<00:24, 98.29 examples/s] 
preprocess datasets:  88%|████████▊ | 17644/20000 [03:57<00:24, 94.82 examples/s]
preprocess datasets:  88%|████████▊ | 17656/20000 [03:57<00:28, 80.97 examples/s]
preprocess datasets:  88%|████████▊ | 17668/20000 [03:58<00:27, 85.40 examples/s]
preprocess datasets:  88%|████████▊ | 17678/20000 [03:58<00:26, 87.67 examples/s]
preprocess datasets:  88%|████████▊ | 17688/20000 [03:58<00:30, 76.42 examples/s]
preprocess datasets:  89%|████████▊ | 17701/20000 [03:58<00:26, 85.66 examples/s]
preprocess datasets:  89%|████████▊ | 17715/20000 [03:58<00:27, 84.14 examples/s]
preprocess datasets:  89%|████████▊ | 17725/20000 [03:58<00:27, 81.76 examples/s]
preprocess datasets:  89%|████████▊ | 17740/20000 [03:58<00:24, 91.08 examples/s]
preprocess datasets:  89%|████████▉ | 17750/20000 [03:59<00:24, 91.07 examples/s]
preprocess datasets:  89%|████████▉ | 17762/20000 [03:59<00:24, 90.72 examples/s]
preprocess datasets:  89%|████████▉ | 17773/20000 [03:59<00:24, 92.61 examples/s]
preprocess datasets:  89%|████████▉ | 17786/20000 [03:59<00:22, 98.10 examples/s]
preprocess datasets:  89%|████████▉ | 17799/20000 [03:59<00:24, 90.72 examples/s]
preprocess datasets:  89%|████████▉ | 17814/20000 [03:59<00:24, 88.03 examples/s]
preprocess datasets:  89%|████████▉ | 17828/20000 [03:59<00:23, 93.51 examples/s]
preprocess datasets:  89%|████████▉ | 17840/20000 [04:00<00:25, 84.28 examples/s]
preprocess datasets:  89%|████████▉ | 17851/20000 [04:00<00:24, 86.07 examples/s]
preprocess datasets:  89%|████████▉ | 17866/20000 [04:00<00:24, 87.56 examples/s]
preprocess datasets:  89%|████████▉ | 17877/20000 [04:00<00:23, 90.31 examples/s]
preprocess datasets:  89%|████████▉ | 17887/20000 [04:00<00:23, 89.80 examples/s]
preprocess datasets:  90%|████████▉ | 17900/20000 [04:00<00:22, 94.45 examples/s]
preprocess datasets:  90%|████████▉ | 17916/20000 [04:00<00:21, 97.49 examples/s]
preprocess datasets:  90%|████████▉ | 17927/20000 [04:00<00:21, 95.58 examples/s]
preprocess datasets:  90%|████████▉ | 17941/20000 [04:01<00:20, 99.05 examples/s]
preprocess datasets:  90%|████████▉ | 17951/20000 [04:01<00:21, 96.50 examples/s]
preprocess datasets:  90%|████████▉ | 17962/20000 [04:01<00:21, 95.26 examples/s]
preprocess datasets:  90%|████████▉ | 17977/20000 [04:01<00:21, 92.03 examples/s]
preprocess datasets:  90%|████████▉ | 17987/20000 [04:01<00:22, 87.54 examples/s]
preprocess datasets:  90%|████████▉ | 17998/20000 [04:01<00:22, 87.23 examples/s]
preprocess datasets:  90%|█████████ | 18011/20000 [04:02<01:03, 31.56 examples/s]
preprocess datasets:  90%|█████████ | 18026/20000 [04:02<00:46, 42.66 examples/s]
preprocess datasets:  90%|█████████ | 18039/20000 [04:02<00:39, 49.12 examples/s]
preprocess datasets:  90%|█████████ | 18053/20000 [04:03<00:33, 58.77 examples/s]
preprocess datasets:  90%|█████████ | 18065/20000 [04:03<00:28, 66.83 examples/s]
preprocess datasets:  90%|█████████ | 18078/20000 [04:03<00:25, 76.40 examples/s]
preprocess datasets:  90%|█████████ | 18092/20000 [04:03<00:23, 82.92 examples/s]
preprocess datasets:  91%|█████████ | 18102/20000 [04:03<00:22, 84.69 examples/s]
preprocess datasets:  91%|█████████ | 18117/20000 [04:03<00:21, 87.54 examples/s]
preprocess datasets:  91%|█████████ | 18132/20000 [04:03<00:18, 100.39 examples/s]
preprocess datasets:  91%|█████████ | 18147/20000 [04:03<00:17, 107.11 examples/s]
preprocess datasets:  91%|█████████ | 18164/20000 [04:04<00:17, 103.89 examples/s]
preprocess datasets:  91%|█████████ | 18177/20000 [04:04<00:19, 93.95 examples/s] 
preprocess datasets:  91%|█████████ | 18189/20000 [04:04<00:18, 96.16 examples/s]
preprocess datasets:  91%|█████████ | 18201/20000 [04:04<00:28, 63.83 examples/s]
preprocess datasets:  91%|█████████ | 18212/20000 [04:04<00:25, 69.87 examples/s]
preprocess datasets:  91%|█████████ | 18222/20000 [04:05<00:24, 72.46 examples/s]
preprocess datasets:  91%|█████████ | 18232/20000 [04:05<00:24, 73.39 examples/s]
preprocess datasets:  91%|█████████▏| 18251/20000 [04:05<00:20, 85.73 examples/s]
preprocess datasets:  91%|█████████▏| 18261/20000 [04:05<00:20, 85.87 examples/s]
preprocess datasets:  91%|█████████▏| 18272/20000 [04:05<00:19, 87.91 examples/s]
preprocess datasets:  91%|█████████▏| 18284/20000 [04:05<00:21, 81.14 examples/s]
preprocess datasets:  91%|█████████▏| 18296/20000 [04:05<00:19, 87.30 examples/s]
preprocess datasets:  92%|█████████▏| 18307/20000 [04:05<00:18, 90.67 examples/s]
preprocess datasets:  92%|█████████▏| 18317/20000 [04:06<00:18, 89.47 examples/s]
preprocess datasets:  92%|█████████▏| 18331/20000 [04:06<00:17, 94.65 examples/s]
preprocess datasets:  92%|█████████▏| 18342/20000 [04:06<00:17, 96.08 examples/s]
preprocess datasets:  92%|█████████▏| 18356/20000 [04:06<00:19, 85.46 examples/s]
preprocess datasets:  92%|█████████▏| 18365/20000 [04:06<00:19, 82.81 examples/s]
preprocess datasets:  92%|█████████▏| 18374/20000 [04:06<00:19, 81.31 examples/s]
preprocess datasets:  92%|█████████▏| 18384/20000 [04:06<00:19, 82.05 examples/s]
preprocess datasets:  92%|█████████▏| 18398/20000 [04:07<00:17, 91.91 examples/s]
preprocess datasets:  92%|█████████▏| 18409/20000 [04:07<00:17, 88.47 examples/s]
preprocess datasets:  92%|█████████▏| 18421/20000 [04:07<00:16, 92.90 examples/s]
preprocess datasets:  92%|█████████▏| 18436/20000 [04:07<00:14, 107.30 examples/s]
preprocess datasets:  92%|█████████▏| 18450/20000 [04:07<00:16, 93.20 examples/s] 
preprocess datasets:  92%|█████████▏| 18463/20000 [04:07<00:15, 97.64 examples/s]
preprocess datasets:  92%|█████████▏| 18480/20000 [04:07<00:15, 95.85 examples/s]
preprocess datasets:  92%|█████████▏| 18494/20000 [04:07<00:14, 102.27 examples/s]
preprocess datasets:  93%|█████████▎| 18506/20000 [04:08<00:15, 93.60 examples/s] 
preprocess datasets:  93%|█████████▎| 18519/20000 [04:08<00:17, 85.29 examples/s]
preprocess datasets:  93%|█████████▎| 18528/20000 [04:08<00:17, 85.57 examples/s]
preprocess datasets:  93%|█████████▎| 18538/20000 [04:08<00:17, 84.81 examples/s]
preprocess datasets:  93%|█████████▎| 18551/20000 [04:08<00:15, 93.68 examples/s]
preprocess datasets:  93%|█████████▎| 18562/20000 [04:08<00:18, 79.01 examples/s]
preprocess datasets:  93%|█████████▎| 18572/20000 [04:08<00:17, 79.64 examples/s]
preprocess datasets:  93%|█████████▎| 18584/20000 [04:09<00:18, 77.66 examples/s]
preprocess datasets:  93%|█████████▎| 18595/20000 [04:09<00:16, 84.94 examples/s]
preprocess datasets:  93%|█████████▎| 18607/20000 [04:09<00:17, 77.57 examples/s]
preprocess datasets:  93%|█████████▎| 18620/20000 [04:09<00:18, 76.57 examples/s]
preprocess datasets:  93%|█████████▎| 18631/20000 [04:09<00:18, 74.62 examples/s]
preprocess datasets:  93%|█████████▎| 18646/20000 [04:09<00:19, 70.06 examples/s]
preprocess datasets:  93%|█████████▎| 18654/20000 [04:10<00:19, 69.65 examples/s]
preprocess datasets:  93%|█████████▎| 18665/20000 [04:10<00:17, 75.97 examples/s]
preprocess datasets:  93%|█████████▎| 18675/20000 [04:10<00:16, 79.73 examples/s]
preprocess datasets:  93%|█████████▎| 18687/20000 [04:10<00:15, 86.46 examples/s]
preprocess datasets:  94%|█████████▎| 18701/20000 [04:10<00:15, 85.29 examples/s]
preprocess datasets:  94%|█████████▎| 18717/20000 [04:10<00:12, 101.31 examples/s]
preprocess datasets:  94%|█████████▎| 18728/20000 [04:10<00:14, 87.66 examples/s] 
preprocess datasets:  94%|█████████▎| 18743/20000 [04:11<00:14, 86.48 examples/s]
preprocess datasets:  94%|█████████▍| 18757/20000 [04:11<00:14, 83.20 examples/s]
preprocess datasets:  94%|█████████▍| 18769/20000 [04:11<00:14, 87.20 examples/s]
preprocess datasets:  94%|█████████▍| 18783/20000 [04:11<00:14, 85.58 examples/s]
preprocess datasets:  94%|█████████▍| 18793/20000 [04:11<00:14, 84.12 examples/s]
preprocess datasets:  94%|█████████▍| 18805/20000 [04:11<00:13, 91.14 examples/s]
preprocess datasets:  94%|█████████▍| 18818/20000 [04:11<00:13, 87.65 examples/s]
preprocess datasets:  94%|█████████▍| 18834/20000 [04:12<00:13, 87.02 examples/s]
preprocess datasets:  94%|█████████▍| 18846/20000 [04:12<00:12, 91.89 examples/s]
preprocess datasets:  94%|█████████▍| 18856/20000 [04:12<00:12, 92.60 examples/s]
preprocess datasets:  94%|█████████▍| 18870/20000 [04:12<00:11, 99.90 examples/s]
preprocess datasets:  94%|█████████▍| 18886/20000 [04:12<00:09, 112.75 examples/s]
preprocess datasets:  95%|█████████▍| 18901/20000 [04:12<00:10, 104.64 examples/s]
preprocess datasets:  95%|█████████▍| 18913/20000 [04:12<00:10, 106.76 examples/s]
preprocess datasets:  95%|█████████▍| 18924/20000 [04:12<00:10, 105.31 examples/s]
preprocess datasets:  95%|█████████▍| 18936/20000 [04:13<00:10, 102.26 examples/s]
preprocess datasets:  95%|█████████▍| 18950/20000 [04:13<00:09, 106.61 examples/s]
preprocess datasets:  95%|█████████▍| 18966/20000 [04:13<00:09, 103.84 examples/s]
preprocess datasets:  95%|█████████▍| 18978/20000 [04:13<00:11, 88.20 examples/s] 
preprocess datasets:  95%|█████████▍| 18993/20000 [04:13<00:10, 95.83 examples/s]
preprocess datasets:  95%|█████████▌| 19004/20000 [04:14<00:29, 33.66 examples/s]
preprocess datasets:  95%|█████████▌| 19014/20000 [04:14<00:24, 40.09 examples/s]
preprocess datasets:  95%|█████████▌| 19025/20000 [04:14<00:21, 44.65 examples/s]
preprocess datasets:  95%|█████████▌| 19035/20000 [04:15<00:19, 50.17 examples/s]
preprocess datasets:  95%|█████████▌| 19045/20000 [04:15<00:17, 55.64 examples/s]
preprocess datasets:  95%|█████████▌| 19054/20000 [04:15<00:16, 56.37 examples/s]
preprocess datasets:  95%|█████████▌| 19063/20000 [04:15<00:17, 54.90 examples/s]
preprocess datasets:  95%|█████████▌| 19074/20000 [04:15<00:14, 62.57 examples/s]
preprocess datasets:  95%|█████████▌| 19084/20000 [04:15<00:13, 68.18 examples/s]
preprocess datasets:  95%|█████████▌| 19095/20000 [04:15<00:11, 75.68 examples/s]
preprocess datasets:  96%|█████████▌| 19106/20000 [04:15<00:11, 81.18 examples/s]
preprocess datasets:  96%|█████████▌| 19115/20000 [04:16<00:11, 80.01 examples/s]
preprocess datasets:  96%|█████████▌| 19126/20000 [04:16<00:10, 84.93 examples/s]
preprocess datasets:  96%|█████████▌| 19137/20000 [04:16<00:10, 83.25 examples/s]
preprocess datasets:  96%|█████████▌| 19146/20000 [04:16<00:10, 83.01 examples/s]
preprocess datasets:  96%|█████████▌| 19158/20000 [04:16<00:09, 87.02 examples/s]
preprocess datasets:  96%|█████████▌| 19169/20000 [04:16<00:10, 77.86 examples/s]
preprocess datasets:  96%|█████████▌| 19180/20000 [04:16<00:10, 78.30 examples/s]
preprocess datasets:  96%|█████████▌| 19192/20000 [04:16<00:09, 86.36 examples/s]
preprocess datasets:  96%|█████████▌| 19202/20000 [04:17<00:09, 83.16 examples/s]
preprocess datasets:  96%|█████████▌| 19216/20000 [04:17<00:08, 94.77 examples/s]
preprocess datasets:  96%|█████████▌| 19227/20000 [04:17<00:08, 86.87 examples/s]
preprocess datasets:  96%|█████████▌| 19240/20000 [04:17<00:08, 84.69 examples/s]
preprocess datasets:  96%|█████████▋| 19252/20000 [04:17<00:09, 77.73 examples/s]
preprocess datasets:  96%|█████████▋| 19265/20000 [04:17<00:09, 79.22 examples/s]
preprocess datasets:  96%|█████████▋| 19282/20000 [04:17<00:07, 96.26 examples/s]
preprocess datasets:  96%|█████████▋| 19296/20000 [04:18<00:06, 100.91 examples/s]
preprocess datasets:  97%|█████████▋| 19308/20000 [04:18<00:07, 98.46 examples/s] 
preprocess datasets:  97%|█████████▋| 19324/20000 [04:18<00:07, 95.30 examples/s]
preprocess datasets:  97%|█████████▋| 19336/20000 [04:18<00:07, 88.23 examples/s]
preprocess datasets:  97%|█████████▋| 19346/20000 [04:18<00:07, 88.66 examples/s]
preprocess datasets:  97%|█████████▋| 19358/20000 [04:18<00:06, 93.54 examples/s]
preprocess datasets:  97%|█████████▋| 19369/20000 [04:18<00:06, 95.13 examples/s]
preprocess datasets:  97%|█████████▋| 19383/20000 [04:19<00:06, 88.69 examples/s]
preprocess datasets:  97%|█████████▋| 19394/20000 [04:19<00:06, 90.16 examples/s]
preprocess datasets:  97%|█████████▋| 19405/20000 [04:19<00:06, 91.40 examples/s]
preprocess datasets:  97%|█████████▋| 19417/20000 [04:19<00:07, 80.52 examples/s]
preprocess datasets:  97%|█████████▋| 19427/20000 [04:19<00:07, 79.30 examples/s]
preprocess datasets:  97%|█████████▋| 19437/20000 [04:19<00:06, 80.46 examples/s]
preprocess datasets:  97%|█████████▋| 19446/20000 [04:19<00:06, 79.28 examples/s]
preprocess datasets:  97%|█████████▋| 19456/20000 [04:19<00:06, 82.08 examples/s]
preprocess datasets:  97%|█████████▋| 19468/20000 [04:20<00:05, 91.18 examples/s]
preprocess datasets:  97%|█████████▋| 19478/20000 [04:20<00:05, 87.52 examples/s]
preprocess datasets:  97%|█████████▋| 19490/20000 [04:20<00:05, 89.60 examples/s]
preprocess datasets:  98%|█████████▊| 19501/20000 [04:20<00:05, 89.28 examples/s]
preprocess datasets:  98%|█████████▊| 19514/20000 [04:20<00:05, 96.72 examples/s]
preprocess datasets:  98%|█████████▊| 19530/20000 [04:20<00:04, 110.61 examples/s]
preprocess datasets:  98%|█████████▊| 19544/20000 [04:20<00:05, 88.98 examples/s] 
preprocess datasets:  98%|█████████▊| 19554/20000 [04:21<00:05, 86.40 examples/s]
preprocess datasets:  98%|█████████▊| 19568/20000 [04:21<00:04, 98.63 examples/s]
preprocess datasets:  98%|█████████▊| 19581/20000 [04:21<00:04, 103.86 examples/s]
preprocess datasets:  98%|█████████▊| 19593/20000 [04:21<00:04, 90.76 examples/s] 
preprocess datasets:  98%|█████████▊| 19603/20000 [04:21<00:04, 89.92 examples/s]
preprocess datasets:  98%|█████████▊| 19616/20000 [04:21<00:04, 81.22 examples/s]
preprocess datasets:  98%|█████████▊| 19629/20000 [04:21<00:04, 89.57 examples/s]
preprocess datasets:  98%|█████████▊| 19645/20000 [04:22<00:03, 91.98 examples/s]
preprocess datasets:  98%|█████████▊| 19655/20000 [04:22<00:03, 91.37 examples/s]
preprocess datasets:  98%|█████████▊| 19666/20000 [04:22<00:03, 92.91 examples/s]
preprocess datasets:  98%|█████████▊| 19677/20000 [04:22<00:03, 93.97 examples/s]
preprocess datasets:  98%|█████████▊| 19689/20000 [04:22<00:03, 96.33 examples/s]
preprocess datasets:  98%|█████████▊| 19699/20000 [04:22<00:03, 95.24 examples/s]
preprocess datasets:  99%|█████████▊| 19710/20000 [04:22<00:03, 81.80 examples/s]
preprocess datasets:  99%|█████████▊| 19719/20000 [04:22<00:03, 79.35 examples/s]
preprocess datasets:  99%|█████████▊| 19732/20000 [04:22<00:03, 86.01 examples/s]
preprocess datasets:  99%|█████████▊| 19744/20000 [04:23<00:02, 89.15 examples/s]
preprocess datasets:  99%|█████████▉| 19756/20000 [04:23<00:02, 93.82 examples/s]
preprocess datasets:  99%|█████████▉| 19767/20000 [04:23<00:02, 91.96 examples/s]
preprocess datasets:  99%|█████████▉| 19777/20000 [04:23<00:02, 86.19 examples/s]
preprocess datasets:  99%|█████████▉| 19790/20000 [04:23<00:02, 81.56 examples/s]
preprocess datasets:  99%|█████████▉| 19806/20000 [04:23<00:02, 96.76 examples/s]
preprocess datasets:  99%|█████████▉| 19818/20000 [04:23<00:01, 99.14 examples/s]
preprocess datasets:  99%|█████████▉| 19834/20000 [04:24<00:01, 96.64 examples/s]
preprocess datasets:  99%|█████████▉| 19844/20000 [04:24<00:01, 96.89 examples/s]
preprocess datasets:  99%|█████████▉| 19855/20000 [04:24<00:01, 96.54 examples/s]
preprocess datasets:  99%|█████████▉| 19867/20000 [04:24<00:01, 99.52 examples/s]
preprocess datasets:  99%|█████████▉| 19879/20000 [04:24<00:01, 100.98 examples/s]
preprocess datasets:  99%|█████████▉| 19892/20000 [04:24<00:01, 87.71 examples/s] 
preprocess datasets: 100%|█████████▉| 19905/20000 [04:24<00:01, 84.83 examples/s]
preprocess datasets: 100%|█████████▉| 19916/20000 [04:25<00:01, 74.45 examples/s]
preprocess datasets: 100%|█████████▉| 19929/20000 [04:25<00:00, 84.08 examples/s]
preprocess datasets: 100%|█████████▉| 19938/20000 [04:25<00:00, 84.55 examples/s]
preprocess datasets: 100%|█████████▉| 19951/20000 [04:25<00:00, 89.14 examples/s]
preprocess datasets: 100%|█████████▉| 19962/20000 [04:25<00:00, 87.11 examples/s]
preprocess datasets: 100%|█████████▉| 19975/20000 [04:25<00:00, 83.32 examples/s]
preprocess datasets: 100%|█████████▉| 19985/20000 [04:25<00:00, 86.26 examples/s]
preprocess datasets: 100%|█████████▉| 19997/20000 [04:25<00:00, 90.74 examples/s]
preprocess datasets: 100%|██████████| 20000/20000 [04:26<00:00, 74.97 examples/s]
/scratch/work/palp3/myenv/lib/python3.11/site-packages/accelerate/accelerator.py:488: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
  self.scaler = torch.cuda.amp.GradScaler(**kwargs)
max_steps is given, it will override any value given in num_train_epochs

  0%|          | 0/1000 [00:00<?, ?it/s]/scratch/work/palp3/myenv/lib/python3.11/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.
  warnings.warn(
/scratch/work/palp3/myenv/lib/python3.11/site-packages/torch/_dynamo/eval_frame.py:600: UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.4 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants.
  return fn(*args, **kwargs)
/scratch/work/palp3/myenv/lib/python3.11/site-packages/torch/utils/checkpoint.py:295: FutureWarning: `torch.cpu.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cpu', args...)` instead.
  with torch.enable_grad(), device_autocast_ctx, torch.cpu.amp.autocast(**ctx.cpu_autocast_kwargs):  # type: ignore[attr-defined]

  0%|          | 1/1000 [00:14<3:53:08, 14.00s/it]
                                                  

  0%|          | 1/1000 [00:14<3:53:08, 14.00s/it]
  0%|          | 2/1000 [00:18<2:17:45,  8.28s/it]
                                                  

  0%|          | 2/1000 [00:18<2:17:45,  8.28s/it]
  0%|          | 3/1000 [00:22<1:43:28,  6.23s/it]
                                                  

  0%|          | 3/1000 [00:22<1:43:28,  6.23s/it]
  0%|          | 4/1000 [00:25<1:24:49,  5.11s/it]
                                                  

  0%|          | 4/1000 [00:25<1:24:49,  5.11s/it]
  0%|          | 5/1000 [00:28<1:12:50,  4.39s/it]
                                                  

  0%|          | 5/1000 [00:28<1:12:50,  4.39s/it]
  1%|          | 6/1000 [00:31<1:04:28,  3.89s/it]
                                                  

  1%|          | 6/1000 [00:31<1:04:28,  3.89s/it]
  1%|          | 7/1000 [00:34<58:00,  3.51s/it]  
                                                

  1%|          | 7/1000 [00:34<58:00,  3.51s/it]
  1%|          | 8/1000 [00:36<53:42,  3.25s/it]
                                                

  1%|          | 8/1000 [00:36<53:42,  3.25s/it]
  1%|          | 9/1000 [00:39<49:51,  3.02s/it]
                                                

  1%|          | 9/1000 [00:39<49:51,  3.02s/it]
  1%|          | 10/1000 [00:41<46:21,  2.81s/it]
                                                 

  1%|          | 10/1000 [00:41<46:21,  2.81s/it]
  1%|          | 11/1000 [00:44<43:54,  2.66s/it]
                                                 

  1%|          | 11/1000 [00:44<43:54,  2.66s/it]
  1%|          | 12/1000 [00:46<42:13,  2.56s/it]
                                                 

  1%|          | 12/1000 [00:46<42:13,  2.56s/it]
  1%|▏         | 13/1000 [00:48<40:13,  2.45s/it]
                                                 

  1%|▏         | 13/1000 [00:48<40:13,  2.45s/it]
  1%|▏         | 14/1000 [00:50<38:09,  2.32s/it]
                                                 

  1%|▏         | 14/1000 [00:50<38:09,  2.32s/it]
  2%|▏         | 15/1000 [00:52<36:41,  2.24s/it]
                                                 

  2%|▏         | 15/1000 [00:52<36:41,  2.24s/it]
  2%|▏         | 16/1000 [00:54<35:46,  2.18s/it]
                                                 

  2%|▏         | 16/1000 [00:54<35:46,  2.18s/it]
  2%|▏         | 17/1000 [00:56<34:45,  2.12s/it]
                                                 

  2%|▏         | 17/1000 [00:56<34:45,  2.12s/it]
  2%|▏         | 18/1000 [00:58<32:49,  2.01s/it]
                                                 

  2%|▏         | 18/1000 [00:58<32:49,  2.01s/it]
  2%|▏         | 19/1000 [01:00<31:29,  1.93s/it]
                                                 

  2%|▏         | 19/1000 [01:00<31:29,  1.93s/it]
  2%|▏         | 20/1000 [01:01<30:45,  1.88s/it]
                                                 

  2%|▏         | 20/1000 [01:01<30:45,  1.88s/it]
  2%|▏         | 21/1000 [01:03<30:01,  1.84s/it]
                                                 

  2%|▏         | 21/1000 [01:03<30:01,  1.84s/it]
  2%|▏         | 22/1000 [01:05<29:28,  1.81s/it]
                                                 

  2%|▏         | 22/1000 [01:05<29:28,  1.81s/it]
  2%|▏         | 23/1000 [01:07<29:09,  1.79s/it]
                                                 

  2%|▏         | 23/1000 [01:07<29:09,  1.79s/it]
  2%|▏         | 24/1000 [01:08<28:21,  1.74s/it]
                                                 

  2%|▏         | 24/1000 [01:08<28:21,  1.74s/it]
  2%|▎         | 25/1000 [01:10<26:57,  1.66s/it]
                                                 

  2%|▎         | 25/1000 [01:10<26:57,  1.66s/it]
  3%|▎         | 26/1000 [01:11<25:59,  1.60s/it]
                                                 

  3%|▎         | 26/1000 [01:11<25:59,  1.60s/it]
  3%|▎         | 27/1000 [01:13<25:18,  1.56s/it]
                                                 

  3%|▎         | 27/1000 [01:13<25:18,  1.56s/it]
  3%|▎         | 28/1000 [01:14<24:48,  1.53s/it]
                                                 

  3%|▎         | 28/1000 [01:14<24:48,  1.53s/it]
  3%|▎         | 29/1000 [01:16<24:28,  1.51s/it]
                                                 

  3%|▎         | 29/1000 [01:16<24:28,  1.51s/it]
  3%|▎         | 30/1000 [01:17<24:18,  1.50s/it]
                                                 

  3%|▎         | 30/1000 [01:17<24:18,  1.50s/it]
  3%|▎         | 31/1000 [01:19<24:08,  1.49s/it]
                                                 

  3%|▎         | 31/1000 [01:19<24:08,  1.49s/it]
  3%|▎         | 32/1000 [01:20<23:32,  1.46s/it]
                                                 

  3%|▎         | 32/1000 [01:20<23:32,  1.46s/it]
  3%|▎         | 33/1000 [01:21<22:17,  1.38s/it]
                                                 

  3%|▎         | 33/1000 [01:21<22:17,  1.38s/it]
  3%|▎         | 34/1000 [01:22<21:23,  1.33s/it]
                                                 

  3%|▎         | 34/1000 [01:22<21:23,  1.33s/it]
  4%|▎         | 35/1000 [01:24<20:44,  1.29s/it]
                                                 

  4%|▎         | 35/1000 [01:24<20:44,  1.29s/it]
  4%|▎         | 36/1000 [01:25<20:16,  1.26s/it]
                                                 

  4%|▎         | 36/1000 [01:25<20:16,  1.26s/it]
  4%|▎         | 37/1000 [01:26<19:56,  1.24s/it]
                                                 

  4%|▎         | 37/1000 [01:26<19:56,  1.24s/it]
  4%|▍         | 38/1000 [01:27<19:43,  1.23s/it]
                                                 

  4%|▍         | 38/1000 [01:27<19:43,  1.23s/it]
  4%|▍         | 39/1000 [01:28<19:33,  1.22s/it]
                                                 

  4%|▍         | 39/1000 [01:28<19:33,  1.22s/it]
  4%|▍         | 40/1000 [01:30<19:08,  1.20s/it]
                                                 

  4%|▍         | 40/1000 [01:30<19:08,  1.20s/it]
  4%|▍         | 41/1000 [01:31<18:19,  1.15s/it]
                                                 

  4%|▍         | 41/1000 [01:31<18:19,  1.15s/it]
  4%|▍         | 42/1000 [01:31<17:12,  1.08s/it]
                                                 

  4%|▍         | 42/1000 [01:32<17:12,  1.08s/it]
  4%|▍         | 43/1000 [01:32<16:29,  1.03s/it]
                                                 

  4%|▍         | 43/1000 [01:32<16:29,  1.03s/it]
  4%|▍         | 44/1000 [01:33<15:54,  1.00it/s]
                                                 

  4%|▍         | 44/1000 [01:33<15:54,  1.00it/s]
  4%|▍         | 45/1000 [01:34<15:32,  1.02it/s]
                                                 

  4%|▍         | 45/1000 [01:34<15:32,  1.02it/s]
  5%|▍         | 46/1000 [01:35<14:58,  1.06it/s]
                                                 

  5%|▍         | 46/1000 [01:35<14:58,  1.06it/s]
  5%|▍         | 47/1000 [01:36<13:53,  1.14it/s]
                                                 

  5%|▍         | 47/1000 [01:36<13:53,  1.14it/s]
  5%|▍         | 48/1000 [01:37<12:54,  1.23it/s]
                                                 

  5%|▍         | 48/1000 [01:37<12:54,  1.23it/s]
  5%|▍         | 49/1000 [01:37<12:10,  1.30it/s]
                                                 

  5%|▍         | 49/1000 [01:37<12:10,  1.30it/s]
  5%|▌         | 50/1000 [01:40<20:36,  1.30s/it]
                                                 

  5%|▌         | 50/1000 [01:40<20:36,  1.30s/it]
  5%|▌         | 51/1000 [01:46<45:50,  2.90s/it]
                                                 

  5%|▌         | 51/1000 [01:46<45:50,  2.90s/it]
  5%|▌         | 52/1000 [01:50<50:59,  3.23s/it]
                                                 

  5%|▌         | 52/1000 [01:50<50:59,  3.23s/it]
  5%|▌         | 53/1000 [01:54<52:42,  3.34s/it]
                                                 

  5%|▌         | 53/1000 [01:54<52:42,  3.34s/it]
  5%|▌         | 54/1000 [01:57<52:21,  3.32s/it]
                                                 

  5%|▌         | 54/1000 [01:57<52:21,  3.32s/it]
  6%|▌         | 55/1000 [02:00<50:52,  3.23s/it]
                                                 

  6%|▌         | 55/1000 [02:00<50:52,  3.23s/it]
  6%|▌         | 56/1000 [02:03<48:59,  3.11s/it]
                                                 

  6%|▌         | 56/1000 [02:03<48:59,  3.11s/it]
  6%|▌         | 57/1000 [02:06<46:51,  2.98s/it]
                                                 

  6%|▌         | 57/1000 [02:06<46:51,  2.98s/it]
  6%|▌         | 58/1000 [02:08<44:47,  2.85s/it]
                                                 

  6%|▌         | 58/1000 [02:08<44:47,  2.85s/it]
  6%|▌         | 59/1000 [02:11<42:20,  2.70s/it]
                                                 

  6%|▌         | 59/1000 [02:11<42:20,  2.70s/it]
  6%|▌         | 60/1000 [02:13<40:37,  2.59s/it]
                                                 

  6%|▌         | 60/1000 [02:13<40:37,  2.59s/it]
  6%|▌         | 61/1000 [02:15<39:05,  2.50s/it]
                                                 

  6%|▌         | 61/1000 [02:15<39:05,  2.50s/it]
  6%|▌         | 62/1000 [02:17<37:14,  2.38s/it]
                                                 

  6%|▌         | 62/1000 [02:17<37:14,  2.38s/it]
  6%|▋         | 63/1000 [02:19<35:34,  2.28s/it]
                                                 

  6%|▋         | 63/1000 [02:19<35:34,  2.28s/it]
  6%|▋         | 64/1000 [02:21<34:29,  2.21s/it]
                                                 

  6%|▋         | 64/1000 [02:21<34:29,  2.21s/it]
  6%|▋         | 65/1000 [02:24<33:42,  2.16s/it]
                                                 

  6%|▋         | 65/1000 [02:24<33:42,  2.16s/it]
  7%|▋         | 66/1000 [02:26<33:11,  2.13s/it]
                                                 

  7%|▋         | 66/1000 [02:26<33:11,  2.13s/it]
  7%|▋         | 67/1000 [02:27<31:36,  2.03s/it]
                                                 

  7%|▋         | 67/1000 [02:27<31:36,  2.03s/it]
  7%|▋         | 68/1000 [02:29<30:12,  1.94s/it]
                                                 

  7%|▋         | 68/1000 [02:29<30:12,  1.94s/it]
  7%|▋         | 69/1000 [02:31<29:27,  1.90s/it]
                                                 

  7%|▋         | 69/1000 [02:31<29:27,  1.90s/it]
  7%|▋         | 70/1000 [02:33<28:38,  1.85s/it]
                                                 

  7%|▋         | 70/1000 [02:33<28:38,  1.85s/it]
  7%|▋         | 71/1000 [02:34<28:05,  1.81s/it]
                                                 

  7%|▋         | 71/1000 [02:34<28:05,  1.81s/it]
  7%|▋         | 72/1000 [02:36<27:45,  1.79s/it]
                                                 

  7%|▋         | 72/1000 [02:36<27:45,  1.79s/it]
  7%|▋         | 73/1000 [02:38<27:30,  1.78s/it]
                                                 

  7%|▋         | 73/1000 [02:38<27:30,  1.78s/it]
  7%|▋         | 74/1000 [02:39<26:31,  1.72s/it]
                                                 

  7%|▋         | 74/1000 [02:39<26:31,  1.72s/it]
  8%|▊         | 75/1000 [02:41<25:19,  1.64s/it]
                                                 

  8%|▊         | 75/1000 [02:41<25:19,  1.64s/it]
  8%|▊         | 76/1000 [02:42<24:31,  1.59s/it]
                                                 

  8%|▊         | 76/1000 [02:42<24:31,  1.59s/it]
  8%|▊         | 77/1000 [02:44<23:57,  1.56s/it]
                                                 

  8%|▊         | 77/1000 [02:44<23:57,  1.56s/it]
  8%|▊         | 78/1000 [02:45<23:29,  1.53s/it]
                                                 

  8%|▊         | 78/1000 [02:45<23:29,  1.53s/it]
  8%|▊         | 79/1000 [02:47<23:10,  1.51s/it]
                                                 

  8%|▊         | 79/1000 [02:47<23:10,  1.51s/it]
  8%|▊         | 80/1000 [02:48<22:56,  1.50s/it]
                                                 

  8%|▊         | 80/1000 [02:48<22:56,  1.50s/it]
  8%|▊         | 81/1000 [02:50<22:47,  1.49s/it]
                                                 

  8%|▊         | 81/1000 [02:50<22:47,  1.49s/it]
  8%|▊         | 82/1000 [02:51<22:01,  1.44s/it]
                                                 

  8%|▊         | 82/1000 [02:51<22:01,  1.44s/it]
  8%|▊         | 83/1000 [02:52<20:53,  1.37s/it]
                                                 

  8%|▊         | 83/1000 [02:52<20:53,  1.37s/it]
  8%|▊         | 84/1000 [02:53<20:07,  1.32s/it]
                                                 

  8%|▊         | 84/1000 [02:53<20:07,  1.32s/it]
  8%|▊         | 85/1000 [02:55<19:35,  1.28s/it]
                                                 

  8%|▊         | 85/1000 [02:55<19:35,  1.28s/it]
  9%|▊         | 86/1000 [02:56<19:10,  1.26s/it]
                                                 

  9%|▊         | 86/1000 [02:56<19:10,  1.26s/it]
  9%|▊         | 87/1000 [02:57<18:53,  1.24s/it]
                                                 

  9%|▊         | 87/1000 [02:57<18:53,  1.24s/it]
  9%|▉         | 88/1000 [02:58<18:41,  1.23s/it]
                                                 

  9%|▉         | 88/1000 [02:58<18:41,  1.23s/it]
  9%|▉         | 89/1000 [02:59<18:31,  1.22s/it]
                                                 

  9%|▉         | 89/1000 [02:59<18:31,  1.22s/it]
  9%|▉         | 90/1000 [03:00<17:23,  1.15s/it]
                                                 

  9%|▉         | 90/1000 [03:00<17:23,  1.15s/it]
  9%|▉         | 91/1000 [03:01<16:34,  1.09s/it]
                                                 

  9%|▉         | 91/1000 [03:01<16:34,  1.09s/it]
  9%|▉         | 92/1000 [03:02<15:44,  1.04s/it]
                                                 

  9%|▉         | 92/1000 [03:02<15:44,  1.04s/it]
  9%|▉         | 93/1000 [03:03<15:09,  1.00s/it]
                                                 

  9%|▉         | 93/1000 [03:03<15:09,  1.00s/it]
  9%|▉         | 94/1000 [03:04<14:47,  1.02it/s]
                                                 

  9%|▉         | 94/1000 [03:04<14:47,  1.02it/s]
 10%|▉         | 95/1000 [03:05<14:32,  1.04it/s]
                                                 

 10%|▉         | 95/1000 [03:05<14:32,  1.04it/s]
 10%|▉         | 96/1000 [03:06<14:09,  1.06it/s]
                                                 

 10%|▉         | 96/1000 [03:06<14:09,  1.06it/s]
 10%|▉         | 97/1000 [03:07<13:08,  1.15it/s]
                                                 

 10%|▉         | 97/1000 [03:07<13:08,  1.15it/s]
 10%|▉         | 98/1000 [03:07<12:13,  1.23it/s]
                                                 

 10%|▉         | 98/1000 [03:07<12:13,  1.23it/s]
 10%|▉         | 99/1000 [03:08<11:33,  1.30it/s]
                                                 

 10%|▉         | 99/1000 [03:08<11:33,  1.30it/s]
 10%|█         | 100/1000 [03:10<18:58,  1.27s/it]
                                                  

 10%|█         | 100/1000 [03:10<18:58,  1.27s/it]
 10%|█         | 101/1000 [03:17<42:00,  2.80s/it]
                                                  

 10%|█         | 101/1000 [03:17<42:00,  2.80s/it]
 10%|█         | 102/1000 [03:21<47:22,  3.17s/it]
                                                  

 10%|█         | 102/1000 [03:21<47:22,  3.17s/it]
 10%|█         | 103/1000 [03:24<48:57,  3.28s/it]
                                                  

 10%|█         | 103/1000 [03:24<48:57,  3.28s/it]
 10%|█         | 104/1000 [03:28<48:25,  3.24s/it]
                                                  

 10%|█         | 104/1000 [03:28<48:25,  3.24s/it]
 10%|█         | 105/1000 [03:30<46:45,  3.13s/it]
                                                  

 10%|█         | 105/1000 [03:30<46:45,  3.13s/it]
 11%|█         | 106/1000 [03:33<45:01,  3.02s/it]
                                                  

 11%|█         | 106/1000 [03:33<45:01,  3.02s/it]
 11%|█         | 107/1000 [03:36<43:02,  2.89s/it]
                                                  

 11%|█         | 107/1000 [03:36<43:02,  2.89s/it]
 11%|█         | 108/1000 [03:38<40:49,  2.75s/it]
                                                  

 11%|█         | 108/1000 [03:38<40:49,  2.75s/it]
 11%|█         | 109/1000 [03:41<38:55,  2.62s/it]
                                                  

 11%|█         | 109/1000 [03:41<38:55,  2.62s/it]
 11%|█         | 110/1000 [03:43<37:39,  2.54s/it]
                                                  

 11%|█         | 110/1000 [03:43<37:39,  2.54s/it]
 11%|█         | 111/1000 [03:45<36:29,  2.46s/it]
                                                  

 11%|█         | 111/1000 [03:45<36:29,  2.46s/it]
 11%|█         | 112/1000 [03:47<34:53,  2.36s/it]
                                                  

 11%|█         | 112/1000 [03:47<34:53,  2.36s/it]
 11%|█▏        | 113/1000 [03:49<33:34,  2.27s/it]
                                                  

 11%|█▏        | 113/1000 [03:49<33:34,  2.27s/it]
 11%|█▏        | 114/1000 [03:51<32:36,  2.21s/it]
                                                  

 11%|█▏        | 114/1000 [03:51<32:36,  2.21s/it]
 12%|█▏        | 115/1000 [03:53<31:49,  2.16s/it]
                                                  

 12%|█▏        | 115/1000 [03:53<31:49,  2.16s/it]
 12%|█▏        | 116/1000 [03:55<31:17,  2.12s/it]
                                                  

 12%|█▏        | 116/1000 [03:55<31:17,  2.12s/it]
 12%|█▏        | 117/1000 [03:57<30:04,  2.04s/it]
                                                  

 12%|█▏        | 117/1000 [03:57<30:04,  2.04s/it]
 12%|█▏        | 118/1000 [03:59<28:40,  1.95s/it]
                                                  

 12%|█▏        | 118/1000 [03:59<28:40,  1.95s/it]
 12%|█▏        | 119/1000 [04:01<27:41,  1.89s/it]
                                                  

 12%|█▏        | 119/1000 [04:01<27:41,  1.89s/it]
 12%|█▏        | 120/1000 [04:03<27:13,  1.86s/it]
                                                  

 12%|█▏        | 120/1000 [04:03<27:13,  1.86s/it]
 12%|█▏        | 121/1000 [04:04<26:42,  1.82s/it]
                                                  

 12%|█▏        | 121/1000 [04:04<26:42,  1.82s/it]
 12%|█▏        | 122/1000 [04:06<26:17,  1.80s/it]
                                                  

 12%|█▏        | 122/1000 [04:06<26:17,  1.80s/it]
 12%|█▏        | 123/1000 [04:08<25:58,  1.78s/it]
                                                  

 12%|█▏        | 123/1000 [04:08<25:58,  1.78s/it]
 12%|█▏        | 124/1000 [04:09<25:20,  1.74s/it]
                                                  

 12%|█▏        | 124/1000 [04:09<25:20,  1.74s/it]
 12%|█▎        | 125/1000 [04:11<24:11,  1.66s/it]
                                                  

 12%|█▎        | 125/1000 [04:11<24:11,  1.66s/it]
 13%|█▎        | 126/1000 [04:12<23:24,  1.61s/it]
                                                  

 13%|█▎        | 126/1000 [04:12<23:24,  1.61s/it]
 13%|█▎        | 127/1000 [04:14<22:46,  1.57s/it]
                                                  

 13%|█▎        | 127/1000 [04:14<22:46,  1.57s/it]
 13%|█▎        | 128/1000 [04:15<22:23,  1.54s/it]
                                                  

 13%|█▎        | 128/1000 [04:15<22:23,  1.54s/it]
 13%|█▎        | 129/1000 [04:17<22:11,  1.53s/it]
                                                  

 13%|█▎        | 129/1000 [04:17<22:11,  1.53s/it]
 13%|█▎        | 130/1000 [04:18<21:55,  1.51s/it]
                                                  

 13%|█▎        | 130/1000 [04:18<21:55,  1.51s/it]
 13%|█▎        | 131/1000 [04:20<21:43,  1.50s/it]
                                                  

 13%|█▎        | 131/1000 [04:20<21:43,  1.50s/it]
 13%|█▎        | 132/1000 [04:21<21:33,  1.49s/it]
                                                  

 13%|█▎        | 132/1000 [04:21<21:33,  1.49s/it]
 13%|█▎        | 133/1000 [04:23<20:55,  1.45s/it]
                                                  

 13%|█▎        | 133/1000 [04:23<20:55,  1.45s/it]
 13%|█▎        | 134/1000 [04:24<19:51,  1.38s/it]
                                                  

 13%|█▎        | 134/1000 [04:24<19:51,  1.38s/it]
 14%|█▎        | 135/1000 [04:25<19:04,  1.32s/it]
                                                  

 14%|█▎        | 135/1000 [04:25<19:04,  1.32s/it]
 14%|█▎        | 136/1000 [04:26<18:32,  1.29s/it]
                                                  

 14%|█▎        | 136/1000 [04:26<18:32,  1.29s/it]
 14%|█▎        | 137/1000 [04:27<18:09,  1.26s/it]
                                                  

 14%|█▎        | 137/1000 [04:27<18:09,  1.26s/it]
 14%|█▍        | 138/1000 [04:29<17:54,  1.25s/it]
                                                  

 14%|█▍        | 138/1000 [04:29<17:54,  1.25s/it]
 14%|█▍        | 139/1000 [04:30<17:45,  1.24s/it]
                                                  

 14%|█▍        | 139/1000 [04:30<17:45,  1.24s/it]
 14%|█▍        | 140/1000 [04:31<17:38,  1.23s/it]
                                                  

 14%|█▍        | 140/1000 [04:31<17:38,  1.23s/it]
 14%|█▍        | 141/1000 [04:32<17:04,  1.19s/it]
                                                  

 14%|█▍        | 141/1000 [04:32<17:04,  1.19s/it]
 14%|█▍        | 142/1000 [04:33<15:54,  1.11s/it]
                                                  

 14%|█▍        | 142/1000 [04:33<15:54,  1.11s/it]
 14%|█▍        | 143/1000 [04:34<15:05,  1.06s/it]
                                                  

 14%|█▍        | 143/1000 [04:34<15:05,  1.06s/it]
 14%|█▍        | 144/1000 [04:35<14:29,  1.02s/it]
                                                  

 14%|█▍        | 144/1000 [04:35<14:29,  1.02s/it]
 14%|█▍        | 145/1000 [04:36<14:04,  1.01it/s]
                                                  

 14%|█▍        | 145/1000 [04:36<14:04,  1.01it/s]
 15%|█▍        | 146/1000 [04:37<13:47,  1.03it/s]
                                                  

 15%|█▍        | 146/1000 [04:37<13:47,  1.03it/s]
 15%|█▍        | 147/1000 [04:38<12:58,  1.10it/s]
                                                  

 15%|█▍        | 147/1000 [04:38<12:58,  1.10it/s]
 15%|█▍        | 148/1000 [04:38<11:54,  1.19it/s]
                                                  

 15%|█▍        | 148/1000 [04:38<11:54,  1.19it/s]
 15%|█▍        | 149/1000 [04:39<11:10,  1.27it/s]
                                                  

 15%|█▍        | 149/1000 [04:39<11:10,  1.27it/s]
 15%|█▌        | 150/1000 [04:41<18:23,  1.30s/it]
                                                  

 15%|█▌        | 150/1000 [04:41<18:23,  1.30s/it]
 15%|█▌        | 151/1000 [04:48<41:28,  2.93s/it]
                                                  

 15%|█▌        | 151/1000 [04:48<41:28,  2.93s/it]
 15%|█▌        | 152/1000 [04:52<46:39,  3.30s/it]
                                                  

 15%|█▌        | 152/1000 [04:52<46:39,  3.30s/it]
 15%|█▌        | 153/1000 [04:56<47:58,  3.40s/it]
                                                  

 15%|█▌        | 153/1000 [04:56<47:58,  3.40s/it]
 15%|█▌        | 154/1000 [04:59<47:42,  3.38s/it]
                                                  

 15%|█▌        | 154/1000 [04:59<47:42,  3.38s/it]
 16%|█▌        | 155/1000 [05:02<46:17,  3.29s/it]
                                                  

 16%|█▌        | 155/1000 [05:02<46:17,  3.29s/it]
 16%|█▌        | 156/1000 [05:05<44:33,  3.17s/it]
                                                  

 16%|█▌        | 156/1000 [05:05<44:33,  3.17s/it]
 16%|█▌        | 157/1000 [05:08<42:31,  3.03s/it]
                                                  

 16%|█▌        | 157/1000 [05:08<42:31,  3.03s/it]
 16%|█▌        | 158/1000 [05:10<40:33,  2.89s/it]
                                                  

 16%|█▌        | 158/1000 [05:11<40:33,  2.89s/it]
 16%|█▌        | 159/1000 [05:13<38:14,  2.73s/it]
                                                  

 16%|█▌        | 159/1000 [05:13<38:14,  2.73s/it]
 16%|█▌        | 160/1000 [05:15<36:40,  2.62s/it]
                                                  

 16%|█▌        | 160/1000 [05:15<36:40,  2.62s/it]
 16%|█▌        | 161/1000 [05:18<35:38,  2.55s/it]
                                                  

 16%|█▌        | 161/1000 [05:18<35:38,  2.55s/it]
 16%|█▌        | 162/1000 [05:20<33:42,  2.41s/it]
                                                  

 16%|█▌        | 162/1000 [05:20<33:42,  2.41s/it]
 16%|█▋        | 163/1000 [05:22<32:09,  2.31s/it]
                                                  

 16%|█▋        | 163/1000 [05:22<32:09,  2.31s/it]
 16%|█▋        | 164/1000 [05:24<31:03,  2.23s/it]
                                                  

 16%|█▋        | 164/1000 [05:24<31:03,  2.23s/it]
 16%|█▋        | 165/1000 [05:26<30:16,  2.18s/it]
                                                  

 16%|█▋        | 165/1000 [05:26<30:16,  2.18s/it]
 17%|█▋        | 166/1000 [05:28<29:44,  2.14s/it]
                                                  

 17%|█▋        | 166/1000 [05:28<29:44,  2.14s/it]
 17%|█▋        | 167/1000 [05:30<28:45,  2.07s/it]
                                                  

 17%|█▋        | 167/1000 [05:30<28:45,  2.07s/it]
 17%|█▋        | 168/1000 [05:32<27:22,  1.97s/it]
                                                  

 17%|█▋        | 168/1000 [05:32<27:22,  1.97s/it]
 17%|█▋        | 169/1000 [05:34<27:13,  1.97s/it]
                                                  

 17%|█▋        | 169/1000 [05:34<27:13,  1.97s/it]
 17%|█▋        | 170/1000 [05:37<33:36,  2.43s/it]
                                                  

 17%|█▋        | 170/1000 [05:37<33:36,  2.43s/it]
 17%|█▋        | 171/1000 [05:39<30:56,  2.24s/it]
                                                  

 17%|█▋        | 171/1000 [05:39<30:56,  2.24s/it]
 17%|█▋        | 172/1000 [05:41<29:53,  2.17s/it]
                                                  

 17%|█▋        | 172/1000 [05:41<29:53,  2.17s/it]
 17%|█▋        | 173/1000 [05:43<28:40,  2.08s/it]
                                                  

 17%|█▋        | 173/1000 [05:43<28:40,  2.08s/it]
 17%|█▋        | 174/1000 [05:44<26:43,  1.94s/it]
                                                  

 17%|█▋        | 174/1000 [05:44<26:43,  1.94s/it]
 18%|█▊        | 175/1000 [05:46<25:27,  1.85s/it]
                                                  

 18%|█▊        | 175/1000 [05:46<25:27,  1.85s/it]
 18%|█▊        | 176/1000 [05:47<24:03,  1.75s/it]
                                                  

 18%|█▊        | 176/1000 [05:48<24:03,  1.75s/it]
 18%|█▊        | 177/1000 [05:49<23:05,  1.68s/it]
                                                  

 18%|█▊        | 177/1000 [05:49<23:05,  1.68s/it]
 18%|█▊        | 178/1000 [05:50<22:13,  1.62s/it]
                                                  

 18%|█▊        | 178/1000 [05:51<22:13,  1.62s/it]
 18%|█▊        | 179/1000 [05:52<21:48,  1.59s/it]
                                                  

 18%|█▊        | 179/1000 [05:52<21:48,  1.59s/it]
 18%|█▊        | 180/1000 [05:54<21:36,  1.58s/it]
                                                  

 18%|█▊        | 180/1000 [05:54<21:36,  1.58s/it]
 18%|█▊        | 181/1000 [05:55<21:41,  1.59s/it]
                                                  

 18%|█▊        | 181/1000 [05:55<21:41,  1.59s/it]
 18%|█▊        | 182/1000 [05:57<20:41,  1.52s/it]
                                                  

 18%|█▊        | 182/1000 [05:57<20:41,  1.52s/it]
 18%|█▊        | 183/1000 [05:58<19:33,  1.44s/it]
                                                  

 18%|█▊        | 183/1000 [05:58<19:33,  1.44s/it]
 18%|█▊        | 184/1000 [05:59<18:48,  1.38s/it]
                                                  

 18%|█▊        | 184/1000 [05:59<18:48,  1.38s/it]
 18%|█▊        | 185/1000 [06:00<18:06,  1.33s/it]
                                                  

 18%|█▊        | 185/1000 [06:00<18:06,  1.33s/it]
 19%|█▊        | 186/1000 [06:01<17:38,  1.30s/it]
                                                  

 19%|█▊        | 186/1000 [06:01<17:38,  1.30s/it]
 19%|█▊        | 187/1000 [06:03<17:22,  1.28s/it]
                                                  

 19%|█▊        | 187/1000 [06:03<17:22,  1.28s/it]
 19%|█▉        | 188/1000 [06:04<17:27,  1.29s/it]
                                                  

 19%|█▉        | 188/1000 [06:04<17:27,  1.29s/it]
 19%|█▉        | 189/1000 [06:05<17:07,  1.27s/it]
                                                  

 19%|█▉        | 189/1000 [06:05<17:07,  1.27s/it]
 19%|█▉        | 190/1000 [06:06<16:40,  1.24s/it]
                                                  

 19%|█▉        | 190/1000 [06:06<16:40,  1.24s/it]
 19%|█▉        | 191/1000 [06:07<15:47,  1.17s/it]
                                                  

 19%|█▉        | 191/1000 [06:07<15:47,  1.17s/it]
 19%|█▉        | 192/1000 [06:08<15:25,  1.14s/it]
                                                  

 19%|█▉        | 192/1000 [06:09<15:25,  1.14s/it]
 19%|█▉        | 193/1000 [06:09<14:30,  1.08s/it]
                                                  

 19%|█▉        | 193/1000 [06:09<14:30,  1.08s/it]
 19%|█▉        | 194/1000 [06:10<14:12,  1.06s/it]
                                                  

 19%|█▉        | 194/1000 [06:10<14:12,  1.06s/it]
 20%|█▉        | 195/1000 [06:11<13:38,  1.02s/it]
                                                  

 20%|█▉        | 195/1000 [06:11<13:38,  1.02s/it]
 20%|█▉        | 196/1000 [06:12<12:50,  1.04it/s]
                                                  

 20%|█▉        | 196/1000 [06:12<12:50,  1.04it/s]
 20%|█▉        | 197/1000 [06:13<11:38,  1.15it/s]
                                                  

 20%|█▉        | 197/1000 [06:13<11:38,  1.15it/s]
 20%|█▉        | 198/1000 [06:13<10:47,  1.24it/s]
                                                  

 20%|█▉        | 198/1000 [06:14<10:47,  1.24it/s]
 20%|█▉        | 199/1000 [06:14<10:15,  1.30it/s]
                                                  

 20%|█▉        | 199/1000 [06:14<10:15,  1.30it/s]
 20%|██        | 200/1000 [06:17<17:18,  1.30s/it]
                                                  

 20%|██        | 200/1000 [06:17<17:18,  1.30s/it]
 20%|██        | 201/1000 [06:23<38:40,  2.90s/it]
                                                  

 20%|██        | 201/1000 [06:23<38:40,  2.90s/it]
 20%|██        | 202/1000 [06:28<45:00,  3.38s/it]
                                                  

 20%|██        | 202/1000 [06:28<45:00,  3.38s/it]
 20%|██        | 203/1000 [06:32<46:38,  3.51s/it]
                                                  

 20%|██        | 203/1000 [06:32<46:38,  3.51s/it]
 20%|██        | 204/1000 [06:35<45:54,  3.46s/it]
                                                  

 20%|██        | 204/1000 [06:35<45:54,  3.46s/it]
 20%|██        | 205/1000 [06:38<44:36,  3.37s/it]
                                                  

 20%|██        | 205/1000 [06:38<44:36,  3.37s/it]
 21%|██        | 206/1000 [06:41<42:56,  3.25s/it]
                                                  

 21%|██        | 206/1000 [06:41<42:56,  3.25s/it]
 21%|██        | 207/1000 [06:44<41:04,  3.11s/it]
                                                  

 21%|██        | 207/1000 [06:44<41:04,  3.11s/it]
 21%|██        | 208/1000 [06:47<39:19,  2.98s/it]
                                                  

 21%|██        | 208/1000 [06:47<39:19,  2.98s/it]
 21%|██        | 209/1000 [06:49<37:40,  2.86s/it]
                                                  

 21%|██        | 209/1000 [06:49<37:40,  2.86s/it]
 21%|██        | 210/1000 [06:52<35:54,  2.73s/it]
                                                  

 21%|██        | 210/1000 [06:52<35:54,  2.73s/it]
 21%|██        | 211/1000 [06:54<35:09,  2.67s/it]
                                                  

 21%|██        | 211/1000 [06:54<35:09,  2.67s/it]
 21%|██        | 212/1000 [06:57<34:17,  2.61s/it]
                                                  

 21%|██        | 212/1000 [06:57<34:17,  2.61s/it]
 21%|██▏       | 213/1000 [06:59<32:36,  2.49s/it]
                                                  

 21%|██▏       | 213/1000 [06:59<32:36,  2.49s/it]
 21%|██▏       | 214/1000 [07:01<31:06,  2.37s/it]
                                                  

 21%|██▏       | 214/1000 [07:01<31:06,  2.37s/it]
 22%|██▏       | 215/1000 [07:03<30:14,  2.31s/it]
                                                  

 22%|██▏       | 215/1000 [07:03<30:14,  2.31s/it]
 22%|██▏       | 216/1000 [07:05<29:15,  2.24s/it]
                                                  

 22%|██▏       | 216/1000 [07:05<29:15,  2.24s/it]
 22%|██▏       | 217/1000 [07:07<28:21,  2.17s/it]
                                                  

 22%|██▏       | 217/1000 [07:07<28:21,  2.17s/it]
 22%|██▏       | 218/1000 [07:09<26:38,  2.04s/it]
                                                  

 22%|██▏       | 218/1000 [07:09<26:38,  2.04s/it]
 22%|██▏       | 219/1000 [07:11<25:37,  1.97s/it]
                                                  

 22%|██▏       | 219/1000 [07:11<25:37,  1.97s/it]
 22%|██▏       | 220/1000 [07:13<25:04,  1.93s/it]
                                                  

 22%|██▏       | 220/1000 [07:13<25:04,  1.93s/it]
 22%|██▏       | 221/1000 [07:14<24:18,  1.87s/it]
                                                  

 22%|██▏       | 221/1000 [07:14<24:18,  1.87s/it]
 22%|██▏       | 222/1000 [07:16<23:45,  1.83s/it]
                                                  

 22%|██▏       | 222/1000 [07:16<23:45,  1.83s/it]
 22%|██▏       | 223/1000 [07:18<23:27,  1.81s/it]
                                                  

 22%|██▏       | 223/1000 [07:18<23:27,  1.81s/it]
 22%|██▏       | 224/1000 [07:20<23:09,  1.79s/it]
                                                  

 22%|██▏       | 224/1000 [07:20<23:09,  1.79s/it]
 22%|██▎       | 225/1000 [07:21<22:07,  1.71s/it]
                                                  

 22%|██▎       | 225/1000 [07:21<22:07,  1.71s/it]
 23%|██▎       | 226/1000 [07:23<21:15,  1.65s/it]
                                                  

 23%|██▎       | 226/1000 [07:23<21:15,  1.65s/it]
 23%|██▎       | 227/1000 [07:24<20:34,  1.60s/it]
                                                  

 23%|██▎       | 227/1000 [07:24<20:34,  1.60s/it]
 23%|██▎       | 228/1000 [07:27<24:17,  1.89s/it]
                                                  

 23%|██▎       | 228/1000 [07:27<24:17,  1.89s/it]
 23%|██▎       | 229/1000 [07:28<22:53,  1.78s/it]
                                                  

 23%|██▎       | 229/1000 [07:28<22:53,  1.78s/it]
 23%|██▎       | 230/1000 [07:30<21:50,  1.70s/it]
                                                  

 23%|██▎       | 230/1000 [07:30<21:50,  1.70s/it]
 23%|██▎       | 231/1000 [07:31<21:05,  1.65s/it]
                                                  

 23%|██▎       | 231/1000 [07:31<21:05,  1.65s/it]
 23%|██▎       | 232/1000 [07:33<20:13,  1.58s/it]
                                                  

 23%|██▎       | 232/1000 [07:33<20:13,  1.58s/it]
 23%|██▎       | 233/1000 [07:34<18:49,  1.47s/it]
                                                  

 23%|██▎       | 233/1000 [07:34<18:49,  1.47s/it]
 23%|██▎       | 234/1000 [07:35<18:04,  1.42s/it]
                                                  

 23%|██▎       | 234/1000 [07:35<18:04,  1.42s/it]
 24%|██▎       | 235/1000 [07:36<17:34,  1.38s/it]
                                                  

 24%|██▎       | 235/1000 [07:36<17:34,  1.38s/it]
 24%|██▎       | 236/1000 [07:38<17:07,  1.35s/it]
                                                  

 24%|██▎       | 236/1000 [07:38<17:07,  1.35s/it]
 24%|██▎       | 237/1000 [07:39<18:54,  1.49s/it]
                                                  

 24%|██▎       | 237/1000 [07:39<18:54,  1.49s/it]
 24%|██▍       | 238/1000 [07:41<17:53,  1.41s/it]
                                                  

 24%|██▍       | 238/1000 [07:41<17:53,  1.41s/it]
 24%|██▍       | 239/1000 [07:42<17:12,  1.36s/it]
                                                  

 24%|██▍       | 239/1000 [07:42<17:12,  1.36s/it]
 24%|██▍       | 240/1000 [07:43<16:42,  1.32s/it]
                                                  

 24%|██▍       | 240/1000 [07:43<16:42,  1.32s/it]
 24%|██▍       | 241/1000 [07:44<16:05,  1.27s/it]
                                                  

 24%|██▍       | 241/1000 [07:44<16:05,  1.27s/it]
 24%|██▍       | 242/1000 [07:45<14:49,  1.17s/it]
                                                  

 24%|██▍       | 242/1000 [07:45<14:49,  1.17s/it]
 24%|██▍       | 243/1000 [07:46<13:51,  1.10s/it]
                                                  

 24%|██▍       | 243/1000 [07:46<13:51,  1.10s/it]
 24%|██▍       | 244/1000 [07:47<13:10,  1.05s/it]
                                                  

 24%|██▍       | 244/1000 [07:47<13:10,  1.05s/it]
 24%|██▍       | 245/1000 [07:48<12:46,  1.02s/it]
                                                  

 24%|██▍       | 245/1000 [07:48<12:46,  1.02s/it]
 25%|██▍       | 246/1000 [07:49<12:17,  1.02it/s]
                                                  

 25%|██▍       | 246/1000 [07:49<12:17,  1.02it/s]
 25%|██▍       | 247/1000 [07:50<11:30,  1.09it/s]
                                                  

 25%|██▍       | 247/1000 [07:50<11:30,  1.09it/s]
 25%|██▍       | 248/1000 [07:50<10:32,  1.19it/s]
                                                  

 25%|██▍       | 248/1000 [07:50<10:32,  1.19it/s]
 25%|██▍       | 249/1000 [07:51<09:52,  1.27it/s]
                                                  

 25%|██▍       | 249/1000 [07:51<09:52,  1.27it/s]
 25%|██▌       | 250/1000 [07:54<16:26,  1.31s/it]
                                                  

 25%|██▌       | 250/1000 [07:54<16:26,  1.31s/it]
 25%|██▌       | 251/1000 [08:00<37:03,  2.97s/it]
                                                  

 25%|██▌       | 251/1000 [08:00<37:03,  2.97s/it]
 25%|██▌       | 252/1000 [08:05<42:15,  3.39s/it]
                                                  

 25%|██▌       | 252/1000 [08:05<42:15,  3.39s/it]
 25%|██▌       | 253/1000 [08:09<43:26,  3.49s/it]
                                                  

 25%|██▌       | 253/1000 [08:09<43:26,  3.49s/it]
 25%|██▌       | 254/1000 [08:12<42:51,  3.45s/it]
                                                  

 25%|██▌       | 254/1000 [08:12<42:51,  3.45s/it]
 26%|██▌       | 255/1000 [08:15<41:51,  3.37s/it]
                                                  

 26%|██▌       | 255/1000 [08:15<41:51,  3.37s/it]
 26%|██▌       | 256/1000 [08:18<40:04,  3.23s/it]
                                                  

 26%|██▌       | 256/1000 [08:18<40:04,  3.23s/it]
 26%|██▌       | 257/1000 [08:21<38:23,  3.10s/it]
                                                  

 26%|██▌       | 257/1000 [08:21<38:23,  3.10s/it]
 26%|██▌       | 258/1000 [08:23<36:56,  2.99s/it]
                                                  

 26%|██▌       | 258/1000 [08:23<36:56,  2.99s/it]
 26%|██▌       | 259/1000 [08:26<35:27,  2.87s/it]
                                                  

 26%|██▌       | 259/1000 [08:26<35:27,  2.87s/it]
 26%|██▌       | 260/1000 [08:28<33:27,  2.71s/it]
                                                  

 26%|██▌       | 260/1000 [08:28<33:27,  2.71s/it]
 26%|██▌       | 261/1000 [08:31<32:27,  2.64s/it]
                                                  

 26%|██▌       | 261/1000 [08:31<32:27,  2.64s/it]
 26%|██▌       | 262/1000 [08:33<31:44,  2.58s/it]
                                                  

 26%|██▌       | 262/1000 [08:33<31:44,  2.58s/it]
 26%|██▋       | 263/1000 [08:36<30:14,  2.46s/it]
                                                  

 26%|██▋       | 263/1000 [08:36<30:14,  2.46s/it]
 26%|██▋       | 264/1000 [08:38<28:39,  2.34s/it]
                                                  

 26%|██▋       | 264/1000 [08:38<28:39,  2.34s/it]
 26%|██▋       | 265/1000 [08:40<27:35,  2.25s/it]
                                                  

 26%|██▋       | 265/1000 [08:40<27:35,  2.25s/it]
 27%|██▋       | 266/1000 [08:42<27:14,  2.23s/it]
                                                  

 27%|██▋       | 266/1000 [08:42<27:14,  2.23s/it]
 27%|██▋       | 267/1000 [08:44<26:38,  2.18s/it]
                                                  

 27%|██▋       | 267/1000 [08:44<26:38,  2.18s/it]
 27%|██▋       | 268/1000 [08:46<25:28,  2.09s/it]
                                                  

 27%|██▋       | 268/1000 [08:46<25:28,  2.09s/it]
 27%|██▋       | 269/1000 [08:48<24:28,  2.01s/it]
                                                  

 27%|██▋       | 269/1000 [08:48<24:28,  2.01s/it]
 27%|██▋       | 270/1000 [08:49<23:47,  1.96s/it]
                                                  

 27%|██▋       | 270/1000 [08:49<23:47,  1.96s/it]
 27%|██▋       | 271/1000 [08:51<23:14,  1.91s/it]
                                                  

 27%|██▋       | 271/1000 [08:51<23:14,  1.91s/it]
 27%|██▋       | 272/1000 [08:53<22:43,  1.87s/it]
                                                  

 27%|██▋       | 272/1000 [08:53<22:43,  1.87s/it]
 27%|██▋       | 273/1000 [08:55<22:24,  1.85s/it]
                                                  

 27%|██▋       | 273/1000 [08:55<22:24,  1.85s/it]
 27%|██▋       | 274/1000 [08:57<22:18,  1.84s/it]
                                                  

 27%|██▋       | 274/1000 [08:57<22:18,  1.84s/it]
 28%|██▊       | 275/1000 [08:58<21:16,  1.76s/it]
                                                  

 28%|██▊       | 275/1000 [08:58<21:16,  1.76s/it]
 28%|██▊       | 276/1000 [09:00<20:14,  1.68s/it]
                                                  

 28%|██▊       | 276/1000 [09:00<20:14,  1.68s/it]
 28%|██▊       | 277/1000 [09:01<19:32,  1.62s/it]
                                                  

 28%|██▊       | 277/1000 [09:01<19:32,  1.62s/it]
 28%|██▊       | 278/1000 [09:03<19:14,  1.60s/it]
                                                  

 28%|██▊       | 278/1000 [09:03<19:14,  1.60s/it]
 28%|██▊       | 279/1000 [09:04<18:47,  1.56s/it]
                                                  

 28%|██▊       | 279/1000 [09:04<18:47,  1.56s/it]
 28%|██▊       | 280/1000 [09:06<18:29,  1.54s/it]
                                                  

 28%|██▊       | 280/1000 [09:06<18:29,  1.54s/it]
 28%|██▊       | 281/1000 [09:07<18:16,  1.52s/it]
                                                  

 28%|██▊       | 281/1000 [09:07<18:16,  1.52s/it]
 28%|██▊       | 282/1000 [09:09<17:57,  1.50s/it]
                                                  

 28%|██▊       | 282/1000 [09:09<17:57,  1.50s/it]
 28%|██▊       | 283/1000 [09:10<17:09,  1.44s/it]
                                                  

 28%|██▊       | 283/1000 [09:10<17:09,  1.44s/it]
 28%|██▊       | 284/1000 [09:11<16:45,  1.40s/it]
                                                  

 28%|██▊       | 284/1000 [09:11<16:45,  1.40s/it]
 28%|██▊       | 285/1000 [09:12<16:10,  1.36s/it]
                                                  

 28%|██▊       | 285/1000 [09:12<16:10,  1.36s/it]
 29%|██▊       | 286/1000 [09:14<15:41,  1.32s/it]
                                                  

 29%|██▊       | 286/1000 [09:14<15:41,  1.32s/it]
 29%|██▊       | 287/1000 [09:15<15:19,  1.29s/it]
                                                  

 29%|██▊       | 287/1000 [09:15<15:19,  1.29s/it]
 29%|██▉       | 288/1000 [09:16<15:18,  1.29s/it]
                                                  

 29%|██▉       | 288/1000 [09:16<15:18,  1.29s/it]
 29%|██▉       | 289/1000 [09:17<15:14,  1.29s/it]
                                                  

 29%|██▉       | 289/1000 [09:17<15:14,  1.29s/it]
 29%|██▉       | 290/1000 [09:19<14:41,  1.24s/it]
                                                  

 29%|██▉       | 290/1000 [09:19<14:41,  1.24s/it]
 29%|██▉       | 291/1000 [09:20<13:36,  1.15s/it]
                                                  

 29%|██▉       | 291/1000 [09:20<13:36,  1.15s/it]
 29%|██▉       | 292/1000 [09:20<12:46,  1.08s/it]
                                                  

 29%|██▉       | 292/1000 [09:20<12:46,  1.08s/it]
 29%|██▉       | 293/1000 [09:21<12:19,  1.05s/it]
                                                  

 29%|██▉       | 293/1000 [09:21<12:19,  1.05s/it]
 29%|██▉       | 294/1000 [09:22<11:56,  1.02s/it]
                                                  

 29%|██▉       | 294/1000 [09:22<11:56,  1.02s/it]
 30%|██▉       | 295/1000 [09:23<11:36,  1.01it/s]
                                                  

 30%|██▉       | 295/1000 [09:23<11:36,  1.01it/s]
 30%|██▉       | 296/1000 [09:24<11:30,  1.02it/s]
                                                  

 30%|██▉       | 296/1000 [09:24<11:30,  1.02it/s]
 30%|██▉       | 297/1000 [09:25<10:33,  1.11it/s]
                                                  

 30%|██▉       | 297/1000 [09:25<10:33,  1.11it/s]
 30%|██▉       | 298/1000 [09:26<09:43,  1.20it/s]
                                                  

 30%|██▉       | 298/1000 [09:26<09:43,  1.20it/s]
 30%|██▉       | 299/1000 [09:26<09:13,  1.27it/s]
                                                  

 30%|██▉       | 299/1000 [09:26<09:13,  1.27it/s]
 30%|███       | 300/1000 [09:29<16:55,  1.45s/it]
                                                  

 30%|███       | 300/1000 [09:29<16:55,  1.45s/it]
 30%|███       | 301/1000 [09:37<39:23,  3.38s/it]
                                                  

 30%|███       | 301/1000 [09:37<39:23,  3.38s/it]
 30%|███       | 302/1000 [09:42<42:57,  3.69s/it]
                                                  

 30%|███       | 302/1000 [09:42<42:57,  3.69s/it]
 30%|███       | 303/1000 [09:46<43:36,  3.75s/it]
                                                  

 30%|███       | 303/1000 [09:46<43:36,  3.75s/it]
 30%|███       | 304/1000 [09:49<42:39,  3.68s/it]
                                                  

 30%|███       | 304/1000 [09:49<42:39,  3.68s/it]
 30%|███       | 305/1000 [09:52<40:56,  3.53s/it]
                                                  

 30%|███       | 305/1000 [09:52<40:56,  3.53s/it]
 31%|███       | 306/1000 [09:55<39:03,  3.38s/it]
                                                  

 31%|███       | 306/1000 [09:55<39:03,  3.38s/it]
 31%|███       | 307/1000 [09:58<37:08,  3.22s/it]
                                                  

 31%|███       | 307/1000 [09:58<37:08,  3.22s/it]
 31%|███       | 308/1000 [10:01<35:16,  3.06s/it]
                                                  

 31%|███       | 308/1000 [10:01<35:16,  3.06s/it]
 31%|███       | 309/1000 [10:03<34:00,  2.95s/it]
                                                  

 31%|███       | 309/1000 [10:04<34:00,  2.95s/it]
 31%|███       | 310/1000 [10:06<32:15,  2.80s/it]
                                                  

 31%|███       | 310/1000 [10:06<32:15,  2.80s/it]
 31%|███       | 311/1000 [10:08<30:36,  2.67s/it]
                                                  

 31%|███       | 311/1000 [10:08<30:36,  2.67s/it]
 31%|███       | 312/1000 [10:11<29:30,  2.57s/it]
                                                  

 31%|███       | 312/1000 [10:11<29:30,  2.57s/it]
 31%|███▏      | 313/1000 [10:13<28:02,  2.45s/it]
                                                  

 31%|███▏      | 313/1000 [10:13<28:02,  2.45s/it]
 31%|███▏      | 314/1000 [10:15<26:58,  2.36s/it]
                                                  

 31%|███▏      | 314/1000 [10:15<26:58,  2.36s/it]
 32%|███▏      | 315/1000 [10:17<26:06,  2.29s/it]
                                                  

 32%|███▏      | 315/1000 [10:17<26:06,  2.29s/it]
 32%|███▏      | 316/1000 [10:19<25:15,  2.22s/it]
                                                  

 32%|███▏      | 316/1000 [10:19<25:15,  2.22s/it]
 32%|███▏      | 317/1000 [10:21<24:50,  2.18s/it]
                                                  

 32%|███▏      | 317/1000 [10:21<24:50,  2.18s/it]
 32%|███▏      | 318/1000 [10:23<24:10,  2.13s/it]
                                                  

 32%|███▏      | 318/1000 [10:23<24:10,  2.13s/it]
 32%|███▏      | 319/1000 [10:25<23:09,  2.04s/it]
                                                  

 32%|███▏      | 319/1000 [10:25<23:09,  2.04s/it]
 32%|███▏      | 320/1000 [10:27<22:04,  1.95s/it]
                                                  

 32%|███▏      | 320/1000 [10:27<22:04,  1.95s/it]
 32%|███▏      | 321/1000 [10:29<21:34,  1.91s/it]
                                                  

 32%|███▏      | 321/1000 [10:29<21:34,  1.91s/it]
 32%|███▏      | 322/1000 [10:31<21:36,  1.91s/it]
                                                  

 32%|███▏      | 322/1000 [10:31<21:36,  1.91s/it]
 32%|███▏      | 323/1000 [10:32<20:59,  1.86s/it]
                                                  

 32%|███▏      | 323/1000 [10:32<20:59,  1.86s/it]
 32%|███▏      | 324/1000 [10:34<20:38,  1.83s/it]
                                                  

 32%|███▏      | 324/1000 [10:34<20:38,  1.83s/it]
 32%|███▎      | 325/1000 [10:36<19:43,  1.75s/it]
                                                  

 32%|███▎      | 325/1000 [10:36<19:43,  1.75s/it]
 33%|███▎      | 326/1000 [10:37<18:54,  1.68s/it]
                                                  

 33%|███▎      | 326/1000 [10:37<18:54,  1.68s/it]
 33%|███▎      | 327/1000 [10:39<18:30,  1.65s/it]
                                                  

 33%|███▎      | 327/1000 [10:39<18:30,  1.65s/it]
 33%|███▎      | 328/1000 [10:40<18:22,  1.64s/it]
                                                  

 33%|███▎      | 328/1000 [10:40<18:22,  1.64s/it]
 33%|███▎      | 329/1000 [10:42<17:52,  1.60s/it]
                                                  

 33%|███▎      | 329/1000 [10:42<17:52,  1.60s/it]
 33%|███▎      | 330/1000 [10:43<17:28,  1.56s/it]
                                                  

 33%|███▎      | 330/1000 [10:43<17:28,  1.56s/it]
 33%|███▎      | 331/1000 [10:45<17:16,  1.55s/it]
                                                  

 33%|███▎      | 331/1000 [10:45<17:16,  1.55s/it]
 33%|███▎      | 332/1000 [10:46<16:57,  1.52s/it]
                                                  

 33%|███▎      | 332/1000 [10:46<16:57,  1.52s/it]
 33%|███▎      | 333/1000 [10:48<16:14,  1.46s/it]
                                                  

 33%|███▎      | 333/1000 [10:48<16:14,  1.46s/it]
 33%|███▎      | 334/1000 [10:49<15:21,  1.38s/it]
                                                  

 33%|███▎      | 334/1000 [10:49<15:21,  1.38s/it]
 34%|███▎      | 335/1000 [10:50<14:51,  1.34s/it]
                                                  

 34%|███▎      | 335/1000 [10:50<14:51,  1.34s/it]
 34%|███▎      | 336/1000 [10:51<14:24,  1.30s/it]
                                                  

 34%|███▎      | 336/1000 [10:51<14:24,  1.30s/it]
 34%|███▎      | 337/1000 [10:52<14:04,  1.27s/it]
                                                  

 34%|███▎      | 337/1000 [10:52<14:04,  1.27s/it]
 34%|███▍      | 338/1000 [10:54<13:49,  1.25s/it]
                                                  

 34%|███▍      | 338/1000 [10:54<13:49,  1.25s/it]
 34%|███▍      | 339/1000 [10:55<13:44,  1.25s/it]
                                                  

 34%|███▍      | 339/1000 [10:55<13:44,  1.25s/it]
 34%|███▍      | 340/1000 [10:56<13:35,  1.24s/it]
                                                  

 34%|███▍      | 340/1000 [10:56<13:35,  1.24s/it]
 34%|███▍      | 341/1000 [10:57<13:08,  1.20s/it]
                                                  

 34%|███▍      | 341/1000 [10:57<13:08,  1.20s/it]
 34%|███▍      | 342/1000 [10:58<12:14,  1.12s/it]
                                                  

 34%|███▍      | 342/1000 [10:58<12:14,  1.12s/it]
 34%|███▍      | 343/1000 [10:59<11:36,  1.06s/it]
                                                  

 34%|███▍      | 343/1000 [10:59<11:36,  1.06s/it]
 34%|███▍      | 344/1000 [11:00<11:11,  1.02s/it]
                                                  

 34%|███▍      | 344/1000 [11:00<11:11,  1.02s/it]
 34%|███▍      | 345/1000 [11:01<10:50,  1.01it/s]
                                                  

 34%|███▍      | 345/1000 [11:01<10:50,  1.01it/s]
 35%|███▍      | 346/1000 [11:02<10:35,  1.03it/s]
                                                  

 35%|███▍      | 346/1000 [11:02<10:35,  1.03it/s]
 35%|███▍      | 347/1000 [11:03<10:01,  1.09it/s]
                                                  

 35%|███▍      | 347/1000 [11:03<10:01,  1.09it/s]
 35%|███▍      | 348/1000 [11:03<09:19,  1.17it/s]
                                                  

 35%|███▍      | 348/1000 [11:03<09:19,  1.17it/s]
 35%|███▍      | 349/1000 [11:04<08:41,  1.25it/s]
                                                  

 35%|███▍      | 349/1000 [11:04<08:41,  1.25it/s]
 35%|███▌      | 350/1000 [11:07<15:31,  1.43s/it]
                                                  

 35%|███▌      | 350/1000 [11:07<15:31,  1.43s/it]
 35%|███▌      | 351/1000 [11:18<46:16,  4.28s/it]
                                                  

 35%|███▌      | 351/1000 [11:18<46:16,  4.28s/it]
 35%|███▌      | 352/1000 [11:22<46:13,  4.28s/it]
                                                  

 35%|███▌      | 352/1000 [11:22<46:13,  4.28s/it]
 35%|███▌      | 353/1000 [11:26<44:29,  4.13s/it]
                                                  

 35%|███▌      | 353/1000 [11:26<44:29,  4.13s/it]
 35%|███▌      | 354/1000 [11:29<41:50,  3.89s/it]
                                                  

 35%|███▌      | 354/1000 [11:29<41:50,  3.89s/it]
 36%|███▌      | 355/1000 [11:32<39:00,  3.63s/it]
                                                  

 36%|███▌      | 355/1000 [11:32<39:00,  3.63s/it]
 36%|███▌      | 356/1000 [11:35<37:05,  3.46s/it]
                                                  

 36%|███▌      | 356/1000 [11:35<37:05,  3.46s/it]
 36%|███▌      | 357/1000 [11:38<35:14,  3.29s/it]
                                                  

 36%|███▌      | 357/1000 [11:38<35:14,  3.29s/it]
 36%|███▌      | 358/1000 [11:41<33:15,  3.11s/it]
                                                  

 36%|███▌      | 358/1000 [11:41<33:15,  3.11s/it]
 36%|███▌      | 359/1000 [11:43<31:24,  2.94s/it]
                                                  

 36%|███▌      | 359/1000 [11:43<31:24,  2.94s/it]
 36%|███▌      | 360/1000 [11:46<29:30,  2.77s/it]
                                                  

 36%|███▌      | 360/1000 [11:46<29:30,  2.77s/it]
 36%|███▌      | 361/1000 [11:48<28:33,  2.68s/it]
                                                  

 36%|███▌      | 361/1000 [11:48<28:33,  2.68s/it]
 36%|███▌      | 362/1000 [11:51<27:31,  2.59s/it]
                                                  

 36%|███▌      | 362/1000 [11:51<27:31,  2.59s/it]
 36%|███▋      | 363/1000 [11:53<26:35,  2.51s/it]
                                                  

 36%|███▋      | 363/1000 [11:53<26:35,  2.51s/it]
 36%|███▋      | 364/1000 [11:55<25:12,  2.38s/it]
                                                  

 36%|███▋      | 364/1000 [11:55<25:12,  2.38s/it]
 36%|███▋      | 365/1000 [11:57<24:15,  2.29s/it]
                                                  

 36%|███▋      | 365/1000 [11:57<24:15,  2.29s/it]
 37%|███▋      | 366/1000 [11:59<23:27,  2.22s/it]
                                                  

 37%|███▋      | 366/1000 [11:59<23:27,  2.22s/it]
 37%|███▋      | 367/1000 [12:01<23:20,  2.21s/it]
                                                  

 37%|███▋      | 367/1000 [12:01<23:20,  2.21s/it]
 37%|███▋      | 368/1000 [12:03<22:35,  2.14s/it]
                                                  

 37%|███▋      | 368/1000 [12:03<22:35,  2.14s/it]
 37%|███▋      | 369/1000 [12:05<21:29,  2.04s/it]
                                                  

 37%|███▋      | 369/1000 [12:05<21:29,  2.04s/it]
 37%|███▋      | 370/1000 [12:07<20:45,  1.98s/it]
                                                  

 37%|███▋      | 370/1000 [12:07<20:45,  1.98s/it]
 37%|███▋      | 371/1000 [12:09<20:01,  1.91s/it]
                                                  

 37%|███▋      | 371/1000 [12:09<20:01,  1.91s/it]
 37%|███▋      | 372/1000 [12:11<19:40,  1.88s/it]
                                                  

 37%|███▋      | 372/1000 [12:11<19:40,  1.88s/it]
 37%|███▋      | 373/1000 [12:12<19:22,  1.85s/it]
                                                  

 37%|███▋      | 373/1000 [12:12<19:22,  1.85s/it]
 37%|███▋      | 374/1000 [12:14<19:12,  1.84s/it]
                                                  

 37%|███▋      | 374/1000 [12:14<19:12,  1.84s/it]
 38%|███▊      | 375/1000 [12:16<18:30,  1.78s/it]
                                                  

 38%|███▊      | 375/1000 [12:16<18:30,  1.78s/it]
 38%|███▊      | 376/1000 [12:17<17:36,  1.69s/it]
                                                  

 38%|███▊      | 376/1000 [12:17<17:36,  1.69s/it]
 38%|███▊      | 377/1000 [12:19<16:55,  1.63s/it]
                                                  

 38%|███▊      | 377/1000 [12:19<16:55,  1.63s/it]
 38%|███▊      | 378/1000 [12:20<16:34,  1.60s/it]
                                                  

 38%|███▊      | 378/1000 [12:20<16:34,  1.60s/it]
 38%|███▊      | 379/1000 [12:22<16:20,  1.58s/it]
                                                  

 38%|███▊      | 379/1000 [12:22<16:20,  1.58s/it]
 38%|███▊      | 380/1000 [12:23<16:05,  1.56s/it]
                                                  

 38%|███▊      | 380/1000 [12:23<16:05,  1.56s/it]
 38%|███▊      | 381/1000 [12:25<15:57,  1.55s/it]
                                                  

 38%|███▊      | 381/1000 [12:25<15:57,  1.55s/it]
 38%|███▊      | 382/1000 [12:26<15:22,  1.49s/it]
                                                  

 38%|███▊      | 382/1000 [12:26<15:22,  1.49s/it]
 38%|███▊      | 383/1000 [12:27<14:35,  1.42s/it]
                                                  

 38%|███▊      | 383/1000 [12:28<14:35,  1.42s/it]
 38%|███▊      | 384/1000 [12:29<14:01,  1.37s/it]
                                                  

 38%|███▊      | 384/1000 [12:29<14:01,  1.37s/it]
 38%|███▊      | 385/1000 [12:30<13:55,  1.36s/it]
                                                  

 38%|███▊      | 385/1000 [12:30<13:55,  1.36s/it]
 39%|███▊      | 386/1000 [12:31<13:30,  1.32s/it]
                                                  

 39%|███▊      | 386/1000 [12:31<13:30,  1.32s/it]
 39%|███▊      | 387/1000 [12:33<13:21,  1.31s/it]
                                                  

 39%|███▊      | 387/1000 [12:33<13:21,  1.31s/it]
 39%|███▉      | 388/1000 [12:34<13:18,  1.31s/it]
                                                  

 39%|███▉      | 388/1000 [12:34<13:18,  1.31s/it]
 39%|███▉      | 389/1000 [12:35<13:09,  1.29s/it]
                                                  

 39%|███▉      | 389/1000 [12:35<13:09,  1.29s/it]
 39%|███▉      | 390/1000 [12:36<12:51,  1.26s/it]
                                                  

 39%|███▉      | 390/1000 [12:36<12:51,  1.26s/it]
 39%|███▉      | 391/1000 [12:37<12:26,  1.23s/it]
                                                  

 39%|███▉      | 391/1000 [12:37<12:26,  1.23s/it]
 39%|███▉      | 392/1000 [12:38<11:30,  1.14s/it]
                                                  

 39%|███▉      | 392/1000 [12:38<11:30,  1.14s/it]
 39%|███▉      | 393/1000 [12:39<10:57,  1.08s/it]
                                                  

 39%|███▉      | 393/1000 [12:39<10:57,  1.08s/it]
 39%|███▉      | 394/1000 [12:40<10:31,  1.04s/it]
                                                  

 39%|███▉      | 394/1000 [12:40<10:31,  1.04s/it]
 40%|███▉      | 395/1000 [12:41<10:16,  1.02s/it]
                                                  

 40%|███▉      | 395/1000 [12:41<10:16,  1.02s/it]
 40%|███▉      | 396/1000 [12:42<10:16,  1.02s/it]
                                                  

 40%|███▉      | 396/1000 [12:42<10:16,  1.02s/it]
 40%|███▉      | 397/1000 [12:43<09:35,  1.05it/s]
                                                  

 40%|███▉      | 397/1000 [12:43<09:35,  1.05it/s]
 40%|███▉      | 398/1000 [12:44<08:52,  1.13it/s]
                                                  

 40%|███▉      | 398/1000 [12:44<08:52,  1.13it/s]
 40%|███▉      | 399/1000 [12:44<08:12,  1.22it/s]
                                                  

 40%|███▉      | 399/1000 [12:45<08:12,  1.22it/s]
 40%|████      | 400/1000 [12:47<13:49,  1.38s/it]
                                                  

 40%|████      | 400/1000 [12:47<13:49,  1.38s/it]
 40%|████      | 401/1000 [12:56<37:28,  3.75s/it]
                                                  

 40%|████      | 401/1000 [12:56<37:28,  3.75s/it]
 40%|████      | 402/1000 [13:01<38:25,  3.85s/it]
                                                  

 40%|████      | 402/1000 [13:01<38:25,  3.85s/it]
 40%|████      | 403/1000 [13:04<37:55,  3.81s/it]
                                                  

 40%|████      | 403/1000 [13:04<37:55,  3.81s/it]
 40%|████      | 404/1000 [13:07<36:08,  3.64s/it]
                                                  

 40%|████      | 404/1000 [13:08<36:08,  3.64s/it]
 40%|████      | 405/1000 [13:11<34:17,  3.46s/it]
                                                  

 40%|████      | 405/1000 [13:11<34:17,  3.46s/it]
 41%|████      | 406/1000 [13:13<32:33,  3.29s/it]
                                                  

 41%|████      | 406/1000 [13:13<32:33,  3.29s/it]
 41%|████      | 407/1000 [13:16<30:41,  3.10s/it]
                                                  

 41%|████      | 407/1000 [13:16<30:41,  3.10s/it]
 41%|████      | 408/1000 [13:19<29:09,  2.96s/it]
                                                  

 41%|████      | 408/1000 [13:19<29:09,  2.96s/it]
 41%|████      | 409/1000 [13:21<27:34,  2.80s/it]
                                                  

 41%|████      | 409/1000 [13:21<27:34,  2.80s/it]
 41%|████      | 410/1000 [13:23<26:10,  2.66s/it]
                                                  

 41%|████      | 410/1000 [13:24<26:10,  2.66s/it]
 41%|████      | 411/1000 [13:26<25:16,  2.57s/it]
                                                  

 41%|████      | 411/1000 [13:26<25:16,  2.57s/it]
 41%|████      | 412/1000 [13:28<24:13,  2.47s/it]
                                                  

 41%|████      | 412/1000 [13:28<24:13,  2.47s/it]
 41%|████▏     | 413/1000 [13:30<23:08,  2.36s/it]
                                                  

 41%|████▏     | 413/1000 [13:30<23:08,  2.36s/it]
 41%|████▏     | 414/1000 [13:32<22:26,  2.30s/it]
                                                  

 41%|████▏     | 414/1000 [13:32<22:26,  2.30s/it]
 42%|████▏     | 415/1000 [13:34<21:56,  2.25s/it]
                                                  

 42%|████▏     | 415/1000 [13:35<21:56,  2.25s/it]
 42%|████▏     | 416/1000 [13:37<21:15,  2.18s/it]
                                                  

 42%|████▏     | 416/1000 [13:37<21:15,  2.18s/it]
 42%|████▏     | 417/1000 [13:38<20:21,  2.09s/it]
                                                  

 42%|████▏     | 417/1000 [13:38<20:21,  2.09s/it]
 42%|████▏     | 418/1000 [13:40<19:20,  1.99s/it]
                                                  

 42%|████▏     | 418/1000 [13:40<19:20,  1.99s/it]
 42%|████▏     | 419/1000 [13:42<18:43,  1.93s/it]
                                                  

 42%|████▏     | 419/1000 [13:42<18:43,  1.93s/it]
 42%|████▏     | 420/1000 [13:44<18:18,  1.89s/it]
                                                  

 42%|████▏     | 420/1000 [13:44<18:18,  1.89s/it]
 42%|████▏     | 421/1000 [13:46<17:54,  1.86s/it]
                                                  

 42%|████▏     | 421/1000 [13:46<17:54,  1.86s/it]
 42%|████▏     | 422/1000 [13:47<17:40,  1.84s/it]
                                                  

 42%|████▏     | 422/1000 [13:47<17:40,  1.84s/it]
 42%|████▏     | 423/1000 [13:49<17:09,  1.78s/it]
                                                  

 42%|████▏     | 423/1000 [13:49<17:09,  1.78s/it]
 42%|████▏     | 424/1000 [13:51<16:32,  1.72s/it]
                                                  

 42%|████▏     | 424/1000 [13:51<16:32,  1.72s/it]
 42%|████▎     | 425/1000 [13:52<15:52,  1.66s/it]
                                                  

 42%|████▎     | 425/1000 [13:52<15:52,  1.66s/it]
 43%|████▎     | 426/1000 [13:54<15:23,  1.61s/it]
                                                  

 43%|████▎     | 426/1000 [13:54<15:23,  1.61s/it]
 43%|████▎     | 427/1000 [13:55<15:06,  1.58s/it]
                                                  

 43%|████▎     | 427/1000 [13:55<15:06,  1.58s/it]
 43%|████▎     | 428/1000 [13:57<14:46,  1.55s/it]
                                                  

 43%|████▎     | 428/1000 [13:57<14:46,  1.55s/it]
 43%|████▎     | 429/1000 [13:58<14:37,  1.54s/it]
                                                  

 43%|████▎     | 429/1000 [13:58<14:37,  1.54s/it]
 43%|████▎     | 430/1000 [14:00<14:35,  1.54s/it]
                                                  

 43%|████▎     | 430/1000 [14:00<14:35,  1.54s/it]
 43%|████▎     | 431/1000 [14:01<14:40,  1.55s/it]
                                                  

 43%|████▎     | 431/1000 [14:01<14:40,  1.55s/it]
 43%|████▎     | 432/1000 [14:02<13:58,  1.48s/it]
                                                  

 43%|████▎     | 432/1000 [14:02<13:58,  1.48s/it]
 43%|████▎     | 433/1000 [14:04<13:16,  1.40s/it]
                                                  

 43%|████▎     | 433/1000 [14:04<13:16,  1.40s/it]
 43%|████▎     | 434/1000 [14:05<13:05,  1.39s/it]
                                                  

 43%|████▎     | 434/1000 [14:05<13:05,  1.39s/it]
 44%|████▎     | 435/1000 [14:06<12:40,  1.35s/it]
                                                  

 44%|████▎     | 435/1000 [14:06<12:40,  1.35s/it]
 44%|████▎     | 436/1000 [14:08<12:25,  1.32s/it]
                                                  

 44%|████▎     | 436/1000 [14:08<12:25,  1.32s/it]
 44%|████▎     | 437/1000 [14:09<12:13,  1.30s/it]
                                                  

 44%|████▎     | 437/1000 [14:09<12:13,  1.30s/it]
 44%|████▍     | 438/1000 [14:10<12:03,  1.29s/it]
                                                  

 44%|████▍     | 438/1000 [14:10<12:03,  1.29s/it]
 44%|████▍     | 439/1000 [14:11<11:55,  1.28s/it]
                                                  

 44%|████▍     | 439/1000 [14:11<11:55,  1.28s/it]
 44%|████▍     | 440/1000 [14:12<11:27,  1.23s/it]
                                                  

 44%|████▍     | 440/1000 [14:12<11:27,  1.23s/it]
 44%|████▍     | 441/1000 [14:13<10:41,  1.15s/it]
                                                  

 44%|████▍     | 441/1000 [14:13<10:41,  1.15s/it]
 44%|████▍     | 442/1000 [14:14<10:12,  1.10s/it]
                                                  

 44%|████▍     | 442/1000 [14:14<10:12,  1.10s/it]
 44%|████▍     | 443/1000 [14:15<09:51,  1.06s/it]
                                                  

 44%|████▍     | 443/1000 [14:15<09:51,  1.06s/it]
 44%|████▍     | 444/1000 [14:16<09:31,  1.03s/it]
                                                  

 44%|████▍     | 444/1000 [14:16<09:31,  1.03s/it]
 44%|████▍     | 445/1000 [14:17<09:20,  1.01s/it]
                                                  

 44%|████▍     | 445/1000 [14:17<09:20,  1.01s/it]
 45%|████▍     | 446/1000 [14:18<09:01,  1.02it/s]
                                                  

 45%|████▍     | 446/1000 [14:18<09:01,  1.02it/s]
 45%|████▍     | 447/1000 [14:19<08:16,  1.11it/s]
                                                  

 45%|████▍     | 447/1000 [14:19<08:16,  1.11it/s]
 45%|████▍     | 448/1000 [14:20<07:38,  1.20it/s]
                                                  

 45%|████▍     | 448/1000 [14:20<07:38,  1.20it/s]
 45%|████▍     | 449/1000 [14:20<07:11,  1.28it/s]
                                                  

 45%|████▍     | 449/1000 [14:20<07:11,  1.28it/s]
 45%|████▌     | 450/1000 [14:23<12:53,  1.41s/it]
                                                  

 45%|████▌     | 450/1000 [14:23<12:53,  1.41s/it]
 45%|████▌     | 451/1000 [14:31<31:57,  3.49s/it]
                                                  

 45%|████▌     | 451/1000 [14:31<31:57,  3.49s/it]
 45%|████▌     | 452/1000 [14:36<34:14,  3.75s/it]
                                                  

 45%|████▌     | 452/1000 [14:36<34:14,  3.75s/it]
 45%|████▌     | 453/1000 [14:39<33:53,  3.72s/it]
                                                  

 45%|████▌     | 453/1000 [14:39<33:53,  3.72s/it]
 45%|████▌     | 454/1000 [14:43<32:44,  3.60s/it]
                                                  

 45%|████▌     | 454/1000 [14:43<32:44,  3.60s/it]
 46%|████▌     | 455/1000 [14:46<31:19,  3.45s/it]
                                                  

 46%|████▌     | 455/1000 [14:46<31:19,  3.45s/it]
 46%|████▌     | 456/1000 [14:49<29:56,  3.30s/it]
                                                  

 46%|████▌     | 456/1000 [14:49<29:56,  3.30s/it]
 46%|████▌     | 457/1000 [14:52<28:24,  3.14s/it]
                                                  

 46%|████▌     | 457/1000 [14:52<28:24,  3.14s/it]
 46%|████▌     | 458/1000 [14:54<26:38,  2.95s/it]
                                                  

 46%|████▌     | 458/1000 [14:54<26:38,  2.95s/it]
 46%|████▌     | 459/1000 [14:57<25:08,  2.79s/it]
                                                  

 46%|████▌     | 459/1000 [14:57<25:08,  2.79s/it]
 46%|████▌     | 460/1000 [14:59<24:01,  2.67s/it]
                                                  

 46%|████▌     | 460/1000 [14:59<24:01,  2.67s/it]
 46%|████▌     | 461/1000 [15:01<22:49,  2.54s/it]
                                                  

 46%|████▌     | 461/1000 [15:01<22:49,  2.54s/it]
 46%|████▌     | 462/1000 [15:03<21:28,  2.39s/it]
                                                  

 46%|████▌     | 462/1000 [15:03<21:28,  2.39s/it]
 46%|████▋     | 463/1000 [15:05<20:46,  2.32s/it]
                                                  

 46%|████▋     | 463/1000 [15:05<20:46,  2.32s/it]
 46%|████▋     | 464/1000 [15:07<20:04,  2.25s/it]
                                                  

 46%|████▋     | 464/1000 [15:07<20:04,  2.25s/it]
 46%|████▋     | 465/1000 [15:10<19:42,  2.21s/it]
                                                  

 46%|████▋     | 465/1000 [15:10<19:42,  2.21s/it]
 47%|████▋     | 466/1000 [15:12<19:12,  2.16s/it]
                                                  

 47%|████▋     | 466/1000 [15:12<19:12,  2.16s/it]
 47%|████▋     | 467/1000 [15:13<18:21,  2.07s/it]
                                                  

 47%|████▋     | 467/1000 [15:13<18:21,  2.07s/it]
 47%|████▋     | 468/1000 [15:15<17:26,  1.97s/it]
                                                  

 47%|████▋     | 468/1000 [15:15<17:26,  1.97s/it]
 47%|████▋     | 469/1000 [15:17<16:50,  1.90s/it]
                                                  

 47%|████▋     | 469/1000 [15:17<16:50,  1.90s/it]
 47%|████▋     | 470/1000 [15:19<16:22,  1.85s/it]
                                                  

 47%|████▋     | 470/1000 [15:19<16:22,  1.85s/it]
 47%|████▋     | 471/1000 [15:20<16:01,  1.82s/it]
                                                  

 47%|████▋     | 471/1000 [15:20<16:01,  1.82s/it]
 47%|████▋     | 472/1000 [15:22<15:51,  1.80s/it]
                                                  

 47%|████▋     | 472/1000 [15:22<15:51,  1.80s/it]
 47%|████▋     | 473/1000 [15:24<15:49,  1.80s/it]
                                                  

 47%|████▋     | 473/1000 [15:24<15:49,  1.80s/it]
 47%|████▋     | 474/1000 [15:25<15:04,  1.72s/it]
                                                  

 47%|████▋     | 474/1000 [15:26<15:04,  1.72s/it]
 48%|████▊     | 475/1000 [15:27<14:32,  1.66s/it]
                                                  

 48%|████▊     | 475/1000 [15:27<14:32,  1.66s/it]
 48%|████▊     | 476/1000 [15:29<14:05,  1.61s/it]
                                                  

 48%|████▊     | 476/1000 [15:29<14:05,  1.61s/it]
 48%|████▊     | 477/1000 [15:30<13:49,  1.59s/it]
                                                  

 48%|████▊     | 477/1000 [15:30<13:49,  1.59s/it]
 48%|████▊     | 478/1000 [15:32<13:47,  1.59s/it]
                                                  

 48%|████▊     | 478/1000 [15:32<13:47,  1.59s/it]
 48%|████▊     | 479/1000 [15:33<13:34,  1.56s/it]
                                                  

 48%|████▊     | 479/1000 [15:33<13:34,  1.56s/it]
 48%|████▊     | 480/1000 [15:35<13:31,  1.56s/it]
                                                  

 48%|████▊     | 480/1000 [15:35<13:31,  1.56s/it]
 48%|████▊     | 481/1000 [15:36<13:16,  1.53s/it]
                                                  

 48%|████▊     | 481/1000 [15:36<13:16,  1.53s/it]
 48%|████▊     | 482/1000 [15:37<12:40,  1.47s/it]
                                                  

 48%|████▊     | 482/1000 [15:38<12:40,  1.47s/it]
 48%|████▊     | 483/1000 [15:39<12:00,  1.39s/it]
                                                  

 48%|████▊     | 483/1000 [15:39<12:00,  1.39s/it]
 48%|████▊     | 484/1000 [15:40<11:39,  1.36s/it]
                                                  

 48%|████▊     | 484/1000 [15:40<11:39,  1.36s/it]
 48%|████▊     | 485/1000 [15:41<11:16,  1.31s/it]
                                                  

 48%|████▊     | 485/1000 [15:41<11:16,  1.31s/it]
 49%|████▊     | 486/1000 [15:42<11:01,  1.29s/it]
                                                  

 49%|████▊     | 486/1000 [15:42<11:01,  1.29s/it]
 49%|████▊     | 487/1000 [15:44<10:48,  1.26s/it]
                                                  

 49%|████▊     | 487/1000 [15:44<10:48,  1.26s/it]
 49%|████▉     | 488/1000 [15:45<10:39,  1.25s/it]
                                                  

 49%|████▉     | 488/1000 [15:45<10:39,  1.25s/it]
 49%|████▉     | 489/1000 [15:46<10:38,  1.25s/it]
                                                  

 49%|████▉     | 489/1000 [15:46<10:38,  1.25s/it]
 49%|████▉     | 490/1000 [15:47<10:17,  1.21s/it]
                                                  

 49%|████▉     | 490/1000 [15:47<10:17,  1.21s/it]
 49%|████▉     | 491/1000 [15:48<09:38,  1.14s/it]
                                                  

 49%|████▉     | 491/1000 [15:48<09:38,  1.14s/it]
 49%|████▉     | 492/1000 [15:49<09:11,  1.09s/it]
                                                  

 49%|████▉     | 492/1000 [15:49<09:11,  1.09s/it]
 49%|████▉     | 493/1000 [15:50<08:55,  1.06s/it]
                                                  

 49%|████▉     | 493/1000 [15:50<08:55,  1.06s/it]
 49%|████▉     | 494/1000 [15:51<08:41,  1.03s/it]
                                                  

 49%|████▉     | 494/1000 [15:51<08:41,  1.03s/it]
 50%|████▉     | 495/1000 [15:52<08:24,  1.00it/s]
                                                  

 50%|████▉     | 495/1000 [15:52<08:24,  1.00it/s]
 50%|████▉     | 496/1000 [15:53<08:13,  1.02it/s]
                                                  

 50%|████▉     | 496/1000 [15:53<08:13,  1.02it/s]
 50%|████▉     | 497/1000 [15:54<07:58,  1.05it/s]
                                                  

 50%|████▉     | 497/1000 [15:54<07:58,  1.05it/s]
 50%|████▉     | 498/1000 [15:55<07:15,  1.15it/s]
                                                  

 50%|████▉     | 498/1000 [15:55<07:15,  1.15it/s]
 50%|████▉     | 499/1000 [15:55<06:45,  1.24it/s]
                                                  

 50%|████▉     | 499/1000 [15:55<06:45,  1.24it/s]
 50%|█████     | 500/1000 [15:58<11:36,  1.39s/it]
                                                  

 50%|█████     | 500/1000 [15:58<11:36,  1.39s/it]
 50%|█████     | 501/1000 [16:07<29:53,  3.59s/it]
                                                  

 50%|█████     | 501/1000 [16:07<29:53,  3.59s/it]
 50%|█████     | 502/1000 [16:11<31:17,  3.77s/it]
                                                  

 50%|█████     | 502/1000 [16:11<31:17,  3.77s/it]
 50%|█████     | 503/1000 [16:15<31:07,  3.76s/it]
                                                  

 50%|█████     | 503/1000 [16:15<31:07,  3.76s/it]
 50%|█████     | 504/1000 [16:18<29:58,  3.63s/it]
                                                  

 50%|█████     | 504/1000 [16:18<29:58,  3.63s/it]
 50%|█████     | 505/1000 [16:21<28:53,  3.50s/it]
                                                  

 50%|█████     | 505/1000 [16:21<28:53,  3.50s/it]
 51%|█████     | 506/1000 [16:24<27:27,  3.34s/it]
                                                  

 51%|█████     | 506/1000 [16:24<27:27,  3.34s/it]
 51%|█████     | 507/1000 [16:27<26:15,  3.20s/it]
                                                  

 51%|█████     | 507/1000 [16:27<26:15,  3.20s/it]
 51%|█████     | 508/1000 [16:30<24:56,  3.04s/it]
                                                  

 51%|█████     | 508/1000 [16:30<24:56,  3.04s/it]
 51%|█████     | 509/1000 [16:32<23:36,  2.89s/it]
                                                  

 51%|█████     | 509/1000 [16:32<23:36,  2.89s/it]
 51%|█████     | 510/1000 [16:35<22:30,  2.76s/it]
                                                  

 51%|█████     | 510/1000 [16:35<22:30,  2.76s/it]
 51%|█████     | 511/1000 [16:37<21:39,  2.66s/it]
                                                  

 51%|█████     | 511/1000 [16:37<21:39,  2.66s/it]
 51%|█████     | 512/1000 [16:39<20:46,  2.55s/it]
                                                  

 51%|█████     | 512/1000 [16:39<20:46,  2.55s/it]
 51%|█████▏    | 513/1000 [16:41<19:34,  2.41s/it]
                                                  

 51%|█████▏    | 513/1000 [16:41<19:34,  2.41s/it]
 51%|█████▏    | 514/1000 [16:43<18:43,  2.31s/it]
                                                  

 51%|█████▏    | 514/1000 [16:43<18:43,  2.31s/it]
 52%|█████▏    | 515/1000 [16:46<18:16,  2.26s/it]
                                                  

 52%|█████▏    | 515/1000 [16:46<18:16,  2.26s/it]
 52%|█████▏    | 516/1000 [16:48<17:52,  2.22s/it]
                                                  

 52%|█████▏    | 516/1000 [16:48<17:52,  2.22s/it]
 52%|█████▏    | 517/1000 [16:50<17:21,  2.16s/it]
                                                  

 52%|█████▏    | 517/1000 [16:50<17:21,  2.16s/it]
 52%|█████▏    | 518/1000 [16:52<16:29,  2.05s/it]
                                                  

 52%|█████▏    | 518/1000 [16:52<16:29,  2.05s/it]
 52%|█████▏    | 519/1000 [16:53<15:58,  1.99s/it]
                                                  

 52%|█████▏    | 519/1000 [16:53<15:58,  1.99s/it]
 52%|█████▏    | 520/1000 [16:55<15:28,  1.93s/it]
                                                  

 52%|█████▏    | 520/1000 [16:55<15:28,  1.93s/it]
 52%|█████▏    | 521/1000 [16:57<15:06,  1.89s/it]
                                                  

 52%|█████▏    | 521/1000 [16:57<15:06,  1.89s/it]
 52%|█████▏    | 522/1000 [16:59<14:47,  1.86s/it]
                                                  

 52%|█████▏    | 522/1000 [16:59<14:47,  1.86s/it]
 52%|█████▏    | 523/1000 [17:01<14:35,  1.84s/it]
                                                  

 52%|█████▏    | 523/1000 [17:01<14:35,  1.84s/it]
 52%|█████▏    | 524/1000 [17:02<14:04,  1.77s/it]
                                                  

 52%|█████▏    | 524/1000 [17:02<14:04,  1.77s/it]
 52%|█████▎    | 525/1000 [17:04<13:20,  1.69s/it]
                                                  

 52%|█████▎    | 525/1000 [17:04<13:20,  1.69s/it]
 53%|█████▎    | 526/1000 [17:05<12:55,  1.64s/it]
                                                  

 53%|█████▎    | 526/1000 [17:05<12:55,  1.64s/it]
 53%|█████▎    | 527/1000 [17:07<12:41,  1.61s/it]
                                                  

 53%|█████▎    | 527/1000 [17:07<12:41,  1.61s/it]
 53%|█████▎    | 528/1000 [17:08<12:26,  1.58s/it]
                                                  

 53%|█████▎    | 528/1000 [17:08<12:26,  1.58s/it]
 53%|█████▎    | 529/1000 [17:10<12:18,  1.57s/it]
                                                  

 53%|█████▎    | 529/1000 [17:10<12:18,  1.57s/it]
 53%|█████▎    | 530/1000 [17:11<12:11,  1.56s/it]
                                                  

 53%|█████▎    | 530/1000 [17:11<12:11,  1.56s/it]
 53%|█████▎    | 531/1000 [17:13<12:07,  1.55s/it]
                                                  

 53%|█████▎    | 531/1000 [17:13<12:07,  1.55s/it]
 53%|█████▎    | 532/1000 [17:14<11:41,  1.50s/it]
                                                  

 53%|█████▎    | 532/1000 [17:14<11:41,  1.50s/it]
 53%|█████▎    | 533/1000 [17:15<11:03,  1.42s/it]
                                                  

 53%|█████▎    | 533/1000 [17:15<11:03,  1.42s/it]
 53%|█████▎    | 534/1000 [17:17<10:44,  1.38s/it]
                                                  

 53%|█████▎    | 534/1000 [17:17<10:44,  1.38s/it]
 54%|█████▎    | 535/1000 [17:18<10:18,  1.33s/it]
                                                  

 54%|█████▎    | 535/1000 [17:18<10:18,  1.33s/it]
 54%|█████▎    | 536/1000 [17:19<10:10,  1.32s/it]
                                                  

 54%|█████▎    | 536/1000 [17:19<10:10,  1.32s/it]
 54%|█████▎    | 537/1000 [17:20<09:57,  1.29s/it]
                                                  

 54%|█████▎    | 537/1000 [17:21<09:57,  1.29s/it]
 54%|█████▍    | 538/1000 [17:22<09:50,  1.28s/it]
                                                  

 54%|█████▍    | 538/1000 [17:22<09:50,  1.28s/it]
 54%|█████▍    | 539/1000 [17:23<09:40,  1.26s/it]
                                                  

 54%|█████▍    | 539/1000 [17:23<09:40,  1.26s/it]
 54%|█████▍    | 540/1000 [17:24<09:25,  1.23s/it]
                                                  

 54%|█████▍    | 540/1000 [17:24<09:25,  1.23s/it]
 54%|█████▍    | 541/1000 [17:25<08:45,  1.15s/it]
                                                  

 54%|█████▍    | 541/1000 [17:25<08:45,  1.15s/it]
 54%|█████▍    | 542/1000 [17:26<08:14,  1.08s/it]
                                                  

 54%|█████▍    | 542/1000 [17:26<08:14,  1.08s/it]
 54%|█████▍    | 543/1000 [17:27<07:52,  1.03s/it]
                                                  

 54%|█████▍    | 543/1000 [17:27<07:52,  1.03s/it]
 54%|█████▍    | 544/1000 [17:28<07:38,  1.01s/it]
                                                  

 54%|█████▍    | 544/1000 [17:28<07:38,  1.01s/it]
 55%|█████▍    | 545/1000 [17:29<07:32,  1.01it/s]
                                                  

 55%|█████▍    | 545/1000 [17:29<07:32,  1.01it/s]
 55%|█████▍    | 546/1000 [17:30<07:18,  1.04it/s]
                                                  

 55%|█████▍    | 546/1000 [17:30<07:18,  1.04it/s]
 55%|█████▍    | 547/1000 [17:30<06:43,  1.12it/s]
                                                  

 55%|█████▍    | 547/1000 [17:30<06:43,  1.12it/s]
 55%|█████▍    | 548/1000 [17:31<06:16,  1.20it/s]
                                                  

 55%|█████▍    | 548/1000 [17:31<06:16,  1.20it/s]
 55%|█████▍    | 549/1000 [17:32<05:55,  1.27it/s]
                                                  

 55%|█████▍    | 549/1000 [17:32<05:55,  1.27it/s]
 55%|█████▌    | 550/1000 [17:35<10:38,  1.42s/it]
                                                  

 55%|█████▌    | 550/1000 [17:35<10:38,  1.42s/it]
 55%|█████▌    | 551/1000 [17:43<25:33,  3.41s/it]
                                                  

 55%|█████▌    | 551/1000 [17:43<25:33,  3.41s/it]
 55%|█████▌    | 552/1000 [17:47<28:14,  3.78s/it]
                                                  

 55%|█████▌    | 552/1000 [17:47<28:14,  3.78s/it]
 55%|█████▌    | 553/1000 [17:51<28:22,  3.81s/it]
                                                  

 55%|█████▌    | 553/1000 [17:51<28:22,  3.81s/it]
 55%|█████▌    | 554/1000 [17:55<27:42,  3.73s/it]
                                                  

 55%|█████▌    | 554/1000 [17:55<27:42,  3.73s/it]
 56%|█████▌    | 555/1000 [17:58<26:44,  3.61s/it]
                                                  

 56%|█████▌    | 555/1000 [17:58<26:44,  3.61s/it]
 56%|█████▌    | 556/1000 [18:01<25:31,  3.45s/it]
                                                  

 56%|█████▌    | 556/1000 [18:01<25:31,  3.45s/it]
 56%|█████▌    | 557/1000 [18:04<24:20,  3.30s/it]
                                                  

 56%|█████▌    | 557/1000 [18:04<24:20,  3.30s/it]
 56%|█████▌    | 558/1000 [18:07<23:04,  3.13s/it]
                                                  

 56%|█████▌    | 558/1000 [18:07<23:04,  3.13s/it]
 56%|█████▌    | 559/1000 [18:10<22:03,  3.00s/it]
                                                  

 56%|█████▌    | 559/1000 [18:10<22:03,  3.00s/it]
 56%|█████▌    | 560/1000 [18:12<20:44,  2.83s/it]
                                                  

 56%|█████▌    | 560/1000 [18:12<20:44,  2.83s/it]
 56%|█████▌    | 561/1000 [18:14<19:44,  2.70s/it]
                                                  

 56%|█████▌    | 561/1000 [18:14<19:44,  2.70s/it]
 56%|█████▌    | 562/1000 [18:17<18:56,  2.59s/it]
                                                  

 56%|█████▌    | 562/1000 [18:17<18:56,  2.59s/it]
 56%|█████▋    | 563/1000 [18:19<18:19,  2.52s/it]
                                                  

 56%|█████▋    | 563/1000 [18:19<18:19,  2.52s/it]
 56%|█████▋    | 564/1000 [18:21<17:29,  2.41s/it]
                                                  

 56%|█████▋    | 564/1000 [18:21<17:29,  2.41s/it]
 56%|█████▋    | 565/1000 [18:23<16:50,  2.32s/it]
                                                  

 56%|█████▋    | 565/1000 [18:23<16:50,  2.32s/it]
 57%|█████▋    | 566/1000 [18:26<16:19,  2.26s/it]
                                                  

 57%|█████▋    | 566/1000 [18:26<16:19,  2.26s/it]
 57%|█████▋    | 567/1000 [18:28<15:53,  2.20s/it]
                                                  

 57%|█████▋    | 567/1000 [18:28<15:53,  2.20s/it]
 57%|█████▋    | 568/1000 [18:30<15:43,  2.18s/it]
                                                  

 57%|█████▋    | 568/1000 [18:30<15:43,  2.18s/it]
 57%|█████▋    | 569/1000 [18:32<14:54,  2.07s/it]
                                                  

 57%|█████▋    | 569/1000 [18:32<14:54,  2.07s/it]
 57%|█████▋    | 570/1000 [18:33<14:08,  1.97s/it]
                                                  

 57%|█████▋    | 570/1000 [18:33<14:08,  1.97s/it]
 57%|█████▋    | 571/1000 [18:35<13:42,  1.92s/it]
                                                  

 57%|█████▋    | 571/1000 [18:35<13:42,  1.92s/it]
 57%|█████▋    | 572/1000 [18:37<13:25,  1.88s/it]
                                                  

 57%|█████▋    | 572/1000 [18:37<13:25,  1.88s/it]
 57%|█████▋    | 573/1000 [18:39<13:12,  1.85s/it]
                                                  

 57%|█████▋    | 573/1000 [18:39<13:12,  1.85s/it]
 57%|█████▋    | 574/1000 [18:41<13:10,  1.86s/it]
                                                  

 57%|█████▋    | 574/1000 [18:41<13:10,  1.86s/it]
 57%|█████▊    | 575/1000 [18:42<12:42,  1.79s/it]
                                                  

 57%|█████▊    | 575/1000 [18:42<12:42,  1.79s/it]
 58%|█████▊    | 576/1000 [18:44<12:05,  1.71s/it]
                                                  

 58%|█████▊    | 576/1000 [18:44<12:05,  1.71s/it]
 58%|█████▊    | 577/1000 [18:45<11:39,  1.65s/it]
                                                  

 58%|█████▊    | 577/1000 [18:45<11:39,  1.65s/it]
 58%|█████▊    | 578/1000 [18:47<11:19,  1.61s/it]
                                                  

 58%|█████▊    | 578/1000 [18:47<11:19,  1.61s/it]
 58%|█████▊    | 579/1000 [18:48<11:05,  1.58s/it]
                                                  

 58%|█████▊    | 579/1000 [18:48<11:05,  1.58s/it]
 58%|█████▊    | 580/1000 [18:50<10:56,  1.56s/it]
                                                  

 58%|█████▊    | 580/1000 [18:50<10:56,  1.56s/it]
 58%|█████▊    | 581/1000 [18:51<10:57,  1.57s/it]
                                                  

 58%|█████▊    | 581/1000 [18:51<10:57,  1.57s/it]
 58%|█████▊    | 582/1000 [18:53<10:52,  1.56s/it]
                                                  

 58%|█████▊    | 582/1000 [18:53<10:52,  1.56s/it]
 58%|█████▊    | 583/1000 [18:54<10:16,  1.48s/it]
                                                  

 58%|█████▊    | 583/1000 [18:54<10:16,  1.48s/it]
 58%|█████▊    | 584/1000 [18:55<09:42,  1.40s/it]
                                                  

 58%|█████▊    | 584/1000 [18:55<09:42,  1.40s/it]
 58%|█████▊    | 585/1000 [18:57<09:23,  1.36s/it]
                                                  

 58%|█████▊    | 585/1000 [18:57<09:23,  1.36s/it]
 59%|█████▊    | 586/1000 [18:58<09:07,  1.32s/it]
                                                  

 59%|█████▊    | 586/1000 [18:58<09:07,  1.32s/it]
 59%|█████▊    | 587/1000 [18:59<08:51,  1.29s/it]
                                                  

 59%|█████▊    | 587/1000 [18:59<08:51,  1.29s/it]
 59%|█████▉    | 588/1000 [19:00<08:41,  1.27s/it]
                                                  

 59%|█████▉    | 588/1000 [19:00<08:41,  1.27s/it]
 59%|█████▉    | 589/1000 [19:02<08:34,  1.25s/it]
                                                  

 59%|█████▉    | 589/1000 [19:02<08:34,  1.25s/it]
 59%|█████▉    | 590/1000 [19:03<08:30,  1.25s/it]
                                                  

 59%|█████▉    | 590/1000 [19:03<08:30,  1.25s/it]
 59%|█████▉    | 591/1000 [19:04<08:08,  1.19s/it]
                                                  

 59%|█████▉    | 591/1000 [19:04<08:08,  1.19s/it]
 59%|█████▉    | 592/1000 [19:05<07:37,  1.12s/it]
                                                  

 59%|█████▉    | 592/1000 [19:05<07:37,  1.12s/it]
 59%|█████▉    | 593/1000 [19:06<07:17,  1.07s/it]
                                                  

 59%|█████▉    | 593/1000 [19:06<07:17,  1.07s/it]
 59%|█████▉    | 594/1000 [19:07<06:58,  1.03s/it]
                                                  

 59%|█████▉    | 594/1000 [19:07<06:58,  1.03s/it]
 60%|█████▉    | 595/1000 [19:08<06:46,  1.00s/it]
                                                  

 60%|█████▉    | 595/1000 [19:08<06:46,  1.00s/it]
 60%|█████▉    | 596/1000 [19:09<06:35,  1.02it/s]
                                                  

 60%|█████▉    | 596/1000 [19:09<06:35,  1.02it/s]
 60%|█████▉    | 597/1000 [19:09<06:16,  1.07it/s]
                                                  

 60%|█████▉    | 597/1000 [19:09<06:16,  1.07it/s]
 60%|█████▉    | 598/1000 [19:10<05:45,  1.16it/s]
                                                  

 60%|█████▉    | 598/1000 [19:10<05:45,  1.16it/s]
 60%|█████▉    | 599/1000 [19:11<05:28,  1.22it/s]
                                                  

 60%|█████▉    | 599/1000 [19:11<05:28,  1.22it/s]
 60%|██████    | 600/1000 [19:13<08:22,  1.26s/it]
                                                  

 60%|██████    | 600/1000 [19:13<08:22,  1.26s/it]
 60%|██████    | 601/1000 [19:20<19:09,  2.88s/it]
                                                  

 60%|██████    | 601/1000 [19:20<19:09,  2.88s/it]
 60%|██████    | 602/1000 [19:23<20:30,  3.09s/it]
                                                  

 60%|██████    | 602/1000 [19:23<20:30,  3.09s/it]
 60%|██████    | 603/1000 [19:26<20:30,  3.10s/it]
                                                  

 60%|██████    | 603/1000 [19:26<20:30,  3.10s/it]
 60%|██████    | 604/1000 [19:29<19:40,  2.98s/it]
                                                  

 60%|██████    | 604/1000 [19:29<19:40,  2.98s/it]
 60%|██████    | 605/1000 [19:32<18:33,  2.82s/it]
                                                  

 60%|██████    | 605/1000 [19:32<18:33,  2.82s/it]
 61%|██████    | 606/1000 [19:34<17:27,  2.66s/it]
                                                  

 61%|██████    | 606/1000 [19:34<17:27,  2.66s/it]
 61%|██████    | 607/1000 [19:36<16:28,  2.51s/it]
                                                  

 61%|██████    | 607/1000 [19:36<16:28,  2.51s/it]
 61%|██████    | 608/1000 [19:38<15:33,  2.38s/it]
                                                  

 61%|██████    | 608/1000 [19:38<15:33,  2.38s/it]
 61%|██████    | 609/1000 [19:40<14:27,  2.22s/it]
                                                  

 61%|██████    | 609/1000 [19:40<14:27,  2.22s/it]
 61%|██████    | 610/1000 [19:42<13:28,  2.07s/it]
                                                  

 61%|██████    | 610/1000 [19:42<13:28,  2.07s/it]
 61%|██████    | 611/1000 [19:43<12:49,  1.98s/it]
                                                  

 61%|██████    | 611/1000 [19:43<12:49,  1.98s/it]
 61%|██████    | 612/1000 [19:45<12:15,  1.90s/it]
                                                  

 61%|██████    | 612/1000 [19:45<12:15,  1.90s/it]
 61%|██████▏   | 613/1000 [19:47<11:39,  1.81s/it]
                                                  

 61%|██████▏   | 613/1000 [19:47<11:39,  1.81s/it]
 61%|██████▏   | 614/1000 [19:48<11:07,  1.73s/it]
                                                  

 61%|██████▏   | 614/1000 [19:48<11:07,  1.73s/it]
 62%|██████▏   | 615/1000 [19:50<10:40,  1.66s/it]
                                                  

 62%|██████▏   | 615/1000 [19:50<10:40,  1.66s/it]
 62%|██████▏   | 616/1000 [19:51<10:06,  1.58s/it]
                                                  

 62%|██████▏   | 616/1000 [19:51<10:06,  1.58s/it]
 62%|██████▏   | 617/1000 [19:52<09:23,  1.47s/it]
                                                  

 62%|██████▏   | 617/1000 [19:52<09:23,  1.47s/it]
 62%|██████▏   | 618/1000 [19:54<08:52,  1.39s/it]
                                                  

 62%|██████▏   | 618/1000 [19:54<08:52,  1.39s/it]
 62%|██████▏   | 619/1000 [19:55<08:36,  1.35s/it]
                                                  

 62%|██████▏   | 619/1000 [19:55<08:36,  1.35s/it]
 62%|██████▏   | 620/1000 [19:56<08:16,  1.31s/it]
                                                  

 62%|██████▏   | 620/1000 [19:56<08:16,  1.31s/it]
 62%|██████▏   | 621/1000 [19:57<07:41,  1.22s/it]
                                                  

 62%|██████▏   | 621/1000 [19:57<07:41,  1.22s/it]
 62%|██████▏   | 622/1000 [19:58<07:17,  1.16s/it]
                                                  

 62%|██████▏   | 622/1000 [19:58<07:17,  1.16s/it]
 62%|██████▏   | 623/1000 [19:59<06:55,  1.10s/it]
                                                  

 62%|██████▏   | 623/1000 [19:59<06:55,  1.10s/it]
 62%|██████▏   | 624/1000 [20:00<06:11,  1.01it/s]
                                                  

 62%|██████▏   | 624/1000 [20:00<06:11,  1.01it/s]
 62%|██████▎   | 625/1000 [20:00<05:12,  1.20it/s]
                                                  

 62%|██████▎   | 625/1000 [20:00<05:12,  1.20it/s]
 63%|██████▎   | 626/1000 [20:14<28:53,  4.64s/it]
                                                  

 63%|██████▎   | 626/1000 [20:14<28:53,  4.64s/it]
 63%|██████▎   | 627/1000 [20:18<28:35,  4.60s/it]
                                                  

 63%|██████▎   | 627/1000 [20:18<28:35,  4.60s/it]
 63%|██████▎   | 628/1000 [20:22<26:51,  4.33s/it]
                                                  

 63%|██████▎   | 628/1000 [20:22<26:51,  4.33s/it]
 63%|██████▎   | 629/1000 [20:25<24:56,  4.03s/it]
                                                  

 63%|██████▎   | 629/1000 [20:25<24:56,  4.03s/it]
 63%|██████▎   | 630/1000 [20:28<23:12,  3.76s/it]
                                                  

 63%|██████▎   | 630/1000 [20:28<23:12,  3.76s/it]
 63%|██████▎   | 631/1000 [20:31<21:40,  3.52s/it]
                                                  

 63%|██████▎   | 631/1000 [20:31<21:40,  3.52s/it]
 63%|██████▎   | 632/1000 [20:34<20:11,  3.29s/it]
                                                  

 63%|██████▎   | 632/1000 [20:34<20:11,  3.29s/it]
 63%|██████▎   | 633/1000 [20:37<19:05,  3.12s/it]
                                                  

 63%|██████▎   | 633/1000 [20:37<19:05,  3.12s/it]
 63%|██████▎   | 634/1000 [20:39<17:58,  2.95s/it]
                                                  

 63%|██████▎   | 634/1000 [20:39<17:58,  2.95s/it]
 64%|██████▎   | 635/1000 [20:42<16:52,  2.78s/it]
                                                  

 64%|██████▎   | 635/1000 [20:42<16:52,  2.78s/it]
 64%|██████▎   | 636/1000 [20:44<16:07,  2.66s/it]
                                                  

 64%|██████▎   | 636/1000 [20:44<16:07,  2.66s/it]
 64%|██████▎   | 637/1000 [20:46<15:14,  2.52s/it]
                                                  

 64%|██████▎   | 637/1000 [20:46<15:14,  2.52s/it]
 64%|██████▍   | 638/1000 [20:48<14:20,  2.38s/it]
                                                  

 64%|██████▍   | 638/1000 [20:48<14:20,  2.38s/it]
 64%|██████▍   | 639/1000 [20:51<13:48,  2.30s/it]
                                                  

 64%|██████▍   | 639/1000 [20:51<13:48,  2.30s/it]
 64%|██████▍   | 640/1000 [20:53<13:20,  2.22s/it]
                                                  

 64%|██████▍   | 640/1000 [20:53<13:20,  2.22s/it]
 64%|██████▍   | 641/1000 [20:55<13:01,  2.18s/it]
                                                  

 64%|██████▍   | 641/1000 [20:55<13:01,  2.18s/it]
 64%|██████▍   | 642/1000 [20:57<12:59,  2.18s/it]
                                                  

 64%|██████▍   | 642/1000 [20:57<12:59,  2.18s/it]
 64%|██████▍   | 643/1000 [20:59<12:18,  2.07s/it]
                                                  

 64%|██████▍   | 643/1000 [20:59<12:18,  2.07s/it]
 64%|██████▍   | 644/1000 [21:00<11:47,  1.99s/it]
                                                  

 64%|██████▍   | 644/1000 [21:00<11:47,  1.99s/it]
 64%|██████▍   | 645/1000 [21:02<11:19,  1.91s/it]
                                                  

 64%|██████▍   | 645/1000 [21:02<11:19,  1.91s/it]
 65%|██████▍   | 646/1000 [21:04<11:04,  1.88s/it]
                                                  

 65%|██████▍   | 646/1000 [21:04<11:04,  1.88s/it]
 65%|██████▍   | 647/1000 [21:06<10:50,  1.84s/it]
                                                  

 65%|██████▍   | 647/1000 [21:06<10:50,  1.84s/it]
 65%|██████▍   | 648/1000 [21:08<10:46,  1.84s/it]
                                                  

 65%|██████▍   | 648/1000 [21:08<10:46,  1.84s/it]
 65%|██████▍   | 649/1000 [21:09<10:32,  1.80s/it]
                                                  

 65%|██████▍   | 649/1000 [21:09<10:32,  1.80s/it]
 65%|██████▌   | 650/1000 [21:11<10:02,  1.72s/it]
                                                  

 65%|██████▌   | 650/1000 [21:11<10:02,  1.72s/it]
 65%|██████▌   | 651/1000 [21:12<09:35,  1.65s/it]
                                                  

 65%|██████▌   | 651/1000 [21:12<09:35,  1.65s/it]
 65%|██████▌   | 652/1000 [21:14<09:16,  1.60s/it]
                                                  

 65%|██████▌   | 652/1000 [21:14<09:16,  1.60s/it]
 65%|██████▌   | 653/1000 [21:15<09:04,  1.57s/it]
                                                  

 65%|██████▌   | 653/1000 [21:15<09:04,  1.57s/it]
 65%|██████▌   | 654/1000 [21:17<08:53,  1.54s/it]
                                                  

 65%|██████▌   | 654/1000 [21:17<08:53,  1.54s/it]
 66%|██████▌   | 655/1000 [21:18<08:46,  1.53s/it]
                                                  

 66%|██████▌   | 655/1000 [21:18<08:46,  1.53s/it]
 66%|██████▌   | 656/1000 [21:20<08:40,  1.51s/it]
                                                  

 66%|██████▌   | 656/1000 [21:20<08:40,  1.51s/it]
 66%|██████▌   | 657/1000 [21:21<08:31,  1.49s/it]
                                                  

 66%|██████▌   | 657/1000 [21:21<08:31,  1.49s/it]
 66%|██████▌   | 658/1000 [21:22<08:06,  1.42s/it]
                                                  

 66%|██████▌   | 658/1000 [21:22<08:06,  1.42s/it]
 66%|██████▌   | 659/1000 [21:24<07:47,  1.37s/it]
                                                  

 66%|██████▌   | 659/1000 [21:24<07:47,  1.37s/it]
 66%|██████▌   | 660/1000 [21:25<07:30,  1.32s/it]
                                                  

 66%|██████▌   | 660/1000 [21:25<07:30,  1.32s/it]
 66%|██████▌   | 661/1000 [21:26<07:18,  1.29s/it]
                                                  

 66%|██████▌   | 661/1000 [21:26<07:18,  1.29s/it]
 66%|██████▌   | 662/1000 [21:27<07:11,  1.28s/it]
                                                  

 66%|██████▌   | 662/1000 [21:27<07:11,  1.28s/it]
 66%|██████▋   | 663/1000 [21:29<07:07,  1.27s/it]
                                                  

 66%|██████▋   | 663/1000 [21:29<07:07,  1.27s/it]
 66%|██████▋   | 664/1000 [21:30<07:00,  1.25s/it]
                                                  

 66%|██████▋   | 664/1000 [21:30<07:00,  1.25s/it]
 66%|██████▋   | 665/1000 [21:31<06:52,  1.23s/it]
                                                  

 66%|██████▋   | 665/1000 [21:31<06:52,  1.23s/it]
 67%|██████▋   | 666/1000 [21:32<06:27,  1.16s/it]
                                                  

 67%|██████▋   | 666/1000 [21:32<06:27,  1.16s/it]
 67%|██████▋   | 667/1000 [21:33<06:04,  1.09s/it]
                                                  

 67%|██████▋   | 667/1000 [21:33<06:04,  1.09s/it]
 67%|██████▋   | 668/1000 [21:34<05:46,  1.04s/it]
                                                  

 67%|██████▋   | 668/1000 [21:34<05:46,  1.04s/it]
 67%|██████▋   | 669/1000 [21:35<05:33,  1.01s/it]
                                                  

 67%|██████▋   | 669/1000 [21:35<05:33,  1.01s/it]
 67%|██████▋   | 670/1000 [21:36<05:24,  1.02it/s]
                                                  

 67%|██████▋   | 670/1000 [21:36<05:24,  1.02it/s]
 67%|██████▋   | 671/1000 [21:37<05:22,  1.02it/s]
                                                  

 67%|██████▋   | 671/1000 [21:37<05:22,  1.02it/s]
 67%|██████▋   | 672/1000 [21:37<05:02,  1.08it/s]
                                                  

 67%|██████▋   | 672/1000 [21:38<05:02,  1.08it/s]
 67%|██████▋   | 673/1000 [21:38<04:37,  1.18it/s]
                                                  

 67%|██████▋   | 673/1000 [21:38<04:37,  1.18it/s]
 67%|██████▋   | 674/1000 [21:39<04:19,  1.26it/s]
                                                  

 67%|██████▋   | 674/1000 [21:39<04:19,  1.26it/s]
 68%|██████▊   | 675/1000 [21:41<07:10,  1.33s/it]
                                                  

 68%|██████▊   | 675/1000 [21:41<07:10,  1.33s/it]
 68%|██████▊   | 676/1000 [21:48<15:43,  2.91s/it]
                                                  

 68%|██████▊   | 676/1000 [21:48<15:43,  2.91s/it]
 68%|██████▊   | 677/1000 [21:52<17:39,  3.28s/it]
                                                  

 68%|██████▊   | 677/1000 [21:52<17:39,  3.28s/it]
 68%|██████▊   | 678/1000 [21:56<18:06,  3.37s/it]
                                                  

 68%|██████▊   | 678/1000 [21:56<18:06,  3.37s/it]
 68%|██████▊   | 679/1000 [21:59<17:57,  3.36s/it]
                                                  

 68%|██████▊   | 679/1000 [21:59<17:57,  3.36s/it]
 68%|██████▊   | 680/1000 [22:02<17:23,  3.26s/it]
                                                  

 68%|██████▊   | 680/1000 [22:02<17:23,  3.26s/it]
 68%|██████▊   | 681/1000 [22:05<16:51,  3.17s/it]
                                                  

 68%|██████▊   | 681/1000 [22:05<16:51,  3.17s/it]
 68%|██████▊   | 682/1000 [22:08<16:08,  3.05s/it]
                                                  

 68%|██████▊   | 682/1000 [22:08<16:08,  3.05s/it]
 68%|██████▊   | 683/1000 [22:11<15:33,  2.95s/it]
                                                  

 68%|██████▊   | 683/1000 [22:11<15:33,  2.95s/it]
 68%|██████▊   | 684/1000 [22:13<14:59,  2.85s/it]
                                                  

 68%|██████▊   | 684/1000 [22:13<14:59,  2.85s/it]
 68%|██████▊   | 685/1000 [22:16<14:16,  2.72s/it]
                                                  

 68%|██████▊   | 685/1000 [22:16<14:16,  2.72s/it]
 69%|██████▊   | 686/1000 [22:18<13:39,  2.61s/it]
                                                  

 69%|██████▊   | 686/1000 [22:18<13:39,  2.61s/it]
 69%|██████▊   | 687/1000 [22:20<13:18,  2.55s/it]
                                                  

 69%|██████▊   | 687/1000 [22:20<13:18,  2.55s/it]
 69%|██████▉   | 688/1000 [22:23<12:48,  2.46s/it]
                                                  

 69%|██████▉   | 688/1000 [22:23<12:48,  2.46s/it]
 69%|██████▉   | 689/1000 [22:25<12:09,  2.34s/it]
                                                  

 69%|██████▉   | 689/1000 [22:25<12:09,  2.34s/it]
 69%|██████▉   | 690/1000 [22:27<11:43,  2.27s/it]
                                                  

 69%|██████▉   | 690/1000 [22:27<11:43,  2.27s/it]
 69%|██████▉   | 691/1000 [22:29<11:23,  2.21s/it]
                                                  

 69%|██████▉   | 691/1000 [22:29<11:23,  2.21s/it]
 69%|██████▉   | 692/1000 [22:31<11:12,  2.18s/it]
                                                  

 69%|██████▉   | 692/1000 [22:31<11:12,  2.18s/it]
 69%|██████▉   | 693/1000 [22:33<10:49,  2.12s/it]
                                                  

 69%|██████▉   | 693/1000 [22:33<10:49,  2.12s/it]
 69%|██████▉   | 694/1000 [22:35<10:16,  2.01s/it]
                                                  

 69%|██████▉   | 694/1000 [22:35<10:16,  2.01s/it]
 70%|██████▉   | 695/1000 [22:36<09:48,  1.93s/it]
                                                  

 70%|██████▉   | 695/1000 [22:36<09:48,  1.93s/it]
 70%|██████▉   | 696/1000 [22:38<09:30,  1.88s/it]
                                                  

 70%|██████▉   | 696/1000 [22:38<09:30,  1.88s/it]
 70%|██████▉   | 697/1000 [22:40<09:16,  1.84s/it]
                                                  

 70%|██████▉   | 697/1000 [22:40<09:16,  1.84s/it]
 70%|██████▉   | 698/1000 [22:42<09:06,  1.81s/it]
                                                  

 70%|██████▉   | 698/1000 [22:42<09:06,  1.81s/it]
 70%|██████▉   | 699/1000 [22:43<08:57,  1.79s/it]
                                                  

 70%|██████▉   | 699/1000 [22:43<08:57,  1.79s/it]
 70%|███████   | 700/1000 [22:45<08:45,  1.75s/it]
                                                  

 70%|███████   | 700/1000 [22:45<08:45,  1.75s/it]
 70%|███████   | 701/1000 [22:47<08:22,  1.68s/it]
                                                  

 70%|███████   | 701/1000 [22:47<08:22,  1.68s/it]
 70%|███████   | 702/1000 [22:48<08:03,  1.62s/it]
                                                  

 70%|███████   | 702/1000 [22:48<08:03,  1.62s/it]
 70%|███████   | 703/1000 [22:50<07:51,  1.59s/it]
                                                  

 70%|███████   | 703/1000 [22:50<07:51,  1.59s/it]
 70%|███████   | 704/1000 [22:51<07:40,  1.56s/it]
                                                  

 70%|███████   | 704/1000 [22:51<07:40,  1.56s/it]
 70%|███████   | 705/1000 [22:53<07:31,  1.53s/it]
                                                  

 70%|███████   | 705/1000 [22:53<07:31,  1.53s/it]
 71%|███████   | 706/1000 [22:54<07:25,  1.51s/it]
                                                  

 71%|███████   | 706/1000 [22:54<07:25,  1.51s/it]
 71%|███████   | 707/1000 [22:55<07:19,  1.50s/it]
                                                  

 71%|███████   | 707/1000 [22:55<07:19,  1.50s/it]
 71%|███████   | 708/1000 [22:57<06:57,  1.43s/it]
                                                  

 71%|███████   | 708/1000 [22:57<06:57,  1.43s/it]
 71%|███████   | 709/1000 [22:58<06:38,  1.37s/it]
                                                  

 71%|███████   | 709/1000 [22:58<06:38,  1.37s/it]
 71%|███████   | 710/1000 [22:59<06:23,  1.32s/it]
                                                  

 71%|███████   | 710/1000 [22:59<06:23,  1.32s/it]
 71%|███████   | 711/1000 [23:00<06:16,  1.30s/it]
                                                  

 71%|███████   | 711/1000 [23:00<06:16,  1.30s/it]
 71%|███████   | 712/1000 [23:02<06:07,  1.28s/it]
                                                  

 71%|███████   | 712/1000 [23:02<06:07,  1.28s/it]
 71%|███████▏  | 713/1000 [23:03<06:01,  1.26s/it]
                                                  

 71%|███████▏  | 713/1000 [23:03<06:01,  1.26s/it]
 71%|███████▏  | 714/1000 [23:04<05:56,  1.24s/it]
                                                  

 71%|███████▏  | 714/1000 [23:04<05:56,  1.24s/it]
 72%|███████▏  | 715/1000 [23:05<05:55,  1.25s/it]
                                                  

 72%|███████▏  | 715/1000 [23:05<05:55,  1.25s/it]
 72%|███████▏  | 716/1000 [23:06<05:39,  1.19s/it]
                                                  

 72%|███████▏  | 716/1000 [23:06<05:39,  1.19s/it]
 72%|███████▏  | 717/1000 [23:07<05:17,  1.12s/it]
                                                  

 72%|███████▏  | 717/1000 [23:07<05:17,  1.12s/it]
 72%|███████▏  | 718/1000 [23:08<05:00,  1.06s/it]
                                                  

 72%|███████▏  | 718/1000 [23:08<05:00,  1.06s/it]
 72%|███████▏  | 719/1000 [23:09<04:47,  1.02s/it]
                                                  

 72%|███████▏  | 719/1000 [23:09<04:47,  1.02s/it]
 72%|███████▏  | 720/1000 [23:10<04:39,  1.00it/s]
                                                  

 72%|███████▏  | 720/1000 [23:10<04:39,  1.00it/s]
 72%|███████▏  | 721/1000 [23:11<04:34,  1.02it/s]
                                                  

 72%|███████▏  | 721/1000 [23:11<04:34,  1.02it/s]
 72%|███████▏  | 722/1000 [23:12<04:17,  1.08it/s]
                                                  

 72%|███████▏  | 722/1000 [23:12<04:17,  1.08it/s]
 72%|███████▏  | 723/1000 [23:13<03:55,  1.17it/s]
                                                  

 72%|███████▏  | 723/1000 [23:13<03:55,  1.17it/s]
 72%|███████▏  | 724/1000 [23:13<03:39,  1.26it/s]
                                                  

 72%|███████▏  | 724/1000 [23:13<03:39,  1.26it/s]
 72%|███████▎  | 725/1000 [23:16<06:55,  1.51s/it]
                                                  

 72%|███████▎  | 725/1000 [23:16<06:55,  1.51s/it]
 73%|███████▎  | 726/1000 [23:28<20:06,  4.40s/it]
                                                  

 73%|███████▎  | 726/1000 [23:28<20:06,  4.40s/it]
 73%|███████▎  | 727/1000 [23:32<20:15,  4.45s/it]
                                                  

 73%|███████▎  | 727/1000 [23:32<20:15,  4.45s/it]
 73%|███████▎  | 728/1000 [23:36<19:13,  4.24s/it]
                                                  

 73%|███████▎  | 728/1000 [23:36<19:13,  4.24s/it]
 73%|███████▎  | 729/1000 [23:39<18:03,  4.00s/it]
                                                  

 73%|███████▎  | 729/1000 [23:39<18:03,  4.00s/it]
 73%|███████▎  | 730/1000 [23:42<16:42,  3.71s/it]
                                                  

 73%|███████▎  | 730/1000 [23:42<16:42,  3.71s/it]
 73%|███████▎  | 731/1000 [23:45<15:31,  3.46s/it]
                                                  

 73%|███████▎  | 731/1000 [23:45<15:31,  3.46s/it]
 73%|███████▎  | 732/1000 [23:48<14:24,  3.22s/it]
                                                  

 73%|███████▎  | 732/1000 [23:48<14:24,  3.22s/it]
 73%|███████▎  | 733/1000 [23:50<13:26,  3.02s/it]
                                                  

 73%|███████▎  | 733/1000 [23:50<13:26,  3.02s/it]
 73%|███████▎  | 734/1000 [23:53<12:29,  2.82s/it]
                                                  

 73%|███████▎  | 734/1000 [23:53<12:29,  2.82s/it]
 74%|███████▎  | 735/1000 [23:55<11:49,  2.68s/it]
                                                  

 74%|███████▎  | 735/1000 [23:55<11:49,  2.68s/it]
 74%|███████▎  | 736/1000 [23:57<11:20,  2.58s/it]
                                                  

 74%|███████▎  | 736/1000 [23:58<11:20,  2.58s/it]
 74%|███████▎  | 737/1000 [24:00<10:42,  2.44s/it]
                                                  

 74%|███████▎  | 737/1000 [24:00<10:42,  2.44s/it]
 74%|███████▍  | 738/1000 [24:02<10:09,  2.33s/it]
                                                  

 74%|███████▍  | 738/1000 [24:02<10:09,  2.33s/it]
 74%|███████▍  | 739/1000 [24:04<09:47,  2.25s/it]
                                                  

 74%|███████▍  | 739/1000 [24:04<09:47,  2.25s/it]
 74%|███████▍  | 740/1000 [24:06<09:32,  2.20s/it]
                                                  

 74%|███████▍  | 740/1000 [24:06<09:32,  2.20s/it]
 74%|███████▍  | 741/1000 [24:08<09:11,  2.13s/it]
                                                  

 74%|███████▍  | 741/1000 [24:08<09:11,  2.13s/it]
 74%|███████▍  | 742/1000 [24:10<08:40,  2.02s/it]
                                                  

 74%|███████▍  | 742/1000 [24:10<08:40,  2.02s/it]
 74%|███████▍  | 743/1000 [24:11<08:16,  1.93s/it]
                                                  

 74%|███████▍  | 743/1000 [24:11<08:16,  1.93s/it]
 74%|███████▍  | 744/1000 [24:13<08:03,  1.89s/it]
                                                  

 74%|███████▍  | 744/1000 [24:13<08:03,  1.89s/it]
 74%|███████▍  | 745/1000 [24:15<07:50,  1.84s/it]
                                                  

 74%|███████▍  | 745/1000 [24:15<07:50,  1.84s/it]
 75%|███████▍  | 746/1000 [24:17<07:43,  1.83s/it]
                                                  

 75%|███████▍  | 746/1000 [24:17<07:43,  1.83s/it]
 75%|███████▍  | 747/1000 [24:18<07:39,  1.81s/it]
                                                  

 75%|███████▍  | 747/1000 [24:18<07:39,  1.81s/it]
 75%|███████▍  | 748/1000 [24:20<07:15,  1.73s/it]
                                                  

 75%|███████▍  | 748/1000 [24:20<07:15,  1.73s/it]
 75%|███████▍  | 749/1000 [24:21<06:55,  1.66s/it]
                                                  

 75%|███████▍  | 749/1000 [24:21<06:55,  1.66s/it]
 75%|███████▌  | 750/1000 [24:23<06:41,  1.61s/it]
                                                  

 75%|███████▌  | 750/1000 [24:23<06:41,  1.61s/it]
 75%|███████▌  | 751/1000 [24:24<06:30,  1.57s/it]
                                                  

 75%|███████▌  | 751/1000 [24:24<06:30,  1.57s/it]
 75%|███████▌  | 752/1000 [24:26<06:22,  1.54s/it]
                                                  

 75%|███████▌  | 752/1000 [24:26<06:22,  1.54s/it]
 75%|███████▌  | 753/1000 [24:27<06:17,  1.53s/it]
                                                  

 75%|███████▌  | 753/1000 [24:27<06:17,  1.53s/it]
 75%|███████▌  | 754/1000 [24:29<06:44,  1.64s/it]
                                                  

 75%|███████▌  | 754/1000 [24:29<06:44,  1.64s/it]
 76%|███████▌  | 755/1000 [24:31<06:31,  1.60s/it]
                                                  

 76%|███████▌  | 755/1000 [24:31<06:31,  1.60s/it]
 76%|███████▌  | 756/1000 [24:32<06:14,  1.53s/it]
                                                  

 76%|███████▌  | 756/1000 [24:32<06:14,  1.53s/it]
 76%|███████▌  | 757/1000 [24:33<05:49,  1.44s/it]
                                                  

 76%|███████▌  | 757/1000 [24:33<05:49,  1.44s/it]
 76%|███████▌  | 758/1000 [24:35<05:31,  1.37s/it]
                                                  

 76%|███████▌  | 758/1000 [24:35<05:31,  1.37s/it]
 76%|███████▌  | 759/1000 [24:36<05:19,  1.33s/it]
                                                  

 76%|███████▌  | 759/1000 [24:36<05:19,  1.33s/it]
 76%|███████▌  | 760/1000 [24:37<05:10,  1.29s/it]
                                                  

 76%|███████▌  | 760/1000 [24:37<05:10,  1.29s/it]
 76%|███████▌  | 761/1000 [24:38<05:03,  1.27s/it]
                                                  

 76%|███████▌  | 761/1000 [24:38<05:03,  1.27s/it]
 76%|███████▌  | 762/1000 [24:39<05:00,  1.26s/it]
                                                  

 76%|███████▌  | 762/1000 [24:39<05:00,  1.26s/it]
 76%|███████▋  | 763/1000 [24:41<04:59,  1.26s/it]
                                                  

 76%|███████▋  | 763/1000 [24:41<04:59,  1.26s/it]
 76%|███████▋  | 764/1000 [24:42<04:53,  1.24s/it]
                                                  

 76%|███████▋  | 764/1000 [24:42<04:53,  1.24s/it]
 76%|███████▋  | 765/1000 [24:43<04:34,  1.17s/it]
                                                  

 76%|███████▋  | 765/1000 [24:43<04:34,  1.17s/it]
 77%|███████▋  | 766/1000 [24:44<04:16,  1.10s/it]
                                                  

 77%|███████▋  | 766/1000 [24:44<04:16,  1.10s/it]
 77%|███████▋  | 767/1000 [24:45<04:04,  1.05s/it]
                                                  

 77%|███████▋  | 767/1000 [24:45<04:04,  1.05s/it]
 77%|███████▋  | 768/1000 [24:46<03:55,  1.01s/it]
                                                  

 77%|███████▋  | 768/1000 [24:46<03:55,  1.01s/it]
 77%|███████▋  | 769/1000 [24:47<03:48,  1.01it/s]
                                                  

 77%|███████▋  | 769/1000 [24:47<03:48,  1.01it/s]
 77%|███████▋  | 770/1000 [24:48<03:43,  1.03it/s]
                                                  

 77%|███████▋  | 770/1000 [24:48<03:43,  1.03it/s]
 77%|███████▋  | 771/1000 [24:48<03:32,  1.08it/s]
                                                  

 77%|███████▋  | 771/1000 [24:48<03:32,  1.08it/s]
 77%|███████▋  | 772/1000 [24:49<03:14,  1.17it/s]
                                                  

 77%|███████▋  | 772/1000 [24:49<03:14,  1.17it/s]
 77%|███████▋  | 773/1000 [24:50<03:01,  1.25it/s]
                                                  

 77%|███████▋  | 773/1000 [24:50<03:01,  1.25it/s]
 77%|███████▋  | 774/1000 [24:50<02:52,  1.31it/s]
                                                  

 77%|███████▋  | 774/1000 [24:50<02:52,  1.31it/s]
 78%|███████▊  | 775/1000 [24:53<04:59,  1.33s/it]
                                                  

 78%|███████▊  | 775/1000 [24:53<04:59,  1.33s/it]
 78%|███████▊  | 776/1000 [25:00<11:44,  3.14s/it]
                                                  

 78%|███████▊  | 776/1000 [25:00<11:44,  3.14s/it]
 78%|███████▊  | 777/1000 [25:05<13:22,  3.60s/it]
                                                  

 78%|███████▊  | 777/1000 [25:05<13:22,  3.60s/it]
 78%|███████▊  | 778/1000 [25:09<13:38,  3.69s/it]
                                                  

 78%|███████▊  | 778/1000 [25:09<13:38,  3.69s/it]
 78%|███████▊  | 779/1000 [25:12<13:20,  3.62s/it]
                                                  

 78%|███████▊  | 779/1000 [25:13<13:20,  3.62s/it]
 78%|███████▊  | 780/1000 [25:16<12:48,  3.49s/it]
                                                  

 78%|███████▊  | 780/1000 [25:16<12:48,  3.49s/it]
 78%|███████▊  | 781/1000 [25:19<12:04,  3.31s/it]
                                                  

 78%|███████▊  | 781/1000 [25:19<12:04,  3.31s/it]
 78%|███████▊  | 782/1000 [25:21<11:24,  3.14s/it]
                                                  

 78%|███████▊  | 782/1000 [25:21<11:24,  3.14s/it]
 78%|███████▊  | 783/1000 [25:24<10:51,  3.00s/it]
                                                  

 78%|███████▊  | 783/1000 [25:24<10:51,  3.00s/it]
 78%|███████▊  | 784/1000 [25:27<10:18,  2.86s/it]
                                                  

 78%|███████▊  | 784/1000 [25:27<10:18,  2.86s/it]
 78%|███████▊  | 785/1000 [25:29<09:42,  2.71s/it]
                                                  

 78%|███████▊  | 785/1000 [25:29<09:42,  2.71s/it]
 79%|███████▊  | 786/1000 [25:31<09:17,  2.60s/it]
                                                  

 79%|███████▊  | 786/1000 [25:31<09:17,  2.60s/it]
 79%|███████▊  | 787/1000 [25:34<08:53,  2.51s/it]
                                                  

 79%|███████▊  | 787/1000 [25:34<08:53,  2.51s/it]
 79%|███████▉  | 788/1000 [25:36<08:26,  2.39s/it]
                                                  

 79%|███████▉  | 788/1000 [25:36<08:26,  2.39s/it]
 79%|███████▉  | 789/1000 [25:38<08:07,  2.31s/it]
                                                  

 79%|███████▉  | 789/1000 [25:38<08:07,  2.31s/it]
 79%|███████▉  | 790/1000 [25:40<07:53,  2.26s/it]
                                                  

 79%|███████▉  | 790/1000 [25:40<07:53,  2.26s/it]
 79%|███████▉  | 791/1000 [25:42<07:38,  2.19s/it]
                                                  

 79%|███████▉  | 791/1000 [25:42<07:38,  2.19s/it]
 79%|███████▉  | 792/1000 [25:44<07:23,  2.13s/it]
                                                  

 79%|███████▉  | 792/1000 [25:44<07:23,  2.13s/it]
 79%|███████▉  | 793/1000 [25:46<07:04,  2.05s/it]
                                                  

 79%|███████▉  | 793/1000 [25:46<07:04,  2.05s/it]
 79%|███████▉  | 794/1000 [25:47<06:42,  1.95s/it]
                                                  

 79%|███████▉  | 794/1000 [25:48<06:42,  1.95s/it]
 80%|███████▉  | 795/1000 [25:49<06:26,  1.89s/it]
                                                  

 80%|███████▉  | 795/1000 [25:49<06:26,  1.89s/it]
 80%|███████▉  | 796/1000 [25:51<06:16,  1.85s/it]
                                                  

 80%|███████▉  | 796/1000 [25:51<06:16,  1.85s/it]
 80%|███████▉  | 797/1000 [25:53<06:08,  1.81s/it]
                                                  

 80%|███████▉  | 797/1000 [25:53<06:08,  1.81s/it]
 80%|███████▉  | 798/1000 [25:54<06:02,  1.79s/it]
                                                  

 80%|███████▉  | 798/1000 [25:54<06:02,  1.79s/it]
 80%|███████▉  | 799/1000 [25:56<05:56,  1.77s/it]
                                                  

 80%|███████▉  | 799/1000 [25:56<05:56,  1.77s/it]
 80%|████████  | 800/1000 [25:58<05:39,  1.70s/it]
                                                  

 80%|████████  | 800/1000 [25:58<05:39,  1.70s/it]
 80%|████████  | 801/1000 [25:59<05:24,  1.63s/it]
                                                  

 80%|████████  | 801/1000 [25:59<05:24,  1.63s/it]
 80%|████████  | 802/1000 [26:01<05:13,  1.58s/it]
                                                  

 80%|████████  | 802/1000 [26:01<05:13,  1.58s/it]
 80%|████████  | 803/1000 [26:02<05:05,  1.55s/it]
                                                  

 80%|████████  | 803/1000 [26:02<05:05,  1.55s/it]
 80%|████████  | 804/1000 [26:04<04:59,  1.53s/it]
                                                  

 80%|████████  | 804/1000 [26:04<04:59,  1.53s/it]
 80%|████████  | 805/1000 [26:05<04:55,  1.51s/it]
                                                  

 80%|████████  | 805/1000 [26:05<04:55,  1.51s/it]
 81%|████████  | 806/1000 [26:07<04:51,  1.50s/it]
                                                  

 81%|████████  | 806/1000 [26:07<04:51,  1.50s/it]
 81%|████████  | 807/1000 [26:08<04:46,  1.48s/it]
                                                  

 81%|████████  | 807/1000 [26:08<04:46,  1.48s/it]
 81%|████████  | 808/1000 [26:09<04:35,  1.44s/it]
                                                  

 81%|████████  | 808/1000 [26:09<04:35,  1.44s/it]
 81%|████████  | 809/1000 [26:11<04:21,  1.37s/it]
                                                  

 81%|████████  | 809/1000 [26:11<04:21,  1.37s/it]
 81%|████████  | 810/1000 [26:12<04:11,  1.32s/it]
                                                  

 81%|████████  | 810/1000 [26:12<04:11,  1.32s/it]
 81%|████████  | 811/1000 [26:13<04:04,  1.29s/it]
                                                  

 81%|████████  | 811/1000 [26:13<04:04,  1.29s/it]
 81%|████████  | 812/1000 [26:14<03:58,  1.27s/it]
                                                  

 81%|████████  | 812/1000 [26:14<03:58,  1.27s/it]
 81%|████████▏ | 813/1000 [26:15<03:55,  1.26s/it]
                                                  

 81%|████████▏ | 813/1000 [26:15<03:55,  1.26s/it]
 81%|████████▏ | 814/1000 [26:17<03:53,  1.25s/it]
                                                  

 81%|████████▏ | 814/1000 [26:17<03:53,  1.25s/it]
 82%|████████▏ | 815/1000 [26:18<03:50,  1.24s/it]
                                                  

 82%|████████▏ | 815/1000 [26:18<03:50,  1.24s/it]
 82%|████████▏ | 816/1000 [26:19<03:39,  1.19s/it]
                                                  

 82%|████████▏ | 816/1000 [26:19<03:39,  1.19s/it]
 82%|████████▏ | 817/1000 [26:20<03:24,  1.11s/it]
                                                  

 82%|████████▏ | 817/1000 [26:20<03:24,  1.11s/it]
 82%|████████▏ | 818/1000 [26:21<03:12,  1.06s/it]
                                                  

 82%|████████▏ | 818/1000 [26:21<03:12,  1.06s/it]
 82%|████████▏ | 819/1000 [26:22<03:04,  1.02s/it]
                                                  

 82%|████████▏ | 819/1000 [26:22<03:04,  1.02s/it]
 82%|████████▏ | 820/1000 [26:23<02:58,  1.01it/s]
                                                  

 82%|████████▏ | 820/1000 [26:23<02:58,  1.01it/s]
 82%|████████▏ | 821/1000 [26:24<02:55,  1.02it/s]
                                                  

 82%|████████▏ | 821/1000 [26:24<02:55,  1.02it/s]
 82%|████████▏ | 822/1000 [26:24<02:43,  1.09it/s]
                                                  

 82%|████████▏ | 822/1000 [26:24<02:43,  1.09it/s]
 82%|████████▏ | 823/1000 [26:25<02:29,  1.19it/s]
                                                  

 82%|████████▏ | 823/1000 [26:25<02:29,  1.19it/s]
 82%|████████▏ | 824/1000 [26:26<02:19,  1.26it/s]
                                                  

 82%|████████▏ | 824/1000 [26:26<02:19,  1.26it/s]
 82%|████████▎ | 825/1000 [26:28<03:50,  1.32s/it]
                                                  

 82%|████████▎ | 825/1000 [26:28<03:50,  1.32s/it]
 83%|████████▎ | 826/1000 [26:35<08:50,  3.05s/it]
                                                  

 83%|████████▎ | 826/1000 [26:35<08:50,  3.05s/it]
 83%|████████▎ | 827/1000 [26:40<09:50,  3.41s/it]
                                                  

 83%|████████▎ | 827/1000 [26:40<09:50,  3.41s/it]
 83%|████████▎ | 828/1000 [26:43<09:59,  3.48s/it]
                                                  

 83%|████████▎ | 828/1000 [26:43<09:59,  3.48s/it]
 83%|████████▎ | 829/1000 [26:47<09:51,  3.46s/it]
                                                  

 83%|████████▎ | 829/1000 [26:47<09:51,  3.46s/it]
 83%|████████▎ | 830/1000 [26:50<09:25,  3.33s/it]
                                                  

 83%|████████▎ | 830/1000 [26:50<09:25,  3.33s/it]
 83%|████████▎ | 831/1000 [26:53<08:57,  3.18s/it]
                                                  

 83%|████████▎ | 831/1000 [26:53<08:57,  3.18s/it]
 83%|████████▎ | 832/1000 [26:55<08:30,  3.04s/it]
                                                  

 83%|████████▎ | 832/1000 [26:55<08:30,  3.04s/it]
 83%|████████▎ | 833/1000 [26:58<08:04,  2.90s/it]
                                                  

 83%|████████▎ | 833/1000 [26:58<08:04,  2.90s/it]
 83%|████████▎ | 834/1000 [27:00<07:34,  2.74s/it]
                                                  

 83%|████████▎ | 834/1000 [27:00<07:34,  2.74s/it]
 84%|████████▎ | 835/1000 [27:03<07:14,  2.63s/it]
                                                  

 84%|████████▎ | 835/1000 [27:03<07:14,  2.63s/it]
 84%|████████▎ | 836/1000 [27:05<06:59,  2.56s/it]
                                                  

 84%|████████▎ | 836/1000 [27:05<06:59,  2.56s/it]
 84%|████████▎ | 837/1000 [27:07<06:40,  2.46s/it]
                                                  

 84%|████████▎ | 837/1000 [27:07<06:40,  2.46s/it]
 84%|████████▍ | 838/1000 [27:09<06:21,  2.35s/it]
                                                  

 84%|████████▍ | 838/1000 [27:09<06:21,  2.35s/it]
 84%|████████▍ | 839/1000 [27:11<06:05,  2.27s/it]
                                                  

 84%|████████▍ | 839/1000 [27:11<06:05,  2.27s/it]
 84%|████████▍ | 840/1000 [27:13<05:53,  2.21s/it]
                                                  

 84%|████████▍ | 840/1000 [27:13<05:53,  2.21s/it]
 84%|████████▍ | 841/1000 [27:16<05:45,  2.18s/it]
                                                  

 84%|████████▍ | 841/1000 [27:16<05:45,  2.18s/it]
 84%|████████▍ | 842/1000 [27:17<05:31,  2.10s/it]
                                                  

 84%|████████▍ | 842/1000 [27:17<05:31,  2.10s/it]
 84%|████████▍ | 843/1000 [27:19<05:12,  1.99s/it]
                                                  

 84%|████████▍ | 843/1000 [27:19<05:12,  1.99s/it]
 84%|████████▍ | 844/1000 [27:21<05:00,  1.93s/it]
                                                  

 84%|████████▍ | 844/1000 [27:21<05:00,  1.93s/it]
 84%|████████▍ | 845/1000 [27:23<04:49,  1.87s/it]
                                                  

 84%|████████▍ | 845/1000 [27:23<04:49,  1.87s/it]
 85%|████████▍ | 846/1000 [27:24<04:41,  1.83s/it]
                                                  

 85%|████████▍ | 846/1000 [27:24<04:41,  1.83s/it]
 85%|████████▍ | 847/1000 [27:26<04:37,  1.82s/it]
                                                  

 85%|████████▍ | 847/1000 [27:26<04:37,  1.82s/it]
 85%|████████▍ | 848/1000 [27:28<04:33,  1.80s/it]
                                                  

 85%|████████▍ | 848/1000 [27:28<04:33,  1.80s/it]
 85%|████████▍ | 849/1000 [27:30<04:24,  1.75s/it]
                                                  

 85%|████████▍ | 849/1000 [27:30<04:24,  1.75s/it]
 85%|████████▌ | 850/1000 [27:31<04:12,  1.68s/it]
                                                  

 85%|████████▌ | 850/1000 [27:31<04:12,  1.68s/it]
 85%|████████▌ | 851/1000 [27:33<04:02,  1.62s/it]
                                                  

 85%|████████▌ | 851/1000 [27:33<04:02,  1.62s/it]
 85%|████████▌ | 852/1000 [27:34<03:54,  1.58s/it]
                                                  

 85%|████████▌ | 852/1000 [27:34<03:54,  1.58s/it]
 85%|████████▌ | 853/1000 [27:36<03:48,  1.55s/it]
                                                  

 85%|████████▌ | 853/1000 [27:36<03:48,  1.55s/it]
 85%|████████▌ | 854/1000 [27:37<03:43,  1.53s/it]
                                                  

 85%|████████▌ | 854/1000 [27:37<03:43,  1.53s/it]
 86%|████████▌ | 855/1000 [27:39<03:42,  1.53s/it]
                                                  

 86%|████████▌ | 855/1000 [27:39<03:42,  1.53s/it]
 86%|████████▌ | 856/1000 [27:40<03:38,  1.52s/it]
                                                  

 86%|████████▌ | 856/1000 [27:40<03:38,  1.52s/it]
 86%|████████▌ | 857/1000 [27:41<03:26,  1.44s/it]
                                                  

 86%|████████▌ | 857/1000 [27:41<03:26,  1.44s/it]
 86%|████████▌ | 858/1000 [27:43<03:15,  1.37s/it]
                                                  

 86%|████████▌ | 858/1000 [27:43<03:15,  1.37s/it]
 86%|████████▌ | 859/1000 [27:44<03:06,  1.32s/it]
                                                  

 86%|████████▌ | 859/1000 [27:44<03:06,  1.32s/it]
 86%|████████▌ | 860/1000 [27:45<03:00,  1.29s/it]
                                                  

 86%|████████▌ | 860/1000 [27:45<03:00,  1.29s/it]
 86%|████████▌ | 861/1000 [27:46<02:56,  1.27s/it]
                                                  

 86%|████████▌ | 861/1000 [27:46<02:56,  1.27s/it]
 86%|████████▌ | 862/1000 [27:47<02:53,  1.26s/it]
                                                  

 86%|████████▌ | 862/1000 [27:48<02:53,  1.26s/it]
 86%|████████▋ | 863/1000 [27:49<02:50,  1.25s/it]
                                                  

 86%|████████▋ | 863/1000 [27:49<02:50,  1.25s/it]
 86%|████████▋ | 864/1000 [27:50<02:49,  1.24s/it]
                                                  

 86%|████████▋ | 864/1000 [27:50<02:49,  1.24s/it]
 86%|████████▋ | 865/1000 [27:51<02:41,  1.20s/it]
                                                  

 86%|████████▋ | 865/1000 [27:51<02:41,  1.20s/it]
 87%|████████▋ | 866/1000 [27:52<02:29,  1.11s/it]
                                                  

 87%|████████▋ | 866/1000 [27:52<02:29,  1.11s/it]
 87%|████████▋ | 867/1000 [27:53<02:20,  1.06s/it]
                                                  

 87%|████████▋ | 867/1000 [27:53<02:20,  1.06s/it]
 87%|████████▋ | 868/1000 [27:54<02:14,  1.02s/it]
                                                  

 87%|████████▋ | 868/1000 [27:54<02:14,  1.02s/it]
 87%|████████▋ | 869/1000 [27:55<02:09,  1.01it/s]
                                                  

 87%|████████▋ | 869/1000 [27:55<02:09,  1.01it/s]
 87%|████████▋ | 870/1000 [27:56<02:06,  1.03it/s]
                                                  

 87%|████████▋ | 870/1000 [27:56<02:06,  1.03it/s]
 87%|████████▋ | 871/1000 [27:56<01:59,  1.08it/s]
                                                  

 87%|████████▋ | 871/1000 [27:56<01:59,  1.08it/s]
 87%|████████▋ | 872/1000 [27:57<01:48,  1.18it/s]
                                                  

 87%|████████▋ | 872/1000 [27:57<01:48,  1.18it/s]
 87%|████████▋ | 873/1000 [27:58<01:40,  1.26it/s]
                                                  

 87%|████████▋ | 873/1000 [27:58<01:40,  1.26it/s]
 87%|████████▋ | 874/1000 [27:58<01:35,  1.32it/s]
                                                  

 87%|████████▋ | 874/1000 [27:59<01:35,  1.32it/s]
 88%|████████▊ | 875/1000 [28:01<02:54,  1.40s/it]
                                                  

 88%|████████▊ | 875/1000 [28:01<02:54,  1.40s/it]
 88%|████████▊ | 876/1000 [28:09<06:28,  3.13s/it]
                                                  

 88%|████████▊ | 876/1000 [28:09<06:28,  3.13s/it]
 88%|████████▊ | 877/1000 [28:13<07:03,  3.44s/it]
                                                  

 88%|████████▊ | 877/1000 [28:13<07:03,  3.44s/it]
 88%|████████▊ | 878/1000 [28:16<07:07,  3.51s/it]
                                                  

 88%|████████▊ | 878/1000 [28:16<07:07,  3.51s/it]
 88%|████████▊ | 879/1000 [28:20<07:00,  3.48s/it]
                                                  

 88%|████████▊ | 879/1000 [28:20<07:00,  3.48s/it]
 88%|████████▊ | 880/1000 [28:23<06:42,  3.36s/it]
                                                  

 88%|████████▊ | 880/1000 [28:23<06:42,  3.36s/it]
 88%|████████▊ | 881/1000 [28:26<06:20,  3.20s/it]
                                                  

 88%|████████▊ | 881/1000 [28:26<06:20,  3.20s/it]
 88%|████████▊ | 882/1000 [28:28<05:59,  3.04s/it]
                                                  

 88%|████████▊ | 882/1000 [28:28<05:59,  3.04s/it]
 88%|████████▊ | 883/1000 [28:31<05:39,  2.90s/it]
                                                  

 88%|████████▊ | 883/1000 [28:31<05:39,  2.90s/it]
 88%|████████▊ | 884/1000 [28:33<05:19,  2.76s/it]
                                                  

 88%|████████▊ | 884/1000 [28:33<05:19,  2.76s/it]
 88%|████████▊ | 885/1000 [28:36<05:02,  2.63s/it]
                                                  

 88%|████████▊ | 885/1000 [28:36<05:02,  2.63s/it]
 89%|████████▊ | 886/1000 [28:38<04:48,  2.53s/it]
                                                  

 89%|████████▊ | 886/1000 [28:38<04:48,  2.53s/it]
 89%|████████▊ | 887/1000 [28:40<04:32,  2.41s/it]
                                                  

 89%|████████▊ | 887/1000 [28:40<04:32,  2.41s/it]
 89%|████████▉ | 888/1000 [28:42<04:18,  2.31s/it]
                                                  

 89%|████████▉ | 888/1000 [28:42<04:18,  2.31s/it]
 89%|████████▉ | 889/1000 [28:44<04:07,  2.23s/it]
                                                  

 89%|████████▉ | 889/1000 [28:44<04:07,  2.23s/it]
 89%|████████▉ | 890/1000 [28:46<03:59,  2.18s/it]
                                                  

 89%|████████▉ | 890/1000 [28:46<03:59,  2.18s/it]
 89%|████████▉ | 891/1000 [28:48<03:53,  2.14s/it]
                                                  

 89%|████████▉ | 891/1000 [28:48<03:53,  2.14s/it]
 89%|████████▉ | 892/1000 [28:50<03:45,  2.09s/it]
                                                  

 89%|████████▉ | 892/1000 [28:50<03:45,  2.09s/it]
 89%|████████▉ | 893/1000 [28:52<03:32,  1.98s/it]
                                                  

 89%|████████▉ | 893/1000 [28:52<03:32,  1.98s/it]
 89%|████████▉ | 894/1000 [28:54<03:22,  1.91s/it]
                                                  

 89%|████████▉ | 894/1000 [28:54<03:22,  1.91s/it]
 90%|████████▉ | 895/1000 [28:56<03:15,  1.86s/it]
                                                  

 90%|████████▉ | 895/1000 [28:56<03:15,  1.86s/it]
 90%|████████▉ | 896/1000 [28:57<03:09,  1.82s/it]
                                                  

 90%|████████▉ | 896/1000 [28:57<03:09,  1.82s/it]
 90%|████████▉ | 897/1000 [28:59<03:05,  1.80s/it]
                                                  

 90%|████████▉ | 897/1000 [28:59<03:05,  1.80s/it]
 90%|████████▉ | 898/1000 [29:01<03:01,  1.78s/it]
                                                  

 90%|████████▉ | 898/1000 [29:01<03:01,  1.78s/it]
 90%|████████▉ | 899/1000 [29:02<02:57,  1.76s/it]
                                                  

 90%|████████▉ | 899/1000 [29:02<02:57,  1.76s/it]
 90%|█████████ | 900/1000 [29:04<02:48,  1.69s/it]
                                                  

 90%|█████████ | 900/1000 [29:04<02:48,  1.69s/it]
 90%|█████████ | 901/1000 [29:05<02:40,  1.63s/it]
                                                  

 90%|█████████ | 901/1000 [29:05<02:40,  1.63s/it]
 90%|█████████ | 902/1000 [29:07<02:35,  1.59s/it]
                                                  

 90%|█████████ | 902/1000 [29:07<02:35,  1.59s/it]
 90%|█████████ | 903/1000 [29:08<02:32,  1.57s/it]
                                                  

 90%|█████████ | 903/1000 [29:09<02:32,  1.57s/it]
 90%|█████████ | 904/1000 [29:10<02:28,  1.55s/it]
                                                  

 90%|█████████ | 904/1000 [29:10<02:28,  1.55s/it]
 90%|█████████ | 905/1000 [29:11<02:25,  1.53s/it]
                                                  

 90%|█████████ | 905/1000 [29:11<02:25,  1.53s/it]
 91%|█████████ | 906/1000 [29:13<02:22,  1.52s/it]
                                                  

 91%|█████████ | 906/1000 [29:13<02:22,  1.52s/it]
 91%|█████████ | 907/1000 [29:14<02:18,  1.49s/it]
                                                  

 91%|█████████ | 907/1000 [29:14<02:18,  1.49s/it]
 91%|█████████ | 908/1000 [29:16<02:09,  1.41s/it]
                                                  

 91%|█████████ | 908/1000 [29:16<02:09,  1.41s/it]
 91%|█████████ | 909/1000 [29:17<02:02,  1.35s/it]
                                                  

 91%|█████████ | 909/1000 [29:17<02:02,  1.35s/it]
 91%|█████████ | 910/1000 [29:18<01:58,  1.32s/it]
                                                  

 91%|█████████ | 910/1000 [29:18<01:58,  1.32s/it]
 91%|█████████ | 911/1000 [29:19<01:54,  1.29s/it]
                                                  

 91%|█████████ | 911/1000 [29:19<01:54,  1.29s/it]
 91%|█████████ | 912/1000 [29:21<01:51,  1.27s/it]
                                                  

 91%|█████████ | 912/1000 [29:21<01:51,  1.27s/it]
 91%|█████████▏| 913/1000 [29:22<01:48,  1.25s/it]
                                                  

 91%|█████████▏| 913/1000 [29:22<01:48,  1.25s/it]
 91%|█████████▏| 914/1000 [29:23<01:46,  1.24s/it]
                                                  

 91%|█████████▏| 914/1000 [29:23<01:46,  1.24s/it]
 92%|█████████▏| 915/1000 [29:24<01:46,  1.25s/it]
                                                  

 92%|█████████▏| 915/1000 [29:24<01:46,  1.25s/it]
 92%|█████████▏| 916/1000 [29:25<01:40,  1.20s/it]
                                                  

 92%|█████████▏| 916/1000 [29:25<01:40,  1.20s/it]
 92%|█████████▏| 917/1000 [29:26<01:32,  1.12s/it]
                                                  

 92%|█████████▏| 917/1000 [29:26<01:32,  1.12s/it]
 92%|█████████▏| 918/1000 [29:27<01:26,  1.06s/it]
                                                  

 92%|█████████▏| 918/1000 [29:27<01:26,  1.06s/it]
 92%|█████████▏| 919/1000 [29:28<01:22,  1.02s/it]
                                                  

 92%|█████████▏| 919/1000 [29:28<01:22,  1.02s/it]
 92%|█████████▏| 920/1000 [29:29<01:19,  1.01it/s]
                                                  

 92%|█████████▏| 920/1000 [29:29<01:19,  1.01it/s]
 92%|█████████▏| 921/1000 [29:30<01:17,  1.03it/s]
                                                  

 92%|█████████▏| 921/1000 [29:30<01:17,  1.03it/s]
 92%|█████████▏| 922/1000 [29:31<01:12,  1.07it/s]
                                                  

 92%|█████████▏| 922/1000 [29:31<01:12,  1.07it/s]
 92%|█████████▏| 923/1000 [29:31<01:05,  1.17it/s]
                                                  

 92%|█████████▏| 923/1000 [29:31<01:05,  1.17it/s]
 92%|█████████▏| 924/1000 [29:32<01:00,  1.25it/s]
                                                  

 92%|█████████▏| 924/1000 [29:32<01:00,  1.25it/s]
 92%|█████████▎| 925/1000 [29:35<01:39,  1.32s/it]
                                                  

 92%|█████████▎| 925/1000 [29:35<01:39,  1.32s/it]
 93%|█████████▎| 926/1000 [29:43<04:15,  3.45s/it]
                                                  

 93%|█████████▎| 926/1000 [29:43<04:15,  3.45s/it]
 93%|█████████▎| 927/1000 [29:47<04:26,  3.66s/it]
                                                  

 93%|█████████▎| 927/1000 [29:47<04:26,  3.66s/it]
 93%|█████████▎| 928/1000 [29:51<04:28,  3.73s/it]
                                                  

 93%|█████████▎| 928/1000 [29:51<04:28,  3.73s/it]
 93%|█████████▎| 929/1000 [29:54<04:16,  3.61s/it]
                                                  

 93%|█████████▎| 929/1000 [29:54<04:16,  3.61s/it]
 93%|█████████▎| 930/1000 [29:57<04:00,  3.44s/it]
                                                  

 93%|█████████▎| 930/1000 [29:57<04:00,  3.44s/it]
 93%|█████████▎| 931/1000 [30:00<03:45,  3.26s/it]
                                                  

 93%|█████████▎| 931/1000 [30:00<03:45,  3.26s/it]
 93%|█████████▎| 932/1000 [30:03<03:29,  3.08s/it]
                                                  

 93%|█████████▎| 932/1000 [30:03<03:29,  3.08s/it]
 93%|█████████▎| 933/1000 [30:06<03:15,  2.92s/it]
                                                  

 93%|█████████▎| 933/1000 [30:06<03:15,  2.92s/it]
 93%|█████████▎| 934/1000 [30:08<03:01,  2.75s/it]
                                                  

 93%|█████████▎| 934/1000 [30:08<03:01,  2.75s/it]
 94%|█████████▎| 935/1000 [30:10<02:51,  2.64s/it]
                                                  

 94%|█████████▎| 935/1000 [30:10<02:51,  2.64s/it]
 94%|█████████▎| 936/1000 [30:13<02:43,  2.55s/it]
                                                  

 94%|█████████▎| 936/1000 [30:13<02:43,  2.55s/it]
 94%|█████████▎| 937/1000 [30:15<02:33,  2.43s/it]
                                                  

 94%|█████████▎| 937/1000 [30:15<02:33,  2.43s/it]
 94%|█████████▍| 938/1000 [30:17<02:23,  2.32s/it]
                                                  

 94%|█████████▍| 938/1000 [30:17<02:23,  2.32s/it]
 94%|█████████▍| 939/1000 [30:19<02:16,  2.24s/it]
                                                  

 94%|█████████▍| 939/1000 [30:19<02:16,  2.24s/it]
 94%|█████████▍| 940/1000 [30:21<02:10,  2.18s/it]
                                                  

 94%|█████████▍| 940/1000 [30:21<02:10,  2.18s/it]
 94%|█████████▍| 941/1000 [30:23<02:06,  2.14s/it]
                                                  

 94%|█████████▍| 941/1000 [30:23<02:06,  2.14s/it]
 94%|█████████▍| 942/1000 [30:25<01:58,  2.05s/it]
                                                  

 94%|█████████▍| 942/1000 [30:25<01:58,  2.05s/it]
 94%|█████████▍| 943/1000 [30:27<01:51,  1.96s/it]
                                                  

 94%|█████████▍| 943/1000 [30:27<01:51,  1.96s/it]
 94%|█████████▍| 944/1000 [30:28<01:45,  1.89s/it]
                                                  

 94%|█████████▍| 944/1000 [30:28<01:45,  1.89s/it]
 94%|█████████▍| 945/1000 [30:30<01:41,  1.85s/it]
                                                  

 94%|█████████▍| 945/1000 [30:30<01:41,  1.85s/it]
 95%|█████████▍| 946/1000 [30:32<01:38,  1.82s/it]
                                                  

 95%|█████████▍| 946/1000 [30:32<01:38,  1.82s/it]
 95%|█████████▍| 947/1000 [30:34<01:35,  1.80s/it]
                                                  

 95%|█████████▍| 947/1000 [30:34<01:35,  1.80s/it]
 95%|█████████▍| 948/1000 [30:35<01:32,  1.78s/it]
                                                  

 95%|█████████▍| 948/1000 [30:35<01:32,  1.78s/it]
 95%|█████████▍| 949/1000 [30:37<01:27,  1.71s/it]
                                                  

 95%|█████████▍| 949/1000 [30:37<01:27,  1.71s/it]
 95%|█████████▌| 950/1000 [30:38<01:21,  1.64s/it]
                                                  

 95%|█████████▌| 950/1000 [30:38<01:21,  1.64s/it]
 95%|█████████▌| 951/1000 [30:40<01:19,  1.61s/it]
                                                  

 95%|█████████▌| 951/1000 [30:40<01:19,  1.61s/it]
 95%|█████████▌| 952/1000 [30:41<01:15,  1.57s/it]
                                                  

 95%|█████████▌| 952/1000 [30:41<01:15,  1.57s/it]
 95%|█████████▌| 953/1000 [30:43<01:12,  1.55s/it]
                                                  

 95%|█████████▌| 953/1000 [30:43<01:12,  1.55s/it]
 95%|█████████▌| 954/1000 [30:44<01:10,  1.53s/it]
                                                  

 95%|█████████▌| 954/1000 [30:44<01:10,  1.53s/it]
 96%|█████████▌| 955/1000 [30:46<01:08,  1.52s/it]
                                                  

 96%|█████████▌| 955/1000 [30:46<01:08,  1.52s/it]
 96%|█████████▌| 956/1000 [30:47<01:06,  1.50s/it]
                                                  

 96%|█████████▌| 956/1000 [30:47<01:06,  1.50s/it]
 96%|█████████▌| 957/1000 [30:49<01:01,  1.43s/it]
                                                  

 96%|█████████▌| 957/1000 [30:49<01:01,  1.43s/it]
 96%|█████████▌| 958/1000 [30:50<00:57,  1.36s/it]
                                                  

 96%|█████████▌| 958/1000 [30:50<00:57,  1.36s/it]
 96%|█████████▌| 959/1000 [30:51<00:54,  1.32s/it]
                                                  

 96%|█████████▌| 959/1000 [30:51<00:54,  1.32s/it]
 96%|█████████▌| 960/1000 [30:52<00:51,  1.29s/it]
                                                  

 96%|█████████▌| 960/1000 [30:52<00:51,  1.29s/it]
 96%|█████████▌| 961/1000 [30:53<00:49,  1.27s/it]
                                                  

 96%|█████████▌| 961/1000 [30:53<00:49,  1.27s/it]
 96%|█████████▌| 962/1000 [30:55<00:47,  1.26s/it]
                                                  

 96%|█████████▌| 962/1000 [30:55<00:47,  1.26s/it]
 96%|█████████▋| 963/1000 [30:56<00:45,  1.24s/it]
                                                  

 96%|█████████▋| 963/1000 [30:56<00:45,  1.24s/it]
 96%|█████████▋| 964/1000 [30:57<00:44,  1.24s/it]
                                                  

 96%|█████████▋| 964/1000 [30:57<00:44,  1.24s/it]
 96%|█████████▋| 965/1000 [30:58<00:41,  1.20s/it]
                                                  

 96%|█████████▋| 965/1000 [30:58<00:41,  1.20s/it]
 97%|█████████▋| 966/1000 [30:59<00:37,  1.12s/it]
                                                  

 97%|█████████▋| 966/1000 [30:59<00:37,  1.12s/it]
 97%|█████████▋| 967/1000 [31:00<00:35,  1.06s/it]
                                                  

 97%|█████████▋| 967/1000 [31:00<00:35,  1.06s/it]
 97%|█████████▋| 968/1000 [31:01<00:33,  1.04s/it]
                                                  

 97%|█████████▋| 968/1000 [31:01<00:33,  1.04s/it]
 97%|█████████▋| 969/1000 [31:02<00:31,  1.01s/it]
                                                  

 97%|█████████▋| 969/1000 [31:02<00:31,  1.01s/it]
 97%|█████████▋| 970/1000 [31:03<00:29,  1.01it/s]
                                                  

 97%|█████████▋| 970/1000 [31:03<00:29,  1.01it/s]
 97%|█████████▋| 971/1000 [31:04<00:28,  1.03it/s]
                                                  

 97%|█████████▋| 971/1000 [31:04<00:28,  1.03it/s]
 97%|█████████▋| 972/1000 [31:05<00:25,  1.09it/s]
                                                  

 97%|█████████▋| 972/1000 [31:05<00:25,  1.09it/s]
 97%|█████████▋| 973/1000 [31:05<00:22,  1.19it/s]
                                                  

 97%|█████████▋| 973/1000 [31:05<00:22,  1.19it/s]
 97%|█████████▋| 974/1000 [31:06<00:20,  1.27it/s]
                                                  

 97%|█████████▋| 974/1000 [31:06<00:20,  1.27it/s]
 98%|█████████▊| 975/1000 [31:08<00:32,  1.31s/it]
                                                  

 98%|█████████▊| 975/1000 [31:08<00:32,  1.31s/it]
 98%|█████████▊| 976/1000 [31:15<01:12,  3.00s/it]
                                                  

 98%|█████████▊| 976/1000 [31:15<01:12,  3.00s/it]
 98%|█████████▊| 977/1000 [31:20<01:18,  3.41s/it]
                                                  

 98%|█████████▊| 977/1000 [31:20<01:18,  3.41s/it]
 98%|█████████▊| 978/1000 [31:24<01:17,  3.53s/it]
                                                  

 98%|█████████▊| 978/1000 [31:24<01:17,  3.53s/it]
 98%|█████████▊| 979/1000 [31:27<01:13,  3.48s/it]
                                                  

 98%|█████████▊| 979/1000 [31:27<01:13,  3.48s/it]
 98%|█████████▊| 980/1000 [31:30<01:07,  3.38s/it]
                                                  

 98%|█████████▊| 980/1000 [31:30<01:07,  3.38s/it]
 98%|█████████▊| 981/1000 [31:33<01:01,  3.25s/it]
                                                  

 98%|█████████▊| 981/1000 [31:33<01:01,  3.25s/it]
 98%|█████████▊| 982/1000 [31:36<00:55,  3.09s/it]
                                                  

 98%|█████████▊| 982/1000 [31:36<00:55,  3.09s/it]
 98%|█████████▊| 983/1000 [31:38<00:50,  2.96s/it]
                                                  

 98%|█████████▊| 983/1000 [31:38<00:50,  2.96s/it]
 98%|█████████▊| 984/1000 [31:41<00:45,  2.85s/it]
                                                  

 98%|█████████▊| 984/1000 [31:41<00:45,  2.85s/it]
 98%|█████████▊| 985/1000 [31:43<00:40,  2.70s/it]
                                                  

 98%|█████████▊| 985/1000 [31:43<00:40,  2.70s/it]
 99%|█████████▊| 986/1000 [31:46<00:36,  2.60s/it]
                                                  

 99%|█████████▊| 986/1000 [31:46<00:36,  2.60s/it]
 99%|█████████▊| 987/1000 [31:48<00:32,  2.52s/it]
                                                  

 99%|█████████▊| 987/1000 [31:48<00:32,  2.52s/it]
 99%|█████████▉| 988/1000 [31:50<00:28,  2.41s/it]
                                                  

 99%|█████████▉| 988/1000 [31:50<00:28,  2.41s/it]
 99%|█████████▉| 989/1000 [31:52<00:25,  2.30s/it]
                                                  

 99%|█████████▉| 989/1000 [31:52<00:25,  2.30s/it]
 99%|█████████▉| 990/1000 [31:54<00:22,  2.23s/it]
                                                  

 99%|█████████▉| 990/1000 [31:54<00:22,  2.23s/it]
 99%|█████████▉| 991/1000 [31:56<00:19,  2.17s/it]
                                                  

 99%|█████████▉| 991/1000 [31:56<00:19,  2.17s/it]
 99%|█████████▉| 992/1000 [31:58<00:16,  2.12s/it]
                                                  

 99%|█████████▉| 992/1000 [31:58<00:16,  2.12s/it]
 99%|█████████▉| 993/1000 [32:00<00:14,  2.02s/it]
                                                  

 99%|█████████▉| 993/1000 [32:00<00:14,  2.02s/it]
 99%|█████████▉| 994/1000 [32:02<00:11,  1.94s/it]
                                                  

 99%|█████████▉| 994/1000 [32:02<00:11,  1.94s/it]
100%|█████████▉| 995/1000 [32:04<00:09,  1.89s/it]
                                                  

100%|█████████▉| 995/1000 [32:04<00:09,  1.89s/it]
100%|█████████▉| 996/1000 [32:05<00:07,  1.85s/it]
                                                  

100%|█████████▉| 996/1000 [32:05<00:07,  1.85s/it]
100%|█████████▉| 997/1000 [32:07<00:05,  1.82s/it]
                                                  

100%|█████████▉| 997/1000 [32:07<00:05,  1.82s/it]
100%|█████████▉| 998/1000 [32:09<00:03,  1.81s/it]
                                                  

100%|█████████▉| 998/1000 [32:09<00:03,  1.81s/it]
100%|█████████▉| 999/1000 [32:11<00:01,  1.77s/it]
                                                  

100%|█████████▉| 999/1000 [32:11<00:01,  1.77s/it]
100%|██████████| 1000/1000 [32:12<00:00,  1.68s/it]
                                                   

100%|██████████| 1000/1000 [32:12<00:00,  1.68s/it]{'loss': 76.924, 'grad_norm': nan, 'learning_rate': 0.0, 'epoch': 0.0}
{'loss': 40.9666, 'grad_norm': inf, 'learning_rate': 0.0, 'epoch': 0.0}
{'loss': 40.3514, 'grad_norm': 22.267667770385742, 'learning_rate': 3e-07, 'epoch': 0.0}
{'loss': 28.7886, 'grad_norm': 11.958697319030762, 'learning_rate': 6e-07, 'epoch': 0.01}
{'loss': 33.1337, 'grad_norm': 14.436713218688965, 'learning_rate': 9e-07, 'epoch': 0.01}
{'loss': 29.2715, 'grad_norm': 15.921396255493164, 'learning_rate': 1.2e-06, 'epoch': 0.01}
{'loss': 28.6694, 'grad_norm': 11.616898536682129, 'learning_rate': 1.4999999999999998e-06, 'epoch': 0.01}
{'loss': 26.7664, 'grad_norm': 12.15279483795166, 'learning_rate': 1.8e-06, 'epoch': 0.01}
{'loss': 27.2963, 'grad_norm': 15.99345874786377, 'learning_rate': 2.1e-06, 'epoch': 0.01}
{'loss': 22.7932, 'grad_norm': 10.025712966918945, 'learning_rate': 2.4e-06, 'epoch': 0.02}
{'loss': 20.7226, 'grad_norm': 9.379335403442383, 'learning_rate': 2.6999999999999996e-06, 'epoch': 0.02}
{'loss': 27.5995, 'grad_norm': 12.390824317932129, 'learning_rate': 2.9999999999999997e-06, 'epoch': 0.02}
{'loss': 23.3013, 'grad_norm': 10.201970100402832, 'learning_rate': 3.2999999999999993e-06, 'epoch': 0.02}
{'loss': 24.6987, 'grad_norm': 11.483911514282227, 'learning_rate': 3.6e-06, 'epoch': 0.02}
{'loss': 22.0543, 'grad_norm': 9.661028861999512, 'learning_rate': 3.899999999999999e-06, 'epoch': 0.02}
{'loss': 20.3867, 'grad_norm': 9.904827117919922, 'learning_rate': 4.2e-06, 'epoch': 0.03}
{'loss': 24.6232, 'grad_norm': 10.597962379455566, 'learning_rate': 4.499999999999999e-06, 'epoch': 0.03}
{'loss': 25.3891, 'grad_norm': 12.7444486618042, 'learning_rate': 4.8e-06, 'epoch': 0.03}
{'loss': 21.5661, 'grad_norm': 10.090996742248535, 'learning_rate': 5.1e-06, 'epoch': 0.03}
{'loss': 23.0623, 'grad_norm': 10.649155616760254, 'learning_rate': 5.399999999999999e-06, 'epoch': 0.03}
{'loss': 20.7193, 'grad_norm': 10.286359786987305, 'learning_rate': 5.7e-06, 'epoch': 0.03}
{'loss': 24.0174, 'grad_norm': 10.968955993652344, 'learning_rate': 5.999999999999999e-06, 'epoch': 0.04}
{'loss': 21.454, 'grad_norm': 9.74566650390625, 'learning_rate': 6.3e-06, 'epoch': 0.04}
{'loss': 23.5266, 'grad_norm': 11.162517547607422, 'learning_rate': 6.599999999999999e-06, 'epoch': 0.04}
{'loss': 20.214, 'grad_norm': 9.547463417053223, 'learning_rate': 6.899999999999999e-06, 'epoch': 0.04}
{'loss': 22.6765, 'grad_norm': 10.754602432250977, 'learning_rate': 7.2e-06, 'epoch': 0.04}
{'loss': 20.4099, 'grad_norm': 9.74982738494873, 'learning_rate': 7.499999999999999e-06, 'epoch': 0.04}
{'loss': 21.5807, 'grad_norm': 10.397897720336914, 'learning_rate': 7.799999999999998e-06, 'epoch': 0.04}
{'loss': 23.4123, 'grad_norm': 10.956497192382812, 'learning_rate': 8.099999999999999e-06, 'epoch': 0.05}
{'loss': 21.6038, 'grad_norm': 10.610095977783203, 'learning_rate': 8.4e-06, 'epoch': 0.05}
{'loss': 21.7059, 'grad_norm': 10.559882164001465, 'learning_rate': 8.7e-06, 'epoch': 0.05}
{'loss': 21.5684, 'grad_norm': 10.241806983947754, 'learning_rate': 8.999999999999999e-06, 'epoch': 0.05}
{'loss': 19.0525, 'grad_norm': 9.802021980285645, 'learning_rate': 9.299999999999999e-06, 'epoch': 0.05}
{'loss': 20.7641, 'grad_norm': 10.859997749328613, 'learning_rate': 9.6e-06, 'epoch': 0.05}
{'loss': 21.9332, 'grad_norm': 11.377524375915527, 'learning_rate': 9.9e-06, 'epoch': 0.06}
{'loss': 19.4306, 'grad_norm': 10.088302612304688, 'learning_rate': 1.02e-05, 'epoch': 0.06}
{'loss': 23.6146, 'grad_norm': 12.069904327392578, 'learning_rate': 1.05e-05, 'epoch': 0.06}
{'loss': 22.8087, 'grad_norm': 12.05452823638916, 'learning_rate': 1.0799999999999998e-05, 'epoch': 0.06}
{'loss': 21.6699, 'grad_norm': 12.891792297363281, 'learning_rate': 1.1099999999999999e-05, 'epoch': 0.06}
{'loss': 19.0892, 'grad_norm': 10.262922286987305, 'learning_rate': 1.14e-05, 'epoch': 0.06}
{'loss': 21.5905, 'grad_norm': 11.921724319458008, 'learning_rate': 1.17e-05, 'epoch': 0.07}
{'loss': 20.87, 'grad_norm': 11.676680564880371, 'learning_rate': 1.1999999999999999e-05, 'epoch': 0.07}
{'loss': 18.0263, 'grad_norm': 10.26872730255127, 'learning_rate': 1.2299999999999999e-05, 'epoch': 0.07}
{'loss': 18.7622, 'grad_norm': 10.563227653503418, 'learning_rate': 1.26e-05, 'epoch': 0.07}
{'loss': 24.0105, 'grad_norm': 14.507094383239746, 'learning_rate': 1.2899999999999998e-05, 'epoch': 0.07}
{'loss': 19.3601, 'grad_norm': 11.43386173248291, 'learning_rate': 1.3199999999999997e-05, 'epoch': 0.07}
{'loss': 19.0576, 'grad_norm': 11.63315200805664, 'learning_rate': 1.3499999999999998e-05, 'epoch': 0.08}
{'loss': 19.2927, 'grad_norm': 12.388842582702637, 'learning_rate': 1.3799999999999998e-05, 'epoch': 0.08}
{'loss': 19.936, 'grad_norm': 12.819602966308594, 'learning_rate': 1.4099999999999999e-05, 'epoch': 0.08}
{'loss': 17.9793, 'grad_norm': nan, 'learning_rate': 1.4099999999999999e-05, 'epoch': 0.08}
{'loss': 64.1187, 'grad_norm': 65.82632446289062, 'learning_rate': 1.44e-05, 'epoch': 0.08}
{'loss': 33.92, 'grad_norm': 26.94750213623047, 'learning_rate': 1.47e-05, 'epoch': 0.08}
{'loss': 34.5358, 'grad_norm': 24.70115852355957, 'learning_rate': 1.4999999999999999e-05, 'epoch': 0.08}
{'loss': 25.5629, 'grad_norm': 18.708255767822266, 'learning_rate': 1.53e-05, 'epoch': 0.09}
{'loss': 27.8492, 'grad_norm': 21.256839752197266, 'learning_rate': 1.5599999999999996e-05, 'epoch': 0.09}
{'loss': 22.1176, 'grad_norm': 17.251680374145508, 'learning_rate': 1.5899999999999997e-05, 'epoch': 0.09}
{'loss': 26.8606, 'grad_norm': 31.902353286743164, 'learning_rate': 1.6199999999999997e-05, 'epoch': 0.09}
{'loss': 23.1075, 'grad_norm': 20.44807243347168, 'learning_rate': 1.6499999999999998e-05, 'epoch': 0.09}
{'loss': 21.0526, 'grad_norm': 17.042905807495117, 'learning_rate': 1.68e-05, 'epoch': 0.09}
{'loss': 20.8373, 'grad_norm': 18.13207244873047, 'learning_rate': 1.71e-05, 'epoch': 0.1}
{'loss': 21.2095, 'grad_norm': 17.839736938476562, 'learning_rate': 1.74e-05, 'epoch': 0.1}
{'loss': 21.5782, 'grad_norm': 18.765409469604492, 'learning_rate': 1.7699999999999997e-05, 'epoch': 0.1}
{'loss': 21.009, 'grad_norm': 18.407758712768555, 'learning_rate': 1.7999999999999997e-05, 'epoch': 0.1}
{'loss': 21.9343, 'grad_norm': 38.16777038574219, 'learning_rate': 1.8299999999999998e-05, 'epoch': 0.1}
{'loss': 22.2912, 'grad_norm': 21.490079879760742, 'learning_rate': 1.8599999999999998e-05, 'epoch': 0.1}
{'loss': 20.3447, 'grad_norm': 22.932668685913086, 'learning_rate': 1.89e-05, 'epoch': 0.11}
{'loss': 23.8814, 'grad_norm': 26.10978126525879, 'learning_rate': 1.92e-05, 'epoch': 0.11}
{'loss': 18.7612, 'grad_norm': 18.075897216796875, 'learning_rate': 1.95e-05, 'epoch': 0.11}
{'loss': 18.8199, 'grad_norm': 18.735963821411133, 'learning_rate': 1.98e-05, 'epoch': 0.11}
{'loss': 20.6774, 'grad_norm': 22.017709732055664, 'learning_rate': 2.01e-05, 'epoch': 0.11}
{'loss': 30.1672, 'grad_norm': 38.08246994018555, 'learning_rate': 2.04e-05, 'epoch': 0.11}
{'loss': 20.0791, 'grad_norm': 22.627145767211914, 'learning_rate': 2.07e-05, 'epoch': 0.12}
{'loss': 23.1779, 'grad_norm': 30.097496032714844, 'learning_rate': 2.1e-05, 'epoch': 0.12}
{'loss': 19.4401, 'grad_norm': 22.679004669189453, 'learning_rate': 2.1299999999999996e-05, 'epoch': 0.12}
{'loss': 19.3537, 'grad_norm': 24.041168212890625, 'learning_rate': 2.1599999999999996e-05, 'epoch': 0.12}
{'loss': 20.2714, 'grad_norm': 26.076839447021484, 'learning_rate': 2.1899999999999997e-05, 'epoch': 0.12}
{'loss': 19.6379, 'grad_norm': 25.533342361450195, 'learning_rate': 2.2199999999999998e-05, 'epoch': 0.12}
{'loss': 18.0205, 'grad_norm': 23.547039031982422, 'learning_rate': 2.2499999999999998e-05, 'epoch': 0.12}
{'loss': 17.6504, 'grad_norm': 23.1020565032959, 'learning_rate': 2.28e-05, 'epoch': 0.13}
{'loss': 19.9713, 'grad_norm': 28.12115478515625, 'learning_rate': 2.31e-05, 'epoch': 0.13}
{'loss': 17.293, 'grad_norm': 24.276756286621094, 'learning_rate': 2.34e-05, 'epoch': 0.13}
{'loss': 15.7224, 'grad_norm': 21.40571403503418, 'learning_rate': 2.3699999999999997e-05, 'epoch': 0.13}
{'loss': 16.4272, 'grad_norm': 24.049413681030273, 'learning_rate': 2.3999999999999997e-05, 'epoch': 0.13}
{'loss': 17.5712, 'grad_norm': 27.002574920654297, 'learning_rate': 2.4299999999999998e-05, 'epoch': 0.13}
{'loss': 19.1111, 'grad_norm': 31.374860763549805, 'learning_rate': 2.4599999999999998e-05, 'epoch': 0.14}
{'loss': 17.1805, 'grad_norm': 28.4317684173584, 'learning_rate': 2.49e-05, 'epoch': 0.14}
{'loss': 18.6232, 'grad_norm': 32.47872543334961, 'learning_rate': 2.52e-05, 'epoch': 0.14}
{'loss': 16.3721, 'grad_norm': 28.26717185974121, 'learning_rate': 2.55e-05, 'epoch': 0.14}
{'loss': 16.6354, 'grad_norm': 29.546110153198242, 'learning_rate': 2.5799999999999997e-05, 'epoch': 0.14}
{'loss': 16.9808, 'grad_norm': 32.13431930541992, 'learning_rate': 2.6099999999999997e-05, 'epoch': 0.14}
{'loss': 17.5935, 'grad_norm': 36.368682861328125, 'learning_rate': 2.6399999999999995e-05, 'epoch': 0.15}
{'loss': 14.6106, 'grad_norm': 28.789241790771484, 'learning_rate': 2.6699999999999995e-05, 'epoch': 0.15}
{'loss': 14.5306, 'grad_norm': 30.914873123168945, 'learning_rate': 2.6999999999999996e-05, 'epoch': 0.15}
{'loss': 14.7256, 'grad_norm': 31.848777770996094, 'learning_rate': 2.7299999999999996e-05, 'epoch': 0.15}
{'loss': 16.3519, 'grad_norm': 43.699851989746094, 'learning_rate': 2.7599999999999997e-05, 'epoch': 0.15}
{'loss': 15.9264, 'grad_norm': 39.825836181640625, 'learning_rate': 2.7899999999999997e-05, 'epoch': 0.15}
{'loss': 13.4326, 'grad_norm': 32.04133224487305, 'learning_rate': 2.8199999999999998e-05, 'epoch': 0.16}
{'loss': 14.3427, 'grad_norm': 39.8133659362793, 'learning_rate': 2.8499999999999998e-05, 'epoch': 0.16}
{'loss': 13.5702, 'grad_norm': 36.54108810424805, 'learning_rate': 2.88e-05, 'epoch': 0.16}
{'loss': 14.6284, 'grad_norm': nan, 'learning_rate': 2.88e-05, 'epoch': 0.16}
{'loss': 25.1519, 'grad_norm': nan, 'learning_rate': 2.88e-05, 'epoch': 0.16}
{'loss': 26.3907, 'grad_norm': 146.48204040527344, 'learning_rate': 2.91e-05, 'epoch': 0.16}
{'loss': 17.1257, 'grad_norm': 56.64327621459961, 'learning_rate': 2.94e-05, 'epoch': 0.16}
{'loss': 18.9131, 'grad_norm': 87.11421966552734, 'learning_rate': 2.97e-05, 'epoch': 0.17}
{'loss': 15.569, 'grad_norm': 57.33453369140625, 'learning_rate': 2.9999999999999997e-05, 'epoch': 0.17}
{'loss': 13.1879, 'grad_norm': 46.68961715698242, 'learning_rate': 3.0299999999999998e-05, 'epoch': 0.17}
{'loss': 14.6438, 'grad_norm': 59.92051315307617, 'learning_rate': 3.06e-05, 'epoch': 0.17}
{'loss': 14.3459, 'grad_norm': 57.27889633178711, 'learning_rate': 3.09e-05, 'epoch': 0.17}
{'loss': 12.7327, 'grad_norm': 51.79650115966797, 'learning_rate': 3.119999999999999e-05, 'epoch': 0.17}
{'loss': 10.6128, 'grad_norm': 45.90155029296875, 'learning_rate': 3.149999999999999e-05, 'epoch': 0.18}
{'loss': 11.1419, 'grad_norm': 46.71571350097656, 'learning_rate': 3.1799999999999994e-05, 'epoch': 0.18}
{'loss': 11.3816, 'grad_norm': 54.34334182739258, 'learning_rate': 3.2099999999999994e-05, 'epoch': 0.18}
{'loss': 9.99, 'grad_norm': 44.52326965332031, 'learning_rate': 3.2399999999999995e-05, 'epoch': 0.18}
{'loss': 10.7379, 'grad_norm': 51.66781997680664, 'learning_rate': 3.2699999999999995e-05, 'epoch': 0.18}
{'loss': 9.5815, 'grad_norm': 44.501441955566406, 'learning_rate': 3.2999999999999996e-05, 'epoch': 0.18}
{'loss': 9.265, 'grad_norm': 42.56653594970703, 'learning_rate': 3.3299999999999996e-05, 'epoch': 0.19}
{'loss': 8.6506, 'grad_norm': 40.3764762878418, 'learning_rate': 3.36e-05, 'epoch': 0.19}
{'loss': 8.5488, 'grad_norm': 40.9335823059082, 'learning_rate': 3.39e-05, 'epoch': 0.19}
{'loss': 8.5519, 'grad_norm': 42.77170181274414, 'learning_rate': 3.42e-05, 'epoch': 0.19}
{'loss': 8.0759, 'grad_norm': 39.98923873901367, 'learning_rate': 3.45e-05, 'epoch': 0.19}
{'loss': 7.3643, 'grad_norm': 33.6198844909668, 'learning_rate': 3.48e-05, 'epoch': 0.19}
{'loss': 7.4889, 'grad_norm': 36.385223388671875, 'learning_rate': 3.51e-05, 'epoch': 0.2}
{'loss': 7.0802, 'grad_norm': 34.519630432128906, 'learning_rate': 3.539999999999999e-05, 'epoch': 0.2}
{'loss': 6.8235, 'grad_norm': 31.894567489624023, 'learning_rate': 3.5699999999999994e-05, 'epoch': 0.2}
{'loss': 6.9291, 'grad_norm': 34.02376174926758, 'learning_rate': 3.5999999999999994e-05, 'epoch': 0.2}
{'loss': 6.4299, 'grad_norm': 28.912235260009766, 'learning_rate': 3.6299999999999995e-05, 'epoch': 0.2}
{'loss': 6.3964, 'grad_norm': 28.84571647644043, 'learning_rate': 3.6599999999999995e-05, 'epoch': 0.2}
{'loss': 6.2274, 'grad_norm': 27.383811950683594, 'learning_rate': 3.6899999999999996e-05, 'epoch': 0.2}
{'loss': 6.0653, 'grad_norm': 29.78708267211914, 'learning_rate': 3.7199999999999996e-05, 'epoch': 0.21}
{'loss': 6.2053, 'grad_norm': 28.544218063354492, 'learning_rate': 3.75e-05, 'epoch': 0.21}
{'loss': 5.7141, 'grad_norm': 22.004798889160156, 'learning_rate': 3.78e-05, 'epoch': 0.21}
{'loss': 5.6288, 'grad_norm': 20.87236785888672, 'learning_rate': 3.81e-05, 'epoch': 0.21}
{'loss': 5.5556, 'grad_norm': 21.300033569335938, 'learning_rate': 3.84e-05, 'epoch': 0.21}
{'loss': 5.4672, 'grad_norm': 19.316028594970703, 'learning_rate': 3.87e-05, 'epoch': 0.21}
{'loss': 5.4904, 'grad_norm': 19.701513290405273, 'learning_rate': 3.9e-05, 'epoch': 0.22}
{'loss': 5.1972, 'grad_norm': 13.995134353637695, 'learning_rate': 3.93e-05, 'epoch': 0.22}
{'loss': 5.1985, 'grad_norm': 14.500862121582031, 'learning_rate': 3.96e-05, 'epoch': 0.22}
{'loss': 5.0034, 'grad_norm': 10.669529914855957, 'learning_rate': 3.99e-05, 'epoch': 0.22}
{'loss': 4.9248, 'grad_norm': 8.051897048950195, 'learning_rate': 4.02e-05, 'epoch': 0.22}
{'loss': 5.0594, 'grad_norm': 11.402167320251465, 'learning_rate': 4.05e-05, 'epoch': 0.22}
{'loss': 5.037, 'grad_norm': 10.03395938873291, 'learning_rate': 4.08e-05, 'epoch': 0.23}
{'loss': 4.9605, 'grad_norm': 8.426224708557129, 'learning_rate': 4.11e-05, 'epoch': 0.23}
{'loss': 4.7972, 'grad_norm': 4.501130104064941, 'learning_rate': 4.14e-05, 'epoch': 0.23}
{'loss': 4.8065, 'grad_norm': 4.365025520324707, 'learning_rate': 4.17e-05, 'epoch': 0.23}
{'loss': 4.8179, 'grad_norm': 4.868807792663574, 'learning_rate': 4.2e-05, 'epoch': 0.23}
{'loss': 4.7889, 'grad_norm': 3.3663101196289062, 'learning_rate': 4.229999999999999e-05, 'epoch': 0.23}
{'loss': 4.702, 'grad_norm': 3.2163665294647217, 'learning_rate': 4.259999999999999e-05, 'epoch': 0.24}
{'loss': 4.7035, 'grad_norm': 3.1945879459381104, 'learning_rate': 4.289999999999999e-05, 'epoch': 0.24}
{'loss': 4.7546, 'grad_norm': 4.427632808685303, 'learning_rate': 4.319999999999999e-05, 'epoch': 0.24}
{'loss': 4.9709, 'grad_norm': 5.550114631652832, 'learning_rate': 4.3499999999999993e-05, 'epoch': 0.24}
{'loss': 5.9402, 'grad_norm': 53.31546401977539, 'learning_rate': 4.3799999999999994e-05, 'epoch': 0.24}
{'loss': 4.5481, 'grad_norm': 7.296631336212158, 'learning_rate': 4.4099999999999995e-05, 'epoch': 0.24}
{'loss': 4.4998, 'grad_norm': 5.802248954772949, 'learning_rate': 4.4399999999999995e-05, 'epoch': 0.24}
{'loss': 4.4536, 'grad_norm': 3.7592978477478027, 'learning_rate': 4.4699999999999996e-05, 'epoch': 0.25}
{'loss': 4.391, 'grad_norm': 3.3045403957366943, 'learning_rate': 4.4999999999999996e-05, 'epoch': 0.25}
{'loss': 4.459, 'grad_norm': 5.204708099365234, 'learning_rate': 4.5299999999999997e-05, 'epoch': 0.25}
{'loss': 4.3071, 'grad_norm': 4.284322261810303, 'learning_rate': 4.56e-05, 'epoch': 0.25}
{'loss': 4.3388, 'grad_norm': 3.191441059112549, 'learning_rate': 4.59e-05, 'epoch': 0.25}
{'loss': 4.2491, 'grad_norm': 3.909501552581787, 'learning_rate': 4.62e-05, 'epoch': 0.25}
{'loss': 4.3493, 'grad_norm': 3.5245823860168457, 'learning_rate': 4.65e-05, 'epoch': 0.26}
{'loss': 4.2599, 'grad_norm': 2.955253839492798, 'learning_rate': 4.68e-05, 'epoch': 0.26}
{'loss': 4.161, 'grad_norm': 3.2109367847442627, 'learning_rate': 4.709999999999999e-05, 'epoch': 0.26}
{'loss': 4.1815, 'grad_norm': 2.6348652839660645, 'learning_rate': 4.7399999999999993e-05, 'epoch': 0.26}
{'loss': 4.0801, 'grad_norm': 2.593337297439575, 'learning_rate': 4.7699999999999994e-05, 'epoch': 0.26}
{'loss': 4.1635, 'grad_norm': 3.77801251411438, 'learning_rate': 4.7999999999999994e-05, 'epoch': 0.26}
{'loss': 4.0901, 'grad_norm': 2.2782046794891357, 'learning_rate': 4.8299999999999995e-05, 'epoch': 0.27}
{'loss': 4.0705, 'grad_norm': 1.8724416494369507, 'learning_rate': 4.8599999999999995e-05, 'epoch': 0.27}
{'loss': 4.0042, 'grad_norm': 1.7749762535095215, 'learning_rate': 4.8899999999999996e-05, 'epoch': 0.27}
{'loss': 4.0104, 'grad_norm': 1.4947004318237305, 'learning_rate': 4.9199999999999997e-05, 'epoch': 0.27}
{'loss': 4.0004, 'grad_norm': 3.1837706565856934, 'learning_rate': 4.95e-05, 'epoch': 0.27}
{'loss': 3.9682, 'grad_norm': 1.914663553237915, 'learning_rate': 4.98e-05, 'epoch': 0.27}
{'loss': 3.9609, 'grad_norm': 1.708173394203186, 'learning_rate': 5.01e-05, 'epoch': 0.28}
{'loss': 3.9917, 'grad_norm': 4.2649407386779785, 'learning_rate': 5.04e-05, 'epoch': 0.28}
{'loss': 3.9464, 'grad_norm': 1.626754641532898, 'learning_rate': 5.07e-05, 'epoch': 0.28}
{'loss': 3.9311, 'grad_norm': 1.2504980564117432, 'learning_rate': 5.1e-05, 'epoch': 0.28}
{'loss': 3.9733, 'grad_norm': 1.5902968645095825, 'learning_rate': 5.13e-05, 'epoch': 0.28}
{'loss': 3.9358, 'grad_norm': 1.160041093826294, 'learning_rate': 5.1599999999999994e-05, 'epoch': 0.28}
{'loss': 3.9375, 'grad_norm': 1.2470163106918335, 'learning_rate': 5.1899999999999994e-05, 'epoch': 0.28}
{'loss': 3.9701, 'grad_norm': 1.0665581226348877, 'learning_rate': 5.2199999999999995e-05, 'epoch': 0.29}
{'loss': 3.8957, 'grad_norm': 1.6660319566726685, 'learning_rate': 5.2499999999999995e-05, 'epoch': 0.29}
{'loss': 3.9527, 'grad_norm': 1.1934682130813599, 'learning_rate': 5.279999999999999e-05, 'epoch': 0.29}
{'loss': 3.9198, 'grad_norm': 2.6113617420196533, 'learning_rate': 5.309999999999999e-05, 'epoch': 0.29}
{'loss': 3.8525, 'grad_norm': 1.4902148246765137, 'learning_rate': 5.339999999999999e-05, 'epoch': 0.29}
{'loss': 3.8462, 'grad_norm': 1.645369529724121, 'learning_rate': 5.369999999999999e-05, 'epoch': 0.29}
{'loss': 3.9076, 'grad_norm': 1.7309008836746216, 'learning_rate': 5.399999999999999e-05, 'epoch': 0.3}
{'loss': 3.9207, 'grad_norm': 1.9582569599151611, 'learning_rate': 5.429999999999999e-05, 'epoch': 0.3}
{'loss': 3.9195, 'grad_norm': 1.795342206954956, 'learning_rate': 5.459999999999999e-05, 'epoch': 0.3}
{'loss': 3.8484, 'grad_norm': 0.6605049967765808, 'learning_rate': 5.489999999999999e-05, 'epoch': 0.3}
{'loss': 3.8709, 'grad_norm': 1.3379170894622803, 'learning_rate': 5.519999999999999e-05, 'epoch': 0.3}
{'loss': 3.8463, 'grad_norm': 2.7950329780578613, 'learning_rate': 5.5499999999999994e-05, 'epoch': 0.3}
{'loss': 4.0707, 'grad_norm': 4.116920471191406, 'learning_rate': 5.5799999999999994e-05, 'epoch': 0.31}
{'loss': 3.9311, 'grad_norm': 1.450844168663025, 'learning_rate': 5.6099999999999995e-05, 'epoch': 0.31}
{'loss': 4.0222, 'grad_norm': 3.2481865882873535, 'learning_rate': 5.6399999999999995e-05, 'epoch': 0.31}
{'loss': 3.9005, 'grad_norm': 1.377772331237793, 'learning_rate': 5.6699999999999996e-05, 'epoch': 0.31}
{'loss': 3.9021, 'grad_norm': 2.0002799034118652, 'learning_rate': 5.6999999999999996e-05, 'epoch': 0.31}
{'loss': 3.8869, 'grad_norm': 2.1365325450897217, 'learning_rate': 5.73e-05, 'epoch': 0.31}
{'loss': 3.8563, 'grad_norm': 2.5995476245880127, 'learning_rate': 5.76e-05, 'epoch': 0.32}
{'loss': 3.9452, 'grad_norm': 3.046848773956299, 'learning_rate': 5.79e-05, 'epoch': 0.32}
{'loss': 3.9164, 'grad_norm': 2.9868597984313965, 'learning_rate': 5.82e-05, 'epoch': 0.32}
{'loss': 3.8911, 'grad_norm': nan, 'learning_rate': 5.82e-05, 'epoch': 0.32}
{'loss': 4.3327, 'grad_norm': 22.723224639892578, 'learning_rate': 5.85e-05, 'epoch': 0.32}
{'loss': 4.0732, 'grad_norm': 14.148520469665527, 'learning_rate': 5.88e-05, 'epoch': 0.32}
{'loss': 4.0389, 'grad_norm': 12.10940170288086, 'learning_rate': 5.91e-05, 'epoch': 0.32}
{'loss': 3.938, 'grad_norm': 7.240406513214111, 'learning_rate': 5.94e-05, 'epoch': 0.33}
{'loss': 3.911, 'grad_norm': 4.678879261016846, 'learning_rate': 5.97e-05, 'epoch': 0.33}
{'loss': 3.9436, 'grad_norm': 2.724951982498169, 'learning_rate': 5.9999999999999995e-05, 'epoch': 0.33}
{'loss': 3.8465, 'grad_norm': 4.7506279945373535, 'learning_rate': 6.0299999999999995e-05, 'epoch': 0.33}
{'loss': 3.932, 'grad_norm': 2.6390953063964844, 'learning_rate': 6.0599999999999996e-05, 'epoch': 0.33}
{'loss': 3.8498, 'grad_norm': 3.661578893661499, 'learning_rate': 6.0899999999999996e-05, 'epoch': 0.33}
{'loss': 3.9245, 'grad_norm': 2.446004867553711, 'learning_rate': 6.12e-05, 'epoch': 0.34}
{'loss': 4.0049, 'grad_norm': 1.197083592414856, 'learning_rate': 6.149999999999999e-05, 'epoch': 0.34}
{'loss': 3.8129, 'grad_norm': 3.957880735397339, 'learning_rate': 6.18e-05, 'epoch': 0.34}
{'loss': 3.8419, 'grad_norm': 2.243058681488037, 'learning_rate': 6.209999999999999e-05, 'epoch': 0.34}
{'loss': 3.8015, 'grad_norm': 0.8457456827163696, 'learning_rate': 6.239999999999999e-05, 'epoch': 0.34}
{'loss': 3.7757, 'grad_norm': 2.7040092945098877, 'learning_rate': 6.269999999999999e-05, 'epoch': 0.34}
{'loss': 3.748, 'grad_norm': 2.867565155029297, 'learning_rate': 6.299999999999999e-05, 'epoch': 0.35}
{'loss': 4.0417, 'grad_norm': 9.108602523803711, 'learning_rate': 6.33e-05, 'epoch': 0.35}
{'loss': 3.7908, 'grad_norm': 2.7541725635528564, 'learning_rate': 6.359999999999999e-05, 'epoch': 0.35}
{'loss': 3.7637, 'grad_norm': 1.1848869323730469, 'learning_rate': 6.39e-05, 'epoch': 0.35}
{'loss': 3.8055, 'grad_norm': 0.6500396132469177, 'learning_rate': 6.419999999999999e-05, 'epoch': 0.35}
{'loss': 3.7637, 'grad_norm': 2.706550359725952, 'learning_rate': 6.45e-05, 'epoch': 0.35}
{'loss': 3.7861, 'grad_norm': 5.064160346984863, 'learning_rate': 6.479999999999999e-05, 'epoch': 0.36}
{'loss': 3.7752, 'grad_norm': 3.20385479927063, 'learning_rate': 6.51e-05, 'epoch': 0.36}
{'loss': 3.7934, 'grad_norm': 2.3726119995117188, 'learning_rate': 6.539999999999999e-05, 'epoch': 0.36}
{'loss': 3.8806, 'grad_norm': 1.985705852508545, 'learning_rate': 6.57e-05, 'epoch': 0.36}
{'loss': 3.7576, 'grad_norm': 0.669208288192749, 'learning_rate': 6.599999999999999e-05, 'epoch': 0.36}
{'loss': 3.7382, 'grad_norm': 1.7072322368621826, 'learning_rate': 6.63e-05, 'epoch': 0.36}
{'loss': 3.8001, 'grad_norm': 2.339816093444824, 'learning_rate': 6.659999999999999e-05, 'epoch': 0.36}
{'loss': 3.7473, 'grad_norm': 0.6553944945335388, 'learning_rate': 6.69e-05, 'epoch': 0.37}
{'loss': 3.79, 'grad_norm': 1.8117849826812744, 'learning_rate': 6.72e-05, 'epoch': 0.37}
{'loss': 3.7968, 'grad_norm': 1.0229136943817139, 'learning_rate': 6.75e-05, 'epoch': 0.37}
{'loss': 3.7716, 'grad_norm': 1.6037867069244385, 'learning_rate': 6.78e-05, 'epoch': 0.37}
{'loss': 3.8464, 'grad_norm': 1.716901183128357, 'learning_rate': 6.81e-05, 'epoch': 0.37}
{'loss': 3.8106, 'grad_norm': 9.919891357421875, 'learning_rate': 6.84e-05, 'epoch': 0.37}
{'loss': 3.7871, 'grad_norm': 1.2543926239013672, 'learning_rate': 6.87e-05, 'epoch': 0.38}
{'loss': 3.9449, 'grad_norm': 5.111069202423096, 'learning_rate': 6.9e-05, 'epoch': 0.38}
{'loss': 3.784, 'grad_norm': 0.940678060054779, 'learning_rate': 6.93e-05, 'epoch': 0.38}
{'loss': 3.8137, 'grad_norm': 0.9248812794685364, 'learning_rate': 6.96e-05, 'epoch': 0.38}
{'loss': 3.7626, 'grad_norm': 0.8821243643760681, 'learning_rate': 6.989999999999999e-05, 'epoch': 0.38}
{'loss': 3.7819, 'grad_norm': 1.0918103456497192, 'learning_rate': 7.02e-05, 'epoch': 0.38}
{'loss': 3.7891, 'grad_norm': 0.6585227251052856, 'learning_rate': 7.049999999999999e-05, 'epoch': 0.39}
{'loss': 3.7803, 'grad_norm': 3.0343358516693115, 'learning_rate': 7.079999999999999e-05, 'epoch': 0.39}
{'loss': 3.8404, 'grad_norm': 2.1487510204315186, 'learning_rate': 7.11e-05, 'epoch': 0.39}
{'loss': 3.7602, 'grad_norm': 1.0203007459640503, 'learning_rate': 7.139999999999999e-05, 'epoch': 0.39}
{'loss': 3.7826, 'grad_norm': 0.8433353900909424, 'learning_rate': 7.17e-05, 'epoch': 0.39}
{'loss': 3.7436, 'grad_norm': 2.8857128620147705, 'learning_rate': 7.199999999999999e-05, 'epoch': 0.39}
{'loss': 4.0391, 'grad_norm': 6.611523628234863, 'learning_rate': 7.23e-05, 'epoch': 0.4}
{'loss': 3.8167, 'grad_norm': 0.7234116196632385, 'learning_rate': 7.259999999999999e-05, 'epoch': 0.4}
{'loss': 3.8963, 'grad_norm': 0.973664402961731, 'learning_rate': 7.29e-05, 'epoch': 0.4}
{'loss': 3.9033, 'grad_norm': 1.6993762254714966, 'learning_rate': 7.319999999999999e-05, 'epoch': 0.4}
{'loss': 4.2596, 'grad_norm': 17.571664810180664, 'learning_rate': 7.35e-05, 'epoch': 0.4}
{'loss': 4.1186, 'grad_norm': 11.271060943603516, 'learning_rate': 7.379999999999999e-05, 'epoch': 0.4}
{'loss': 4.013, 'grad_norm': 8.646568298339844, 'learning_rate': 7.41e-05, 'epoch': 0.4}
{'loss': 3.8974, 'grad_norm': 2.02486252784729, 'learning_rate': 7.439999999999999e-05, 'epoch': 0.41}
{'loss': 3.8285, 'grad_norm': 3.4109764099121094, 'learning_rate': 7.47e-05, 'epoch': 0.41}
{'loss': 3.9306, 'grad_norm': 3.8505735397338867, 'learning_rate': 7.5e-05, 'epoch': 0.41}
{'loss': 3.8432, 'grad_norm': 7.018677234649658, 'learning_rate': 7.529999999999999e-05, 'epoch': 0.41}
{'loss': 3.8534, 'grad_norm': 4.351247310638428, 'learning_rate': 7.56e-05, 'epoch': 0.41}
{'loss': 3.8408, 'grad_norm': 5.365427494049072, 'learning_rate': 7.589999999999999e-05, 'epoch': 0.41}
{'loss': 3.7589, 'grad_norm': 3.984861135482788, 'learning_rate': 7.62e-05, 'epoch': 0.42}
{'loss': 3.748, 'grad_norm': 1.2847763299942017, 'learning_rate': 7.649999999999999e-05, 'epoch': 0.42}
{'loss': 3.8104, 'grad_norm': 4.559200286865234, 'learning_rate': 7.68e-05, 'epoch': 0.42}
{'loss': 3.7676, 'grad_norm': 4.230029106140137, 'learning_rate': 7.709999999999999e-05, 'epoch': 0.42}
{'loss': 3.7336, 'grad_norm': 6.13962984085083, 'learning_rate': 7.74e-05, 'epoch': 0.42}
{'loss': 3.744, 'grad_norm': 4.625703811645508, 'learning_rate': 7.769999999999999e-05, 'epoch': 0.42}
{'loss': 3.7662, 'grad_norm': 4.050301551818848, 'learning_rate': 7.8e-05, 'epoch': 0.43}
{'loss': 3.7469, 'grad_norm': 3.0125648975372314, 'learning_rate': 7.829999999999999e-05, 'epoch': 0.43}
{'loss': 3.7913, 'grad_norm': 0.6710224747657776, 'learning_rate': 7.86e-05, 'epoch': 0.43}
{'loss': 3.7765, 'grad_norm': 0.7062709927558899, 'learning_rate': 7.89e-05, 'epoch': 0.43}
{'loss': 3.7567, 'grad_norm': 5.028995990753174, 'learning_rate': 7.92e-05, 'epoch': 0.43}
{'loss': 3.7673, 'grad_norm': 4.44848108291626, 'learning_rate': 7.95e-05, 'epoch': 0.43}
{'loss': 3.7462, 'grad_norm': 4.467078685760498, 'learning_rate': 7.98e-05, 'epoch': 0.44}
{'loss': 3.715, 'grad_norm': 3.1866374015808105, 'learning_rate': 8.01e-05, 'epoch': 0.44}
{'loss': 3.6984, 'grad_norm': 2.605476140975952, 'learning_rate': 8.04e-05, 'epoch': 0.44}
{'loss': 3.7325, 'grad_norm': 0.6094714999198914, 'learning_rate': 8.07e-05, 'epoch': 0.44}
{'loss': 3.8765, 'grad_norm': 6.599428653717041, 'learning_rate': 8.1e-05, 'epoch': 0.44}
{'loss': 3.7577, 'grad_norm': 2.6780223846435547, 'learning_rate': 8.13e-05, 'epoch': 0.44}
{'loss': 3.8035, 'grad_norm': 3.663605213165283, 'learning_rate': 8.16e-05, 'epoch': 0.44}
{'loss': 3.749, 'grad_norm': 2.812157392501831, 'learning_rate': 8.19e-05, 'epoch': 0.45}
{'loss': 3.7149, 'grad_norm': 2.2692039012908936, 'learning_rate': 8.22e-05, 'epoch': 0.45}
{'loss': 3.7246, 'grad_norm': 1.1938503980636597, 'learning_rate': 8.25e-05, 'epoch': 0.45}
{'loss': 3.6932, 'grad_norm': 1.3016897439956665, 'learning_rate': 8.28e-05, 'epoch': 0.45}
{'loss': 3.7896, 'grad_norm': 2.0602409839630127, 'learning_rate': 8.31e-05, 'epoch': 0.45}
{'loss': 3.7896, 'grad_norm': 1.2453322410583496, 'learning_rate': 8.34e-05, 'epoch': 0.45}
{'loss': 3.7406, 'grad_norm': 0.7699930667877197, 'learning_rate': 8.37e-05, 'epoch': 0.46}
{'loss': 3.7951, 'grad_norm': 0.9949842691421509, 'learning_rate': 8.4e-05, 'epoch': 0.46}
{'loss': 3.7142, 'grad_norm': 1.2708395719528198, 'learning_rate': 8.43e-05, 'epoch': 0.46}
{'loss': 3.7042, 'grad_norm': 1.6578696966171265, 'learning_rate': 8.459999999999998e-05, 'epoch': 0.46}
{'loss': 3.6875, 'grad_norm': 0.9027276635169983, 'learning_rate': 8.489999999999999e-05, 'epoch': 0.46}
{'loss': 3.7219, 'grad_norm': 1.3110026121139526, 'learning_rate': 8.519999999999998e-05, 'epoch': 0.46}
{'loss': 3.7555, 'grad_norm': 0.9840269088745117, 'learning_rate': 8.549999999999999e-05, 'epoch': 0.47}
{'loss': 3.7981, 'grad_norm': 1.4040346145629883, 'learning_rate': 8.579999999999998e-05, 'epoch': 0.47}
{'loss': 3.7075, 'grad_norm': 1.0543975830078125, 'learning_rate': 8.609999999999999e-05, 'epoch': 0.47}
{'loss': 3.677, 'grad_norm': 0.9345111846923828, 'learning_rate': 8.639999999999999e-05, 'epoch': 0.47}
{'loss': 3.7533, 'grad_norm': 1.007042646408081, 'learning_rate': 8.669999999999998e-05, 'epoch': 0.47}
{'loss': 3.6897, 'grad_norm': 1.7284626960754395, 'learning_rate': 8.699999999999999e-05, 'epoch': 0.47}
{'loss': 3.8189, 'grad_norm': 2.507981538772583, 'learning_rate': 8.729999999999998e-05, 'epoch': 0.48}
{'loss': 3.8095, 'grad_norm': 2.26454496383667, 'learning_rate': 8.759999999999999e-05, 'epoch': 0.48}
{'loss': 3.8321, 'grad_norm': 1.5712822675704956, 'learning_rate': 8.789999999999998e-05, 'epoch': 0.48}
{'loss': 3.9162, 'grad_norm': 1.8837485313415527, 'learning_rate': 8.819999999999999e-05, 'epoch': 0.48}
{'loss': 4.0945, 'grad_norm': 14.770750999450684, 'learning_rate': 8.849999999999998e-05, 'epoch': 0.48}
{'loss': 4.0664, 'grad_norm': 14.976526260375977, 'learning_rate': 8.879999999999999e-05, 'epoch': 0.48}
{'loss': 4.0088, 'grad_norm': 9.496882438659668, 'learning_rate': 8.909999999999998e-05, 'epoch': 0.48}
{'loss': 4.1825, 'grad_norm': 13.879667282104492, 'learning_rate': 8.939999999999999e-05, 'epoch': 0.49}
{'loss': 3.883, 'grad_norm': 6.049519062042236, 'learning_rate': 8.969999999999998e-05, 'epoch': 0.49}
{'loss': 3.8272, 'grad_norm': 1.975704312324524, 'learning_rate': 8.999999999999999e-05, 'epoch': 0.49}
{'loss': 3.8001, 'grad_norm': 5.8130598068237305, 'learning_rate': 9.029999999999999e-05, 'epoch': 0.49}
{'loss': 3.8353, 'grad_norm': 3.5878612995147705, 'learning_rate': 9.059999999999999e-05, 'epoch': 0.49}
{'loss': 3.9413, 'grad_norm': 4.1221513748168945, 'learning_rate': 9.089999999999999e-05, 'epoch': 0.49}
{'loss': 3.7904, 'grad_norm': 5.489438533782959, 'learning_rate': 9.12e-05, 'epoch': 0.5}
{'loss': 3.7937, 'grad_norm': 1.6620556116104126, 'learning_rate': 9.149999999999999e-05, 'epoch': 0.5}
{'loss': 3.7336, 'grad_norm': 1.13966703414917, 'learning_rate': 9.18e-05, 'epoch': 0.5}
{'loss': 3.7161, 'grad_norm': 1.5242611169815063, 'learning_rate': 9.209999999999999e-05, 'epoch': 0.5}
{'loss': 3.7, 'grad_norm': 3.9798734188079834, 'learning_rate': 9.24e-05, 'epoch': 0.5}
{'loss': 3.7537, 'grad_norm': 7.939405918121338, 'learning_rate': 9.269999999999999e-05, 'epoch': 0.5}
{'loss': 3.708, 'grad_norm': 4.0154709815979, 'learning_rate': 9.3e-05, 'epoch': 0.51}
{'loss': 3.7166, 'grad_norm': 4.138357639312744, 'learning_rate': 9.329999999999999e-05, 'epoch': 0.51}
{'loss': 4.0627, 'grad_norm': 8.64471435546875, 'learning_rate': 9.36e-05, 'epoch': 0.51}
{'loss': 3.7427, 'grad_norm': 0.7231702208518982, 'learning_rate': 9.389999999999999e-05, 'epoch': 0.51}
{'loss': 3.7203, 'grad_norm': 2.371631622314453, 'learning_rate': 9.419999999999999e-05, 'epoch': 0.51}
{'loss': 3.7413, 'grad_norm': 4.284900188446045, 'learning_rate': 9.449999999999999e-05, 'epoch': 0.51}
{'loss': 3.6992, 'grad_norm': 3.0372443199157715, 'learning_rate': 9.479999999999999e-05, 'epoch': 0.52}
{'loss': 3.7184, 'grad_norm': 1.9789845943450928, 'learning_rate': 9.51e-05, 'epoch': 0.52}
{'loss': 3.6749, 'grad_norm': 1.624227523803711, 'learning_rate': 9.539999999999999e-05, 'epoch': 0.52}
{'loss': 3.7581, 'grad_norm': 1.5696678161621094, 'learning_rate': 9.57e-05, 'epoch': 0.52}
{'loss': 3.6773, 'grad_norm': 2.7740790843963623, 'learning_rate': 9.599999999999999e-05, 'epoch': 0.52}
{'loss': 3.6821, 'grad_norm': 2.1769227981567383, 'learning_rate': 9.63e-05, 'epoch': 0.52}
{'loss': 3.6977, 'grad_norm': 3.454484224319458, 'learning_rate': 9.659999999999999e-05, 'epoch': 0.52}
{'loss': 3.6816, 'grad_norm': 1.035311222076416, 'learning_rate': 9.69e-05, 'epoch': 0.53}
{'loss': 3.7105, 'grad_norm': 1.0064358711242676, 'learning_rate': 9.719999999999999e-05, 'epoch': 0.53}
{'loss': 3.7867, 'grad_norm': 2.302251100540161, 'learning_rate': 9.75e-05, 'epoch': 0.53}
{'loss': 3.7186, 'grad_norm': 2.8935694694519043, 'learning_rate': 9.779999999999999e-05, 'epoch': 0.53}
{'loss': 3.6946, 'grad_norm': 4.943471908569336, 'learning_rate': 9.81e-05, 'epoch': 0.53}
{'loss': 3.7091, 'grad_norm': 2.8398258686065674, 'learning_rate': 9.839999999999999e-05, 'epoch': 0.53}
{'loss': 3.7574, 'grad_norm': 3.0762977600097656, 'learning_rate': 9.87e-05, 'epoch': 0.54}
{'loss': 3.7118, 'grad_norm': 1.8813797235488892, 'learning_rate': 9.9e-05, 'epoch': 0.54}
{'loss': 3.77, 'grad_norm': 0.8849917054176331, 'learning_rate': 9.93e-05, 'epoch': 0.54}
{'loss': 3.6983, 'grad_norm': 1.4980673789978027, 'learning_rate': 9.96e-05, 'epoch': 0.54}
{'loss': 3.6434, 'grad_norm': 1.593652367591858, 'learning_rate': 9.99e-05, 'epoch': 0.54}
{'loss': 3.6421, 'grad_norm': 1.0899137258529663, 'learning_rate': 0.0001002, 'epoch': 0.54}
{'loss': 3.6891, 'grad_norm': 0.6649819016456604, 'learning_rate': 0.0001005, 'epoch': 0.55}
{'loss': 3.794, 'grad_norm': 1.5821571350097656, 'learning_rate': 0.0001008, 'epoch': 0.55}
{'loss': 3.6779, 'grad_norm': 2.7996299266815186, 'learning_rate': 0.0001011, 'epoch': 0.55}
{'loss': 3.7879, 'grad_norm': 2.5575685501098633, 'learning_rate': 0.0001014, 'epoch': 0.55}
{'loss': 3.7208, 'grad_norm': 1.2596614360809326, 'learning_rate': 0.00010169999999999999, 'epoch': 0.55}
{'loss': 3.6811, 'grad_norm': 0.8037718534469604, 'learning_rate': 0.000102, 'epoch': 0.55}
{'loss': 3.6959, 'grad_norm': 1.3349064588546753, 'learning_rate': 0.00010229999999999999, 'epoch': 0.56}
{'loss': 3.7447, 'grad_norm': 1.269572138786316, 'learning_rate': 0.0001026, 'epoch': 0.56}
{'loss': 3.6698, 'grad_norm': 1.022356629371643, 'learning_rate': 0.0001029, 'epoch': 0.56}
{'loss': 3.7888, 'grad_norm': 1.5080015659332275, 'learning_rate': 0.00010319999999999999, 'epoch': 0.56}
{'loss': 5.0541, 'grad_norm': 39.285152435302734, 'learning_rate': 0.00010349999999999998, 'epoch': 0.56}
{'loss': 4.014, 'grad_norm': 9.576460838317871, 'learning_rate': 0.00010379999999999999, 'epoch': 0.56}
{'loss': 3.9312, 'grad_norm': 6.356123447418213, 'learning_rate': 0.00010409999999999998, 'epoch': 0.56}
{'loss': 3.7221, 'grad_norm': 2.139646291732788, 'learning_rate': 0.00010439999999999999, 'epoch': 0.57}
{'loss': 3.8395, 'grad_norm': 1.8156242370605469, 'learning_rate': 0.00010469999999999998, 'epoch': 0.57}
{'loss': 3.719, 'grad_norm': 4.785361289978027, 'learning_rate': 0.00010499999999999999, 'epoch': 0.57}
{'loss': 3.7428, 'grad_norm': 3.600017786026001, 'learning_rate': 0.00010529999999999998, 'epoch': 0.57}
{'loss': 3.6832, 'grad_norm': 2.4187095165252686, 'learning_rate': 0.00010559999999999998, 'epoch': 0.57}
{'loss': 3.6504, 'grad_norm': 1.5843887329101562, 'learning_rate': 0.00010589999999999999, 'epoch': 0.57}
{'loss': 3.6816, 'grad_norm': 1.5045654773712158, 'learning_rate': 0.00010619999999999998, 'epoch': 0.58}
{'loss': 3.642, 'grad_norm': 2.58827543258667, 'learning_rate': 0.00010649999999999999, 'epoch': 0.58}
{'loss': 3.6578, 'grad_norm': 2.5386884212493896, 'learning_rate': 0.00010679999999999998, 'epoch': 0.58}
{'loss': 3.6694, 'grad_norm': 2.9344706535339355, 'learning_rate': 0.00010709999999999999, 'epoch': 0.58}
{'loss': 3.6504, 'grad_norm': 2.340221643447876, 'learning_rate': 0.00010739999999999998, 'epoch': 0.58}
{'loss': 3.6654, 'grad_norm': 2.816999912261963, 'learning_rate': 0.00010769999999999999, 'epoch': 0.58}
{'loss': 3.6406, 'grad_norm': 1.5071390867233276, 'learning_rate': 0.00010799999999999998, 'epoch': 0.59}
{'loss': 3.6683, 'grad_norm': 0.7593219876289368, 'learning_rate': 0.00010829999999999999, 'epoch': 0.59}
{'loss': 3.6844, 'grad_norm': 2.646967887878418, 'learning_rate': 0.00010859999999999998, 'epoch': 0.59}
{'loss': 3.6159, 'grad_norm': 2.8628735542297363, 'learning_rate': 0.00010889999999999999, 'epoch': 0.59}
{'loss': 3.6951, 'grad_norm': 2.4796457290649414, 'learning_rate': 0.00010919999999999998, 'epoch': 0.59}
{'loss': 3.5725, 'grad_norm': 1.1962988376617432, 'learning_rate': 0.00010949999999999999, 'epoch': 0.59}
{'loss': 3.5847, 'grad_norm': 0.9031145572662354, 'learning_rate': 0.00010979999999999999, 'epoch': 0.6}
{'loss': 3.6181, 'grad_norm': 2.3092095851898193, 'learning_rate': 0.00011009999999999999, 'epoch': 0.6}
{'loss': 3.6774, 'grad_norm': 1.1398162841796875, 'learning_rate': 0.00011039999999999999, 'epoch': 0.6}
{'loss': 3.5872, 'grad_norm': 1.0708636045455933, 'learning_rate': 0.0001107, 'epoch': 0.6}
{'loss': 3.6512, 'grad_norm': 0.873319149017334, 'learning_rate': 0.00011099999999999999, 'epoch': 0.6}
{'loss': 3.6434, 'grad_norm': 0.8766927123069763, 'learning_rate': 0.0001113, 'epoch': 0.6}
{'loss': 3.5572, 'grad_norm': 0.7983845472335815, 'learning_rate': 0.00011159999999999999, 'epoch': 0.6}
{'loss': 3.7195, 'grad_norm': 6.645163059234619, 'learning_rate': 0.0001119, 'epoch': 0.61}
{'loss': 3.7342, 'grad_norm': 4.845424652099609, 'learning_rate': 0.00011219999999999999, 'epoch': 0.61}
{'loss': 3.5633, 'grad_norm': 0.7528507709503174, 'learning_rate': 0.0001125, 'epoch': 0.61}
{'loss': 3.6274, 'grad_norm': 0.69414883852005, 'learning_rate': 0.00011279999999999999, 'epoch': 0.61}
{'loss': 3.5491, 'grad_norm': 2.0266685485839844, 'learning_rate': 0.00011309999999999998, 'epoch': 0.61}
{'loss': 3.6293, 'grad_norm': 0.7420620918273926, 'learning_rate': 0.00011339999999999999, 'epoch': 0.61}
{'loss': 3.5036, 'grad_norm': 1.1609050035476685, 'learning_rate': 0.00011369999999999999, 'epoch': 0.62}
{'loss': 3.5909, 'grad_norm': 1.6696407794952393, 'learning_rate': 0.00011399999999999999, 'epoch': 0.62}
{'loss': 3.6343, 'grad_norm': 1.1470685005187988, 'learning_rate': 0.00011429999999999999, 'epoch': 0.62}
{'loss': 3.5755, 'grad_norm': 1.3622722625732422, 'learning_rate': 0.0001146, 'epoch': 0.62}
{'loss': 3.5538, 'grad_norm': 1.2317267656326294, 'learning_rate': 0.00011489999999999999, 'epoch': 0.62}
{'loss': 3.5555, 'grad_norm': 1.1414676904678345, 'learning_rate': 0.0001152, 'epoch': 0.62}
{'loss': 3.5465, 'grad_norm': 1.998960018157959, 'learning_rate': 0.00011549999999999999, 'epoch': 0.63}
{'loss': 3.5777, 'grad_norm': 1.4650264978408813, 'learning_rate': 0.0001158, 'epoch': 0.63}
{'loss': 3.6034, 'grad_norm': 1.5700796842575073, 'learning_rate': 0.00011609999999999999, 'epoch': 0.63}
{'loss': 3.5582, 'grad_norm': 2.38299298286438, 'learning_rate': 0.0001164, 'epoch': 0.63}
{'loss': 3.4869, 'grad_norm': 1.2898112535476685, 'learning_rate': 0.00011669999999999999, 'epoch': 0.63}
{'loss': 3.5423, 'grad_norm': 1.2601486444473267, 'learning_rate': 0.000117, 'epoch': 0.63}
{'loss': 3.5019, 'grad_norm': 1.907885193824768, 'learning_rate': 0.00011729999999999999, 'epoch': 0.64}
{'loss': 3.6299, 'grad_norm': 1.2280569076538086, 'learning_rate': 0.0001176, 'epoch': 0.64}
{'loss': 3.5979, 'grad_norm': 2.214331865310669, 'learning_rate': 0.00011789999999999999, 'epoch': 0.64}
{'loss': 3.4218, 'grad_norm': nan, 'learning_rate': 0.00011789999999999999, 'epoch': 0.64}
{'loss': 4.5562, 'grad_norm': 38.77112579345703, 'learning_rate': 0.0001182, 'epoch': 0.64}
{'loss': 3.7699, 'grad_norm': 8.848291397094727, 'learning_rate': 0.0001185, 'epoch': 0.64}
{'loss': 3.539, 'grad_norm': 6.007197856903076, 'learning_rate': 0.0001188, 'epoch': 0.64}
{'loss': 3.5382, 'grad_norm': 3.0180368423461914, 'learning_rate': 0.0001191, 'epoch': 0.65}
{'loss': 3.5857, 'grad_norm': 2.071746587753296, 'learning_rate': 0.0001194, 'epoch': 0.65}
{'loss': 3.526, 'grad_norm': 4.427801132202148, 'learning_rate': 0.0001197, 'epoch': 0.65}
{'loss': 3.4296, 'grad_norm': 5.680927753448486, 'learning_rate': 0.00011999999999999999, 'epoch': 0.65}
{'loss': 3.4657, 'grad_norm': 2.7837042808532715, 'learning_rate': 0.0001203, 'epoch': 0.65}
{'loss': 3.4279, 'grad_norm': 4.605573654174805, 'learning_rate': 0.00012059999999999999, 'epoch': 0.65}
{'loss': 3.3618, 'grad_norm': 1.96554696559906, 'learning_rate': 0.0001209, 'epoch': 0.66}
{'loss': 3.4163, 'grad_norm': 5.76222038269043, 'learning_rate': 0.00012119999999999999, 'epoch': 0.66}
{'loss': 3.4429, 'grad_norm': 4.640344619750977, 'learning_rate': 0.0001215, 'epoch': 0.66}
{'loss': 3.3255, 'grad_norm': 4.301933288574219, 'learning_rate': 0.00012179999999999999, 'epoch': 0.66}
{'loss': 3.3261, 'grad_norm': 3.781334638595581, 'learning_rate': 0.00012209999999999999, 'epoch': 0.66}
{'loss': 3.2962, 'grad_norm': 3.663053035736084, 'learning_rate': 0.0001224, 'epoch': 0.66}
{'loss': 3.333, 'grad_norm': 3.2776567935943604, 'learning_rate': 0.00012269999999999997, 'epoch': 0.67}
{'loss': 3.2321, 'grad_norm': 1.000927209854126, 'learning_rate': 0.00012299999999999998, 'epoch': 0.67}
{'loss': 3.3121, 'grad_norm': 1.561220407485962, 'learning_rate': 0.0001233, 'epoch': 0.67}
{'loss': 3.3394, 'grad_norm': 0.8714520931243896, 'learning_rate': 0.0001236, 'epoch': 0.67}
{'loss': 3.1645, 'grad_norm': 1.1457229852676392, 'learning_rate': 0.00012389999999999998, 'epoch': 0.67}
{'loss': 3.2115, 'grad_norm': 2.054020881652832, 'learning_rate': 0.00012419999999999998, 'epoch': 0.67}
{'loss': 3.3334, 'grad_norm': 3.8146936893463135, 'learning_rate': 0.0001245, 'epoch': 0.68}
{'loss': 3.2264, 'grad_norm': 2.3825631141662598, 'learning_rate': 0.00012479999999999997, 'epoch': 0.68}
{'loss': 3.3354, 'grad_norm': 1.282517671585083, 'learning_rate': 0.00012509999999999998, 'epoch': 0.68}
{'loss': 3.1819, 'grad_norm': 1.5535123348236084, 'learning_rate': 0.00012539999999999999, 'epoch': 0.68}
{'loss': 3.1989, 'grad_norm': 1.8400110006332397, 'learning_rate': 0.0001257, 'epoch': 0.68}
{'loss': 3.2336, 'grad_norm': 1.3851298093795776, 'learning_rate': 0.00012599999999999997, 'epoch': 0.68}
{'loss': 3.2123, 'grad_norm': 1.884459376335144, 'learning_rate': 0.00012629999999999998, 'epoch': 0.68}
{'loss': 3.0558, 'grad_norm': 1.7640012502670288, 'learning_rate': 0.0001266, 'epoch': 0.69}
{'loss': 3.0314, 'grad_norm': 2.564265489578247, 'learning_rate': 0.0001269, 'epoch': 0.69}
{'loss': 3.0916, 'grad_norm': 1.8793052434921265, 'learning_rate': 0.00012719999999999997, 'epoch': 0.69}
{'loss': 3.0977, 'grad_norm': 1.3174560070037842, 'learning_rate': 0.00012749999999999998, 'epoch': 0.69}
{'loss': 3.1459, 'grad_norm': 0.9135323166847229, 'learning_rate': 0.0001278, 'epoch': 0.69}
{'loss': 3.1823, 'grad_norm': 1.05746591091156, 'learning_rate': 0.0001281, 'epoch': 0.69}
{'loss': 2.9603, 'grad_norm': 1.2425645589828491, 'learning_rate': 0.00012839999999999998, 'epoch': 0.7}
{'loss': 2.9414, 'grad_norm': 1.2454054355621338, 'learning_rate': 0.00012869999999999998, 'epoch': 0.7}
{'loss': 3.1432, 'grad_norm': 0.9464673399925232, 'learning_rate': 0.000129, 'epoch': 0.7}
{'loss': 3.0063, 'grad_norm': 1.5856995582580566, 'learning_rate': 0.0001293, 'epoch': 0.7}
{'loss': 2.9146, 'grad_norm': 1.043485403060913, 'learning_rate': 0.00012959999999999998, 'epoch': 0.7}
{'loss': 2.9979, 'grad_norm': 1.240867257118225, 'learning_rate': 0.00012989999999999999, 'epoch': 0.7}
{'loss': 2.8699, 'grad_norm': 1.7289670705795288, 'learning_rate': 0.0001302, 'epoch': 0.71}
{'loss': 2.7802, 'grad_norm': 1.728317141532898, 'learning_rate': 0.0001305, 'epoch': 0.71}
{'loss': 2.9141, 'grad_norm': 0.960502028465271, 'learning_rate': 0.00013079999999999998, 'epoch': 0.71}
{'loss': 3.1318, 'grad_norm': 2.093698501586914, 'learning_rate': 0.0001311, 'epoch': 0.71}
{'loss': 2.9467, 'grad_norm': 1.6515812873840332, 'learning_rate': 0.0001314, 'epoch': 0.71}
{'loss': 2.7909, 'grad_norm': 1.4129968881607056, 'learning_rate': 0.00013169999999999998, 'epoch': 0.71}
{'loss': 3.1262, 'grad_norm': 1.5885038375854492, 'learning_rate': 0.00013199999999999998, 'epoch': 0.72}
{'loss': 3.2029, 'grad_norm': 1.222842812538147, 'learning_rate': 0.0001323, 'epoch': 0.72}
{'loss': 3.0013, 'grad_norm': 1.3282477855682373, 'learning_rate': 0.0001326, 'epoch': 0.72}
{'loss': 3.4352, 'grad_norm': nan, 'learning_rate': 0.0001326, 'epoch': 0.72}
{'loss': 4.3657, 'grad_norm': 27.799081802368164, 'learning_rate': 0.00013289999999999998, 'epoch': 0.72}
{'loss': 2.9244, 'grad_norm': 5.403924465179443, 'learning_rate': 0.00013319999999999999, 'epoch': 0.72}
{'loss': 2.927, 'grad_norm': 3.8071448802948, 'learning_rate': 0.0001335, 'epoch': 0.72}
{'loss': 2.9719, 'grad_norm': 3.504509210586548, 'learning_rate': 0.0001338, 'epoch': 0.73}
{'loss': 3.0386, 'grad_norm': 3.500847578048706, 'learning_rate': 0.00013409999999999998, 'epoch': 0.73}
{'loss': 2.9468, 'grad_norm': 3.5392863750457764, 'learning_rate': 0.0001344, 'epoch': 0.73}
{'loss': 2.7885, 'grad_norm': 5.1045732498168945, 'learning_rate': 0.0001347, 'epoch': 0.73}
{'loss': 2.9067, 'grad_norm': 6.027789115905762, 'learning_rate': 0.000135, 'epoch': 0.73}
{'loss': 2.8379, 'grad_norm': 5.094452381134033, 'learning_rate': 0.00013529999999999998, 'epoch': 0.73}
{'loss': 2.8325, 'grad_norm': 2.6457953453063965, 'learning_rate': 0.0001356, 'epoch': 0.74}
{'loss': 2.8004, 'grad_norm': 1.5734143257141113, 'learning_rate': 0.0001359, 'epoch': 0.74}
{'loss': 2.5294, 'grad_norm': 2.7408978939056396, 'learning_rate': 0.0001362, 'epoch': 0.74}
{'loss': 2.5774, 'grad_norm': 3.2462551593780518, 'learning_rate': 0.00013649999999999998, 'epoch': 0.74}
{'loss': 2.5412, 'grad_norm': 5.122827529907227, 'learning_rate': 0.0001368, 'epoch': 0.74}
{'loss': 2.5768, 'grad_norm': 6.828001976013184, 'learning_rate': 0.0001371, 'epoch': 0.74}
{'loss': 2.5803, 'grad_norm': 5.996628761291504, 'learning_rate': 0.0001374, 'epoch': 0.75}
{'loss': 2.3747, 'grad_norm': 3.842134714126587, 'learning_rate': 0.00013769999999999999, 'epoch': 0.75}
{'loss': 2.4186, 'grad_norm': 1.4524292945861816, 'learning_rate': 0.000138, 'epoch': 0.75}
{'loss': 2.3012, 'grad_norm': 1.6084707975387573, 'learning_rate': 0.0001383, 'epoch': 0.75}
{'loss': 2.442, 'grad_norm': 2.121351718902588, 'learning_rate': 0.0001386, 'epoch': 0.75}
{'loss': 2.2728, 'grad_norm': 1.5034464597702026, 'learning_rate': 0.0001389, 'epoch': 0.75}
{'loss': 2.3669, 'grad_norm': 1.2867931127548218, 'learning_rate': 0.0001392, 'epoch': 0.76}
{'loss': 2.3831, 'grad_norm': 1.8455201387405396, 'learning_rate': 0.0001395, 'epoch': 0.76}
{'loss': 2.6884, 'grad_norm': 1.4569259881973267, 'learning_rate': 0.00013979999999999998, 'epoch': 0.76}
{'loss': 2.4852, 'grad_norm': 1.9550684690475464, 'learning_rate': 0.0001401, 'epoch': 0.76}
{'loss': 2.5227, 'grad_norm': 2.876927137374878, 'learning_rate': 0.0001404, 'epoch': 0.76}
{'loss': 2.5994, 'grad_norm': 1.2651807069778442, 'learning_rate': 0.00014069999999999998, 'epoch': 0.76}
{'loss': 2.2933, 'grad_norm': 1.26189386844635, 'learning_rate': 0.00014099999999999998, 'epoch': 0.76}
{'loss': 2.3087, 'grad_norm': 1.3137550354003906, 'learning_rate': 0.0001413, 'epoch': 0.77}
{'loss': 2.4592, 'grad_norm': 1.7220642566680908, 'learning_rate': 0.00014159999999999997, 'epoch': 0.77}
{'loss': 2.0056, 'grad_norm': 1.3261381387710571, 'learning_rate': 0.00014189999999999998, 'epoch': 0.77}
{'loss': 2.2005, 'grad_norm': 2.571230173110962, 'learning_rate': 0.0001422, 'epoch': 0.77}
{'loss': 2.444, 'grad_norm': 1.9342719316482544, 'learning_rate': 0.0001425, 'epoch': 0.77}
{'loss': 2.5657, 'grad_norm': 1.9060297012329102, 'learning_rate': 0.00014279999999999997, 'epoch': 0.77}
{'loss': 2.2488, 'grad_norm': 1.7057262659072876, 'learning_rate': 0.00014309999999999998, 'epoch': 0.78}
{'loss': 2.3053, 'grad_norm': 1.5254745483398438, 'learning_rate': 0.0001434, 'epoch': 0.78}
{'loss': 2.7327, 'grad_norm': 1.2841426134109497, 'learning_rate': 0.00014369999999999997, 'epoch': 0.78}
{'loss': 2.1748, 'grad_norm': 1.2939062118530273, 'learning_rate': 0.00014399999999999998, 'epoch': 0.78}
{'loss': 2.2685, 'grad_norm': 1.041858434677124, 'learning_rate': 0.00014429999999999998, 'epoch': 0.78}
{'loss': 2.6499, 'grad_norm': 1.1529954671859741, 'learning_rate': 0.0001446, 'epoch': 0.78}
{'loss': 2.4287, 'grad_norm': 1.2997585535049438, 'learning_rate': 0.00014489999999999997, 'epoch': 0.79}
{'loss': 2.4024, 'grad_norm': 1.8214664459228516, 'learning_rate': 0.00014519999999999998, 'epoch': 0.79}
{'loss': 2.3568, 'grad_norm': 2.8641598224639893, 'learning_rate': 0.00014549999999999999, 'epoch': 0.79}
{'loss': 2.635, 'grad_norm': 2.793945789337158, 'learning_rate': 0.0001458, 'epoch': 0.79}
{'loss': 2.4789, 'grad_norm': 1.2558726072311401, 'learning_rate': 0.00014609999999999997, 'epoch': 0.79}
{'loss': 2.0977, 'grad_norm': 1.8537378311157227, 'learning_rate': 0.00014639999999999998, 'epoch': 0.79}
{'loss': 2.168, 'grad_norm': 1.3181400299072266, 'learning_rate': 0.0001467, 'epoch': 0.8}
{'loss': 3.4399, 'grad_norm': 9.861762046813965, 'learning_rate': 0.000147, 'epoch': 0.8}
{'loss': 2.4976, 'grad_norm': 2.7572944164276123, 'learning_rate': 0.00014729999999999998, 'epoch': 0.8}
{'loss': 3.0006, 'grad_norm': 3.072735071182251, 'learning_rate': 0.00014759999999999998, 'epoch': 0.8}
{'loss': 2.4371, 'grad_norm': 3.723292350769043, 'learning_rate': 0.0001479, 'epoch': 0.8}
{'loss': 3.0689, 'grad_norm': 5.342506408691406, 'learning_rate': 0.0001482, 'epoch': 0.8}
{'loss': 2.8854, 'grad_norm': 5.763881683349609, 'learning_rate': 0.00014849999999999998, 'epoch': 0.8}
{'loss': 2.4936, 'grad_norm': 1.8335249423980713, 'learning_rate': 0.00014879999999999998, 'epoch': 0.81}
{'loss': 2.4671, 'grad_norm': 2.8503644466400146, 'learning_rate': 0.0001491, 'epoch': 0.81}
{'loss': 2.2154, 'grad_norm': 5.93911600112915, 'learning_rate': 0.0001494, 'epoch': 0.81}
{'loss': 2.2564, 'grad_norm': 4.656365871429443, 'learning_rate': 0.00014969999999999998, 'epoch': 0.81}
{'loss': 2.4022, 'grad_norm': 4.47904109954834, 'learning_rate': 0.00015, 'epoch': 0.81}
{'loss': 1.9681, 'grad_norm': 2.0499017238616943, 'learning_rate': 0.0001503, 'epoch': 0.81}
{'loss': 2.0941, 'grad_norm': 1.0935138463974, 'learning_rate': 0.00015059999999999997, 'epoch': 0.82}
{'loss': 2.0268, 'grad_norm': 2.3944854736328125, 'learning_rate': 0.00015089999999999998, 'epoch': 0.82}
{'loss': 2.3145, 'grad_norm': 6.021939277648926, 'learning_rate': 0.0001512, 'epoch': 0.82}
{'loss': 2.038, 'grad_norm': 5.291767120361328, 'learning_rate': 0.0001515, 'epoch': 0.82}
{'loss': 1.8124, 'grad_norm': 4.051759719848633, 'learning_rate': 0.00015179999999999998, 'epoch': 0.82}
{'loss': 2.114, 'grad_norm': 6.387513637542725, 'learning_rate': 0.00015209999999999998, 'epoch': 0.82}
{'loss': 1.9412, 'grad_norm': 3.993975877761841, 'learning_rate': 0.0001524, 'epoch': 0.83}
{'loss': 1.8678, 'grad_norm': 2.036212682723999, 'learning_rate': 0.0001527, 'epoch': 0.83}
{'loss': 2.1287, 'grad_norm': 1.404420256614685, 'learning_rate': 0.00015299999999999998, 'epoch': 0.83}
{'loss': 1.9134, 'grad_norm': 1.0048662424087524, 'learning_rate': 0.00015329999999999999, 'epoch': 0.83}
{'loss': 1.8799, 'grad_norm': 2.347856044769287, 'learning_rate': 0.0001536, 'epoch': 0.83}
{'loss': 1.9441, 'grad_norm': 3.0598201751708984, 'learning_rate': 0.0001539, 'epoch': 0.83}
{'loss': 1.7355, 'grad_norm': 2.636126756668091, 'learning_rate': 0.00015419999999999998, 'epoch': 0.84}
{'loss': 1.9851, 'grad_norm': 1.8599352836608887, 'learning_rate': 0.0001545, 'epoch': 0.84}
{'loss': 1.7774, 'grad_norm': 0.9748109579086304, 'learning_rate': 0.0001548, 'epoch': 0.84}
{'loss': 2.1997, 'grad_norm': 1.414323091506958, 'learning_rate': 0.0001551, 'epoch': 0.84}
{'loss': 2.0179, 'grad_norm': 2.8852648735046387, 'learning_rate': 0.00015539999999999998, 'epoch': 0.84}
{'loss': 1.9451, 'grad_norm': 2.0136239528656006, 'learning_rate': 0.0001557, 'epoch': 0.84}
{'loss': 1.7522, 'grad_norm': 2.07312273979187, 'learning_rate': 0.000156, 'epoch': 0.84}
{'loss': 1.6561, 'grad_norm': 1.4143507480621338, 'learning_rate': 0.0001563, 'epoch': 0.85}
{'loss': 1.913, 'grad_norm': 3.017238140106201, 'learning_rate': 0.00015659999999999998, 'epoch': 0.85}
{'loss': 1.8592, 'grad_norm': 0.9368352293968201, 'learning_rate': 0.0001569, 'epoch': 0.85}
{'loss': 2.2341, 'grad_norm': 1.308072566986084, 'learning_rate': 0.0001572, 'epoch': 0.85}
{'loss': 1.9506, 'grad_norm': 2.2798593044281006, 'learning_rate': 0.00015749999999999998, 'epoch': 0.85}
{'loss': 1.9343, 'grad_norm': 2.6132118701934814, 'learning_rate': 0.0001578, 'epoch': 0.85}
{'loss': 1.9341, 'grad_norm': 1.162194848060608, 'learning_rate': 0.0001581, 'epoch': 0.86}
{'loss': 1.7395, 'grad_norm': 1.3427730798721313, 'learning_rate': 0.0001584, 'epoch': 0.86}
{'loss': 2.3282, 'grad_norm': 2.1670310497283936, 'learning_rate': 0.00015869999999999998, 'epoch': 0.86}
{'loss': 2.09, 'grad_norm': 1.257582187652588, 'learning_rate': 0.000159, 'epoch': 0.86}
{'loss': 1.8402, 'grad_norm': 1.4573386907577515, 'learning_rate': 0.0001593, 'epoch': 0.86}
{'loss': 1.7193, 'grad_norm': 1.3384615182876587, 'learning_rate': 0.0001596, 'epoch': 0.86}
{'loss': 1.5656, 'grad_norm': 2.220402479171753, 'learning_rate': 0.00015989999999999998, 'epoch': 0.87}
{'loss': 2.0628, 'grad_norm': 2.4653773307800293, 'learning_rate': 0.0001602, 'epoch': 0.87}
{'loss': 1.8363, 'grad_norm': 1.280678391456604, 'learning_rate': 0.0001605, 'epoch': 0.87}
{'loss': 1.7545, 'grad_norm': 2.4655933380126953, 'learning_rate': 0.0001608, 'epoch': 0.87}
{'loss': 1.8381, 'grad_norm': 1.506415605545044, 'learning_rate': 0.00016109999999999999, 'epoch': 0.87}
{'loss': 1.829, 'grad_norm': 1.1475555896759033, 'learning_rate': 0.0001614, 'epoch': 0.87}
{'loss': 1.8184, 'grad_norm': 1.4434545040130615, 'learning_rate': 0.0001617, 'epoch': 0.88}
{'loss': 1.9946, 'grad_norm': 1.8260152339935303, 'learning_rate': 0.000162, 'epoch': 0.88}
{'loss': 2.031, 'grad_norm': 1.8104926347732544, 'learning_rate': 0.0001623, 'epoch': 0.88}
{'loss': 2.2711, 'grad_norm': 2.094877243041992, 'learning_rate': 0.0001626, 'epoch': 0.88}
{'loss': 4.8174, 'grad_norm': 23.733247756958008, 'learning_rate': 0.0001629, 'epoch': 0.88}
{'loss': 3.3335, 'grad_norm': 12.243576049804688, 'learning_rate': 0.0001632, 'epoch': 0.88}
{'loss': 2.3234, 'grad_norm': 3.982137441635132, 'learning_rate': 0.0001635, 'epoch': 0.88}
{'loss': 2.1768, 'grad_norm': 2.5422203540802, 'learning_rate': 0.0001638, 'epoch': 0.89}
{'loss': 2.022, 'grad_norm': 2.649517059326172, 'learning_rate': 0.0001641, 'epoch': 0.89}
{'loss': 1.8511, 'grad_norm': 4.723710536956787, 'learning_rate': 0.0001644, 'epoch': 0.89}
{'loss': 1.9528, 'grad_norm': 2.3035788536071777, 'learning_rate': 0.0001647, 'epoch': 0.89}
{'loss': 1.9104, 'grad_norm': 3.8410518169403076, 'learning_rate': 0.000165, 'epoch': 0.89}
{'loss': 1.7834, 'grad_norm': 3.0108225345611572, 'learning_rate': 0.0001653, 'epoch': 0.89}
{'loss': 1.883, 'grad_norm': 1.3487671613693237, 'learning_rate': 0.0001656, 'epoch': 0.9}
{'loss': 1.5688, 'grad_norm': 1.061733365058899, 'learning_rate': 0.0001659, 'epoch': 0.9}
{'loss': 1.6914, 'grad_norm': 2.0784027576446533, 'learning_rate': 0.0001662, 'epoch': 0.9}
{'loss': 2.3407, 'grad_norm': 6.085043907165527, 'learning_rate': 0.0001665, 'epoch': 0.9}
{'loss': 1.7104, 'grad_norm': 1.459148645401001, 'learning_rate': 0.0001668, 'epoch': 0.9}
{'loss': 1.5955, 'grad_norm': 1.9622076749801636, 'learning_rate': 0.0001671, 'epoch': 0.9}
{'loss': 1.4071, 'grad_norm': 1.2756608724594116, 'learning_rate': 0.0001674, 'epoch': 0.91}
{'loss': 1.6557, 'grad_norm': 0.940319299697876, 'learning_rate': 0.0001677, 'epoch': 0.91}
{'loss': 1.774, 'grad_norm': 0.9497667551040649, 'learning_rate': 0.000168, 'epoch': 0.91}
{'loss': 1.8378, 'grad_norm': 1.1930807828903198, 'learning_rate': 0.0001683, 'epoch': 0.91}
{'loss': 1.6816, 'grad_norm': 1.7330429553985596, 'learning_rate': 0.0001686, 'epoch': 0.91}
{'loss': 1.6782, 'grad_norm': 0.9604584574699402, 'learning_rate': 0.00016889999999999996, 'epoch': 0.91}
{'loss': 1.5947, 'grad_norm': 0.9503042101860046, 'learning_rate': 0.00016919999999999997, 'epoch': 0.92}
{'loss': 1.6978, 'grad_norm': 1.1088024377822876, 'learning_rate': 0.00016949999999999997, 'epoch': 0.92}
{'loss': 1.656, 'grad_norm': 1.118318796157837, 'learning_rate': 0.00016979999999999998, 'epoch': 0.92}
{'loss': 1.6588, 'grad_norm': 1.5163230895996094, 'learning_rate': 0.00017009999999999996, 'epoch': 0.92}
{'loss': 1.9119, 'grad_norm': 1.4612356424331665, 'learning_rate': 0.00017039999999999997, 'epoch': 0.92}
{'loss': 1.4299, 'grad_norm': 1.2807903289794922, 'learning_rate': 0.00017069999999999998, 'epoch': 0.92}
{'loss': 1.3226, 'grad_norm': 1.049907922744751, 'learning_rate': 0.00017099999999999998, 'epoch': 0.92}
{'loss': 1.8021, 'grad_norm': 1.0162078142166138, 'learning_rate': 0.00017129999999999996, 'epoch': 0.93}
{'loss': 1.6087, 'grad_norm': 1.3673537969589233, 'learning_rate': 0.00017159999999999997, 'epoch': 0.93}
{'loss': 1.6225, 'grad_norm': 1.2779172658920288, 'learning_rate': 0.00017189999999999998, 'epoch': 0.93}
{'loss': 1.5889, 'grad_norm': 1.2135735750198364, 'learning_rate': 0.00017219999999999998, 'epoch': 0.93}
{'loss': 2.1697, 'grad_norm': 1.45180344581604, 'learning_rate': 0.00017249999999999996, 'epoch': 0.93}
{'loss': 1.79, 'grad_norm': 1.1630367040634155, 'learning_rate': 0.00017279999999999997, 'epoch': 0.93}
{'loss': 1.5455, 'grad_norm': 2.428530693054199, 'learning_rate': 0.00017309999999999998, 'epoch': 0.94}
{'loss': 1.7658, 'grad_norm': 1.3975725173950195, 'learning_rate': 0.00017339999999999996, 'epoch': 0.94}
{'loss': 1.8039, 'grad_norm': 1.242210865020752, 'learning_rate': 0.00017369999999999997, 'epoch': 0.94}
{'loss': 1.7215, 'grad_norm': 1.071577787399292, 'learning_rate': 0.00017399999999999997, 'epoch': 0.94}
{'loss': 1.8733, 'grad_norm': 1.208039402961731, 'learning_rate': 0.00017429999999999998, 'epoch': 0.94}
{'loss': 1.4408, 'grad_norm': 1.5233865976333618, 'learning_rate': 0.00017459999999999996, 'epoch': 0.94}
{'loss': 1.8393, 'grad_norm': 1.411783218383789, 'learning_rate': 0.00017489999999999997, 'epoch': 0.95}
{'loss': 1.679, 'grad_norm': 1.629401683807373, 'learning_rate': 0.00017519999999999998, 'epoch': 0.95}
{'loss': 1.9937, 'grad_norm': 1.487720012664795, 'learning_rate': 0.00017549999999999998, 'epoch': 0.95}
{'loss': 1.8585, 'grad_norm': 1.7428632974624634, 'learning_rate': 0.00017579999999999996, 'epoch': 0.95}
{'loss': 1.758, 'grad_norm': 1.5290313959121704, 'learning_rate': 0.00017609999999999997, 'epoch': 0.95}
{'loss': 1.6403, 'grad_norm': 1.4210582971572876, 'learning_rate': 0.00017639999999999998, 'epoch': 0.95}
{'loss': 2.0706, 'grad_norm': 1.487386703491211, 'learning_rate': 0.00017669999999999999, 'epoch': 0.96}
{'loss': 2.0324, 'grad_norm': 1.789679765701294, 'learning_rate': 0.00017699999999999997, 'epoch': 0.96}
{'loss': 2.4765, 'grad_norm': 3.552408456802368, 'learning_rate': 0.00017729999999999997, 'epoch': 0.96}
{'loss': 2.49, 'grad_norm': 2.6970980167388916, 'learning_rate': 0.00017759999999999998, 'epoch': 0.96}
{'loss': 2.2124, 'grad_norm': 6.3989667892456055, 'learning_rate': 0.0001779, 'epoch': 0.96}
{'loss': 1.9114, 'grad_norm': 3.559483528137207, 'learning_rate': 0.00017819999999999997, 'epoch': 0.96}
{'loss': 1.7274, 'grad_norm': 2.688811779022217, 'learning_rate': 0.00017849999999999997, 'epoch': 0.96}
{'loss': 1.5342, 'grad_norm': 1.4167048931121826, 'learning_rate': 0.00017879999999999998, 'epoch': 0.97}
{'loss': 1.6476, 'grad_norm': 1.0234233140945435, 'learning_rate': 0.0001791, 'epoch': 0.97}
{'loss': 1.8034, 'grad_norm': 2.3607473373413086, 'learning_rate': 0.00017939999999999997, 'epoch': 0.97}
{'loss': 1.2502, 'grad_norm': 1.8193793296813965, 'learning_rate': 0.00017969999999999998, 'epoch': 0.97}
{'loss': 1.7518, 'grad_norm': 2.5050389766693115, 'learning_rate': 0.00017999999999999998, 'epoch': 0.97}
{'loss': 2.2657, 'grad_norm': 1.852980375289917, 'learning_rate': 0.00018029999999999996, 'epoch': 0.97}
{'loss': 1.6213, 'grad_norm': 1.1846544742584229, 'learning_rate': 0.00018059999999999997, 'epoch': 0.98}
{'loss': 1.5566, 'grad_norm': 1.1806446313858032, 'learning_rate': 0.00018089999999999998, 'epoch': 0.98}
{'loss': 1.4004, 'grad_norm': 0.9722961187362671, 'learning_rate': 0.00018119999999999999, 'epoch': 0.98}
{'loss': 1.9613, 'grad_norm': 1.2534488439559937, 'learning_rate': 0.00018149999999999997, 'epoch': 0.98}
{'loss': 1.3668, 'grad_norm': 1.55427885055542, 'learning_rate': 0.00018179999999999997, 'epoch': 0.98}
{'loss': 1.153, 'grad_norm': 1.8559104204177856, 'learning_rate': 0.00018209999999999998, 'epoch': 0.98}
{'loss': 1.6635, 'grad_norm': 1.3127942085266113, 'learning_rate': 0.0001824, 'epoch': 0.99}
{'loss': 1.5436, 'grad_norm': 1.3206202983856201, 'learning_rate': 0.00018269999999999997, 'epoch': 0.99}
{'loss': 1.6072, 'grad_norm': 1.0405744314193726, 'learning_rate': 0.00018299999999999998, 'epoch': 0.99}
{'loss': 1.3522, 'grad_norm': 1.1208364963531494, 'learning_rate': 0.00018329999999999998, 'epoch': 0.99}
{'loss': 1.8288, 'grad_norm': 1.4611485004425049, 'learning_rate': 0.0001836, 'epoch': 0.99}
{'loss': 2.2311, 'grad_norm': 2.102464199066162, 'learning_rate': 0.00018389999999999997, 'epoch': 0.99}
{'loss': 1.6955, 'grad_norm': 1.3121858835220337, 'learning_rate': 0.00018419999999999998, 'epoch': 1.0}
{'loss': 2.066, 'grad_norm': 1.732784390449524, 'learning_rate': 0.00018449999999999999, 'epoch': 1.0}
{'loss': 1.7517, 'grad_norm': 1.474577784538269, 'learning_rate': 0.0001848, 'epoch': 1.0}
{'loss': 2.8279, 'grad_norm': nan, 'learning_rate': 0.0001848, 'epoch': 1.0}
{'loss': 4.359, 'grad_norm': 21.10396385192871, 'learning_rate': 0.00018509999999999997, 'epoch': 1.0}
{'loss': 1.5803, 'grad_norm': 2.5289759635925293, 'learning_rate': 0.00018539999999999998, 'epoch': 1.0}
{'loss': 4.1665, 'grad_norm': 17.63152503967285, 'learning_rate': 0.0001857, 'epoch': 1.0}
{'loss': 1.5211, 'grad_norm': 1.2565017938613892, 'learning_rate': 0.000186, 'epoch': 1.01}
{'loss': 1.6206, 'grad_norm': 0.9237573146820068, 'learning_rate': 0.00018629999999999997, 'epoch': 1.01}
{'loss': 1.7635, 'grad_norm': 1.304307222366333, 'learning_rate': 0.00018659999999999998, 'epoch': 1.01}
{'loss': 1.4183, 'grad_norm': 2.240795850753784, 'learning_rate': 0.0001869, 'epoch': 1.01}
{'loss': 1.8278, 'grad_norm': 1.2945712804794312, 'learning_rate': 0.0001872, 'epoch': 1.01}
{'loss': 1.8362, 'grad_norm': 2.4284050464630127, 'learning_rate': 0.00018749999999999998, 'epoch': 1.01}
{'loss': 1.3312, 'grad_norm': 1.5324746370315552, 'learning_rate': 0.00018779999999999998, 'epoch': 1.02}
{'loss': 1.5771, 'grad_norm': 0.9457862973213196, 'learning_rate': 0.0001881, 'epoch': 1.02}
{'loss': 1.3939, 'grad_norm': 1.761409878730774, 'learning_rate': 0.00018839999999999997, 'epoch': 1.02}
{'loss': 1.305, 'grad_norm': 2.4509124755859375, 'learning_rate': 0.00018869999999999998, 'epoch': 1.02}
{'loss': 1.2198, 'grad_norm': 1.434770941734314, 'learning_rate': 0.00018899999999999999, 'epoch': 1.02}
{'loss': 1.4401, 'grad_norm': 1.683680772781372, 'learning_rate': 0.0001893, 'epoch': 1.02}
{'loss': 1.3005, 'grad_norm': 1.468677282333374, 'learning_rate': 0.00018959999999999997, 'epoch': 1.03}
{'loss': 1.6153, 'grad_norm': 2.2306525707244873, 'learning_rate': 0.00018989999999999998, 'epoch': 1.03}
{'loss': 2.2058, 'grad_norm': 4.796661853790283, 'learning_rate': 0.0001902, 'epoch': 1.03}
{'loss': 1.3829, 'grad_norm': 1.139748454093933, 'learning_rate': 0.0001905, 'epoch': 1.03}
{'loss': 1.5598, 'grad_norm': 1.9971469640731812, 'learning_rate': 0.00019079999999999998, 'epoch': 1.03}
{'loss': 1.3654, 'grad_norm': 2.224128007888794, 'learning_rate': 0.00019109999999999998, 'epoch': 1.03}
{'loss': 1.6379, 'grad_norm': 2.5159313678741455, 'learning_rate': 0.0001914, 'epoch': 1.04}
{'loss': 1.5734, 'grad_norm': 1.9604592323303223, 'learning_rate': 0.0001917, 'epoch': 1.04}
{'loss': 1.1349, 'grad_norm': 1.4151877164840698, 'learning_rate': 0.00019199999999999998, 'epoch': 1.04}
{'loss': 1.7592, 'grad_norm': 1.21165931224823, 'learning_rate': 0.00019229999999999999, 'epoch': 1.04}
{'loss': 1.505, 'grad_norm': 2.344447135925293, 'learning_rate': 0.0001926, 'epoch': 1.04}
{'loss': 1.6673, 'grad_norm': 2.5432910919189453, 'learning_rate': 0.0001929, 'epoch': 1.04}
{'loss': 1.6617, 'grad_norm': 1.5895689725875854, 'learning_rate': 0.00019319999999999998, 'epoch': 1.04}
{'loss': 1.6216, 'grad_norm': 1.7360563278198242, 'learning_rate': 0.0001935, 'epoch': 1.05}
{'loss': 1.257, 'grad_norm': 1.3723790645599365, 'learning_rate': 0.0001938, 'epoch': 1.05}
{'loss': 1.4356, 'grad_norm': 0.8750591278076172, 'learning_rate': 0.0001941, 'epoch': 1.05}
{'loss': 1.346, 'grad_norm': 1.407861590385437, 'learning_rate': 0.00019439999999999998, 'epoch': 1.05}
{'loss': 1.2363, 'grad_norm': 1.2812424898147583, 'learning_rate': 0.0001947, 'epoch': 1.05}
{'loss': 1.4353, 'grad_norm': 1.2920845746994019, 'learning_rate': 0.000195, 'epoch': 1.05}
{'loss': 1.5272, 'grad_norm': 1.0122877359390259, 'learning_rate': 0.00019529999999999998, 'epoch': 1.06}
{'loss': 1.1926, 'grad_norm': 1.0607578754425049, 'learning_rate': 0.00019559999999999998, 'epoch': 1.06}
{'loss': 1.361, 'grad_norm': 1.2849078178405762, 'learning_rate': 0.0001959, 'epoch': 1.06}
{'loss': 1.4892, 'grad_norm': 2.199488401412964, 'learning_rate': 0.0001962, 'epoch': 1.06}
{'loss': 1.4795, 'grad_norm': 1.7300806045532227, 'learning_rate': 0.00019649999999999998, 'epoch': 1.06}
{'loss': 1.6863, 'grad_norm': 1.210700273513794, 'learning_rate': 0.00019679999999999999, 'epoch': 1.06}
{'loss': 1.3863, 'grad_norm': 1.1998845338821411, 'learning_rate': 0.0001971, 'epoch': 1.07}
{'loss': 1.9558, 'grad_norm': 1.5421574115753174, 'learning_rate': 0.0001974, 'epoch': 1.07}
{'loss': 1.3471, 'grad_norm': 2.3596279621124268, 'learning_rate': 0.00019769999999999998, 'epoch': 1.07}
{'loss': 1.3686, 'grad_norm': 1.3288168907165527, 'learning_rate': 0.000198, 'epoch': 1.07}
{'loss': 1.6142, 'grad_norm': 1.5977771282196045, 'learning_rate': 0.0001983, 'epoch': 1.07}
{'loss': 1.8817, 'grad_norm': 1.171886682510376, 'learning_rate': 0.0001986, 'epoch': 1.07}
{'loss': 1.502, 'grad_norm': 1.4820473194122314, 'learning_rate': 0.00019889999999999998, 'epoch': 1.08}
{'loss': 1.9869, 'grad_norm': 1.4286924600601196, 'learning_rate': 0.0001992, 'epoch': 1.08}
{'loss': 1.5545, 'grad_norm': 1.496476650238037, 'learning_rate': 0.0001995, 'epoch': 1.08}
{'loss': 3.5297, 'grad_norm': 11.650896072387695, 'learning_rate': 0.0001998, 'epoch': 1.08}
{'loss': 3.5244, 'grad_norm': 10.930564880371094, 'learning_rate': 0.00020009999999999998, 'epoch': 1.08}
{'loss': 1.948, 'grad_norm': 4.526219367980957, 'learning_rate': 0.0002004, 'epoch': 1.08}
{'loss': 1.6832, 'grad_norm': 1.8217471837997437, 'learning_rate': 0.0002007, 'epoch': 1.08}
{'loss': 2.3308, 'grad_norm': 2.5544323921203613, 'learning_rate': 0.000201, 'epoch': 1.09}
{'loss': 1.7663, 'grad_norm': 2.732450246810913, 'learning_rate': 0.0002013, 'epoch': 1.09}
{'loss': 1.9597, 'grad_norm': 4.002326488494873, 'learning_rate': 0.0002016, 'epoch': 1.09}
{'loss': 1.6625, 'grad_norm': 2.9579389095306396, 'learning_rate': 0.0002019, 'epoch': 1.09}
{'loss': 1.4949, 'grad_norm': 3.6762917041778564, 'learning_rate': 0.0002022, 'epoch': 1.09}
{'loss': 1.5695, 'grad_norm': 2.8355441093444824, 'learning_rate': 0.0002025, 'epoch': 1.09}
{'loss': 1.5717, 'grad_norm': 2.894350290298462, 'learning_rate': 0.0002028, 'epoch': 1.1}
{'loss': 1.7573, 'grad_norm': 4.992308616638184, 'learning_rate': 0.0002031, 'epoch': 1.1}
{'loss': 1.2767, 'grad_norm': 1.175133466720581, 'learning_rate': 0.00020339999999999998, 'epoch': 1.1}
{'loss': 1.4346, 'grad_norm': 0.7449688911437988, 'learning_rate': 0.0002037, 'epoch': 1.1}
{'loss': 1.5286, 'grad_norm': 2.100440740585327, 'learning_rate': 0.000204, 'epoch': 1.1}
{'loss': 1.4716, 'grad_norm': 1.06446373462677, 'learning_rate': 0.0002043, 'epoch': 1.1}
{'loss': 1.729, 'grad_norm': 1.1813894510269165, 'learning_rate': 0.00020459999999999999, 'epoch': 1.11}
{'loss': 1.5456, 'grad_norm': 1.2244285345077515, 'learning_rate': 0.0002049, 'epoch': 1.11}
{'loss': 1.6253, 'grad_norm': 1.395920991897583, 'learning_rate': 0.0002052, 'epoch': 1.11}
{'loss': 1.3474, 'grad_norm': 0.8973720073699951, 'learning_rate': 0.0002055, 'epoch': 1.11}
{'loss': 1.5375, 'grad_norm': 0.9351361393928528, 'learning_rate': 0.0002058, 'epoch': 1.11}
{'loss': 1.2332, 'grad_norm': 0.9488412737846375, 'learning_rate': 0.0002061, 'epoch': 1.11}
{'loss': 1.3265, 'grad_norm': 0.800336480140686, 'learning_rate': 0.00020639999999999998, 'epoch': 1.12}
{'loss': 1.3347, 'grad_norm': 1.771794319152832, 'learning_rate': 0.00020669999999999996, 'epoch': 1.12}
{'loss': 1.783, 'grad_norm': 3.4581542015075684, 'learning_rate': 0.00020699999999999996, 'epoch': 1.12}
{'loss': 1.3295, 'grad_norm': 0.837477445602417, 'learning_rate': 0.00020729999999999997, 'epoch': 1.12}
{'loss': 1.4163, 'grad_norm': 2.1295042037963867, 'learning_rate': 0.00020759999999999998, 'epoch': 1.12}
{'loss': 1.2891, 'grad_norm': 1.0342674255371094, 'learning_rate': 0.00020789999999999996, 'epoch': 1.12}
{'loss': 1.5386, 'grad_norm': 1.1783955097198486, 'learning_rate': 0.00020819999999999996, 'epoch': 1.12}
{'loss': 1.5942, 'grad_norm': 2.5988528728485107, 'learning_rate': 0.00020849999999999997, 'epoch': 1.13}
{'loss': 1.4828, 'grad_norm': 1.206281065940857, 'learning_rate': 0.00020879999999999998, 'epoch': 1.13}
{'loss': 1.6748, 'grad_norm': 1.60711669921875, 'learning_rate': 0.00020909999999999996, 'epoch': 1.13}
{'loss': 1.4464, 'grad_norm': 1.3890515565872192, 'learning_rate': 0.00020939999999999997, 'epoch': 1.13}
{'loss': 1.9039, 'grad_norm': 1.4788490533828735, 'learning_rate': 0.00020969999999999997, 'epoch': 1.13}
{'loss': 1.5258, 'grad_norm': 0.9197102189064026, 'learning_rate': 0.00020999999999999998, 'epoch': 1.13}
{'loss': 1.6637, 'grad_norm': 3.082664728164673, 'learning_rate': 0.00021029999999999996, 'epoch': 1.14}
{'loss': 1.3499, 'grad_norm': 1.3979014158248901, 'learning_rate': 0.00021059999999999997, 'epoch': 1.14}
{'loss': 1.7379, 'grad_norm': 2.7370402812957764, 'learning_rate': 0.00021089999999999998, 'epoch': 1.14}
{'loss': 1.3235, 'grad_norm': 1.36969792842865, 'learning_rate': 0.00021119999999999996, 'epoch': 1.14}
{'loss': 1.2209, 'grad_norm': 1.3009356260299683, 'learning_rate': 0.00021149999999999996, 'epoch': 1.14}
{'loss': 1.237, 'grad_norm': 1.0813698768615723, 'learning_rate': 0.00021179999999999997, 'epoch': 1.14}
{'loss': 1.5799, 'grad_norm': 1.2386032342910767, 'learning_rate': 0.00021209999999999998, 'epoch': 1.15}
{'loss': 1.852, 'grad_norm': 1.7847639322280884, 'learning_rate': 0.00021239999999999996, 'epoch': 1.15}
{'loss': 1.7199, 'grad_norm': 1.4111274480819702, 'learning_rate': 0.00021269999999999997, 'epoch': 1.15}
{'loss': 1.6921, 'grad_norm': 1.6253108978271484, 'learning_rate': 0.00021299999999999997, 'epoch': 1.15}
{'loss': 1.5512, 'grad_norm': 1.3691827058792114, 'learning_rate': 0.00021329999999999998, 'epoch': 1.15}
{'loss': 1.6953, 'grad_norm': 1.0425063371658325, 'learning_rate': 0.00021359999999999996, 'epoch': 1.15}
{'loss': 1.2235, 'grad_norm': 1.5456832647323608, 'learning_rate': 0.00021389999999999997, 'epoch': 1.16}
{'loss': 2.3722, 'grad_norm': 5.289543151855469, 'learning_rate': 0.00021419999999999998, 'epoch': 1.16}
{'loss': 1.7361, 'grad_norm': 3.060047149658203, 'learning_rate': 0.00021449999999999998, 'epoch': 1.16}
{'loss': 2.2835, 'grad_norm': 2.2316486835479736, 'learning_rate': 0.00021479999999999996, 'epoch': 1.16}
{'loss': 2.8832, 'grad_norm': 11.319620132446289, 'learning_rate': 0.00021509999999999997, 'epoch': 1.16}
{'loss': 2.4756, 'grad_norm': 4.8169121742248535, 'learning_rate': 0.00021539999999999998, 'epoch': 1.16}
{'loss': 2.5684, 'grad_norm': 4.998867511749268, 'learning_rate': 0.00021569999999999998, 'epoch': 1.16}
{'loss': 1.9992, 'grad_norm': 1.6369566917419434, 'learning_rate': 0.00021599999999999996, 'epoch': 1.17}
{'loss': 1.6888, 'grad_norm': 4.867010593414307, 'learning_rate': 0.00021629999999999997, 'epoch': 1.17}
{'loss': 1.703, 'grad_norm': 4.665241241455078, 'learning_rate': 0.00021659999999999998, 'epoch': 1.17}
{'loss': 1.8941, 'grad_norm': 4.923267364501953, 'learning_rate': 0.0002169, 'epoch': 1.17}
{'loss': 1.8063, 'grad_norm': 5.301763534545898, 'learning_rate': 0.00021719999999999997, 'epoch': 1.17}
{'loss': 1.6896, 'grad_norm': 5.480170726776123, 'learning_rate': 0.00021749999999999997, 'epoch': 1.17}
{'loss': 1.7705, 'grad_norm': 5.136298656463623, 'learning_rate': 0.00021779999999999998, 'epoch': 1.18}
{'loss': 1.29, 'grad_norm': 2.6885194778442383, 'learning_rate': 0.00021809999999999996, 'epoch': 1.18}
{'loss': 1.8537, 'grad_norm': 1.7481634616851807, 'learning_rate': 0.00021839999999999997, 'epoch': 1.18}
{'loss': 1.3772, 'grad_norm': 2.1533167362213135, 'learning_rate': 0.00021869999999999998, 'epoch': 1.18}
{'loss': 1.2517, 'grad_norm': 1.7290595769882202, 'learning_rate': 0.00021899999999999998, 'epoch': 1.18}
{'loss': 1.9578, 'grad_norm': 5.765242576599121, 'learning_rate': 0.00021929999999999996, 'epoch': 1.18}
{'loss': 1.6263, 'grad_norm': 5.171415328979492, 'learning_rate': 0.00021959999999999997, 'epoch': 1.19}
{'loss': 1.5452, 'grad_norm': 2.4269332885742188, 'learning_rate': 0.00021989999999999998, 'epoch': 1.19}
{'loss': 1.2282, 'grad_norm': 1.2465523481369019, 'learning_rate': 0.00022019999999999999, 'epoch': 1.19}
{'loss': 1.1983, 'grad_norm': 1.9669184684753418, 'learning_rate': 0.00022049999999999997, 'epoch': 1.19}
{'loss': 1.7768, 'grad_norm': 5.07749605178833, 'learning_rate': 0.00022079999999999997, 'epoch': 1.19}
{'loss': 1.504, 'grad_norm': 1.4985103607177734, 'learning_rate': 0.00022109999999999998, 'epoch': 1.19}
{'loss': 1.2868, 'grad_norm': 0.8555597066879272, 'learning_rate': 0.0002214, 'epoch': 1.2}
{'loss': 1.5408, 'grad_norm': 1.0134530067443848, 'learning_rate': 0.00022169999999999997, 'epoch': 1.2}
{'loss': 1.4542, 'grad_norm': 2.2932121753692627, 'learning_rate': 0.00022199999999999998, 'epoch': 1.2}
{'loss': 1.6303, 'grad_norm': 2.048572063446045, 'learning_rate': 0.00022229999999999998, 'epoch': 1.2}
{'loss': 1.6202, 'grad_norm': 1.3398712873458862, 'learning_rate': 0.0002226, 'epoch': 1.2}
{'loss': 1.114, 'grad_norm': 1.2826422452926636, 'learning_rate': 0.00022289999999999997, 'epoch': 1.2}
{'loss': 1.2535, 'grad_norm': 0.9887292385101318, 'learning_rate': 0.00022319999999999998, 'epoch': 1.2}
{'loss': 1.123, 'grad_norm': 0.8880885243415833, 'learning_rate': 0.00022349999999999998, 'epoch': 1.21}
{'loss': 1.7848, 'grad_norm': 4.056207180023193, 'learning_rate': 0.0002238, 'epoch': 1.21}
{'loss': 1.6084, 'grad_norm': 1.0242630243301392, 'learning_rate': 0.00022409999999999997, 'epoch': 1.21}
{'loss': 1.0884, 'grad_norm': 1.5216087102890015, 'learning_rate': 0.00022439999999999998, 'epoch': 1.21}
{'loss': 1.4366, 'grad_norm': 1.1595895290374756, 'learning_rate': 0.0002247, 'epoch': 1.21}
{'loss': 1.4678, 'grad_norm': 1.78994619846344, 'learning_rate': 0.000225, 'epoch': 1.21}
{'loss': 1.5742, 'grad_norm': 1.5748515129089355, 'learning_rate': 0.00022529999999999997, 'epoch': 1.22}
{'loss': 1.2028, 'grad_norm': 1.2527673244476318, 'learning_rate': 0.00022559999999999998, 'epoch': 1.22}
{'loss': 1.8887, 'grad_norm': 1.4951261281967163, 'learning_rate': 0.0002259, 'epoch': 1.22}
{'loss': 1.6479, 'grad_norm': 1.1303513050079346, 'learning_rate': 0.00022619999999999997, 'epoch': 1.22}
{'loss': 1.703, 'grad_norm': 1.3236031532287598, 'learning_rate': 0.00022649999999999998, 'epoch': 1.22}
{'loss': 1.8706, 'grad_norm': 1.5853848457336426, 'learning_rate': 0.00022679999999999998, 'epoch': 1.22}
{'loss': 1.495, 'grad_norm': 2.0144317150115967, 'learning_rate': 0.0002271, 'epoch': 1.23}
{'loss': 1.6167, 'grad_norm': 1.472916841506958, 'learning_rate': 0.00022739999999999997, 'epoch': 1.23}
{'loss': 1.5432, 'grad_norm': 1.3060656785964966, 'learning_rate': 0.00022769999999999998, 'epoch': 1.23}
{'loss': 2.3, 'grad_norm': 1.9118512868881226, 'learning_rate': 0.00022799999999999999, 'epoch': 1.23}
{'loss': 1.3154, 'grad_norm': 1.5411431789398193, 'learning_rate': 0.0002283, 'epoch': 1.23}
{'loss': 1.3445, 'grad_norm': 1.2540593147277832, 'learning_rate': 0.00022859999999999997, 'epoch': 1.23}
{'loss': 1.7902, 'grad_norm': 1.74718177318573, 'learning_rate': 0.00022889999999999998, 'epoch': 1.24}
{'loss': 1.7406, 'grad_norm': 1.5919808149337769, 'learning_rate': 0.0002292, 'epoch': 1.24}
{'loss': 2.3024, 'grad_norm': 2.1802892684936523, 'learning_rate': 0.0002295, 'epoch': 1.24}
{'loss': 2.2887, 'grad_norm': nan, 'learning_rate': 0.0002295, 'epoch': 1.24}
{'loss': 2.6305, 'grad_norm': 5.746895790100098, 'learning_rate': 0.00022979999999999997, 'epoch': 1.24}
{'loss': 2.3811, 'grad_norm': 5.819034099578857, 'learning_rate': 0.00023009999999999998, 'epoch': 1.24}
{'loss': 1.9592, 'grad_norm': 2.528698444366455, 'learning_rate': 0.0002304, 'epoch': 1.24}
{'loss': 2.035, 'grad_norm': 4.070464611053467, 'learning_rate': 0.0002307, 'epoch': 1.25}
{'loss': 1.8043, 'grad_norm': 1.93435800075531, 'learning_rate': 0.00023099999999999998, 'epoch': 1.25}
{'loss': 1.7722, 'grad_norm': 3.285830497741699, 'learning_rate': 0.00023129999999999998, 'epoch': 1.25}
{'loss': 1.6131, 'grad_norm': 4.356208324432373, 'learning_rate': 0.0002316, 'epoch': 1.25}
{'loss': 1.5492, 'grad_norm': 5.4774603843688965, 'learning_rate': 0.0002319, 'epoch': 1.25}
{'loss': 1.6548, 'grad_norm': 3.671088218688965, 'learning_rate': 0.00023219999999999998, 'epoch': 1.25}
{'loss': 1.3874, 'grad_norm': 3.7231082916259766, 'learning_rate': 0.00023249999999999999, 'epoch': 1.26}
{'loss': 1.3857, 'grad_norm': 1.782421588897705, 'learning_rate': 0.0002328, 'epoch': 1.26}
{'loss': 1.7764, 'grad_norm': 1.4939918518066406, 'learning_rate': 0.00023309999999999997, 'epoch': 1.26}
{'loss': 1.3059, 'grad_norm': 1.064145565032959, 'learning_rate': 0.00023339999999999998, 'epoch': 1.26}
{'loss': 1.3497, 'grad_norm': 2.0802013874053955, 'learning_rate': 0.0002337, 'epoch': 1.26}
{'loss': 1.6281, 'grad_norm': 2.4550795555114746, 'learning_rate': 0.000234, 'epoch': 1.26}
{'loss': 1.3037, 'grad_norm': 1.424136996269226, 'learning_rate': 0.00023429999999999998, 'epoch': 1.27}
{'loss': 1.2327, 'grad_norm': 2.6355724334716797, 'learning_rate': 0.00023459999999999998, 'epoch': 1.27}
{'loss': 1.1327, 'grad_norm': 1.9551432132720947, 'learning_rate': 0.0002349, 'epoch': 1.27}
{'loss': 1.329, 'grad_norm': 0.920864462852478, 'learning_rate': 0.0002352, 'epoch': 1.27}
{'loss': 1.4342, 'grad_norm': 0.8361489176750183, 'learning_rate': 0.00023549999999999998, 'epoch': 1.27}
{'loss': 1.2214, 'grad_norm': 1.4463287591934204, 'learning_rate': 0.00023579999999999999, 'epoch': 1.27}
{'loss': 1.126, 'grad_norm': 0.8743594884872437, 'learning_rate': 0.0002361, 'epoch': 1.28}
{'loss': 1.4563, 'grad_norm': 0.9425063133239746, 'learning_rate': 0.0002364, 'epoch': 1.28}
{'loss': 1.495, 'grad_norm': 1.1034338474273682, 'learning_rate': 0.00023669999999999998, 'epoch': 1.28}
{'loss': 1.2458, 'grad_norm': 1.235459804534912, 'learning_rate': 0.000237, 'epoch': 1.28}
{'loss': 1.2275, 'grad_norm': 1.0407472848892212, 'learning_rate': 0.0002373, 'epoch': 1.28}
{'loss': 1.2064, 'grad_norm': 1.0057398080825806, 'learning_rate': 0.0002376, 'epoch': 1.28}
{'loss': 1.457, 'grad_norm': 1.2582429647445679, 'learning_rate': 0.00023789999999999998, 'epoch': 1.28}
{'loss': 1.0123, 'grad_norm': 1.2544838190078735, 'learning_rate': 0.0002382, 'epoch': 1.29}
{'loss': 1.3412, 'grad_norm': 1.267555832862854, 'learning_rate': 0.0002385, 'epoch': 1.29}
{'loss': 1.3812, 'grad_norm': 1.585595726966858, 'learning_rate': 0.0002388, 'epoch': 1.29}
{'loss': 1.2368, 'grad_norm': 1.1115787029266357, 'learning_rate': 0.00023909999999999998, 'epoch': 1.29}
{'loss': 1.0813, 'grad_norm': 1.1539804935455322, 'learning_rate': 0.0002394, 'epoch': 1.29}
{'loss': 1.2567, 'grad_norm': 1.2517136335372925, 'learning_rate': 0.0002397, 'epoch': 1.29}
{'loss': 1.3813, 'grad_norm': 1.0020838975906372, 'learning_rate': 0.00023999999999999998, 'epoch': 1.3}
{'loss': 1.4291, 'grad_norm': 1.278122067451477, 'learning_rate': 0.00024029999999999999, 'epoch': 1.3}
{'loss': 1.5433, 'grad_norm': 1.1353975534439087, 'learning_rate': 0.0002406, 'epoch': 1.3}
{'loss': 1.4993, 'grad_norm': 1.0918465852737427, 'learning_rate': 0.0002409, 'epoch': 1.3}
{'loss': 1.442, 'grad_norm': 1.1691175699234009, 'learning_rate': 0.00024119999999999998, 'epoch': 1.3}
{'loss': 1.3307, 'grad_norm': 2.067641258239746, 'learning_rate': 0.0002415, 'epoch': 1.3}
{'loss': 1.3187, 'grad_norm': 1.2151570320129395, 'learning_rate': 0.0002418, 'epoch': 1.31}
{'loss': 1.1919, 'grad_norm': 1.3653641939163208, 'learning_rate': 0.0002421, 'epoch': 1.31}
{'loss': 1.5955, 'grad_norm': 1.193217158317566, 'learning_rate': 0.00024239999999999998, 'epoch': 1.31}
{'loss': 1.6028, 'grad_norm': 1.2559990882873535, 'learning_rate': 0.0002427, 'epoch': 1.31}
{'loss': 1.4464, 'grad_norm': 1.5885244607925415, 'learning_rate': 0.000243, 'epoch': 1.31}
{'loss': 1.743, 'grad_norm': 1.5733736753463745, 'learning_rate': 0.0002433, 'epoch': 1.31}
{'loss': 1.4574, 'grad_norm': 2.05718731880188, 'learning_rate': 0.00024359999999999999, 'epoch': 1.32}
{'loss': 1.9888, 'grad_norm': 1.5828289985656738, 'learning_rate': 0.00024389999999999997, 'epoch': 1.32}
{'loss': 1.3748, 'grad_norm': 1.8411847352981567, 'learning_rate': 0.00024419999999999997, 'epoch': 1.32}
{'loss': 2.2596, 'grad_norm': 2.4953489303588867, 'learning_rate': 0.0002445, 'epoch': 1.32}
{'loss': 5.1826, 'grad_norm': 22.735031127929688, 'learning_rate': 0.0002448, 'epoch': 1.32}
{'loss': 1.7049, 'grad_norm': 2.6146559715270996, 'learning_rate': 0.00024509999999999994, 'epoch': 1.32}
{'loss': 1.6428, 'grad_norm': 1.7866498231887817, 'learning_rate': 0.00024539999999999995, 'epoch': 1.32}
{'loss': 1.7732, 'grad_norm': 3.011427640914917, 'learning_rate': 0.00024569999999999995, 'epoch': 1.33}
{'loss': 1.7, 'grad_norm': 1.7671997547149658, 'learning_rate': 0.00024599999999999996, 'epoch': 1.33}
{'loss': 1.8395, 'grad_norm': 3.2919392585754395, 'learning_rate': 0.00024629999999999997, 'epoch': 1.33}
{'loss': 1.4656, 'grad_norm': 3.4365289211273193, 'learning_rate': 0.0002466, 'epoch': 1.33}
{'loss': 1.3553, 'grad_norm': 2.34206485748291, 'learning_rate': 0.0002469, 'epoch': 1.33}
{'loss': 1.6943, 'grad_norm': 1.3108103275299072, 'learning_rate': 0.0002472, 'epoch': 1.33}
{'loss': 1.6788, 'grad_norm': 1.1649718284606934, 'learning_rate': 0.00024749999999999994, 'epoch': 1.34}
{'loss': 1.064, 'grad_norm': 0.8755460977554321, 'learning_rate': 0.00024779999999999995, 'epoch': 1.34}
{'loss': 1.1169, 'grad_norm': 1.0399974584579468, 'learning_rate': 0.00024809999999999996, 'epoch': 1.34}
{'loss': 1.32, 'grad_norm': 1.590290904045105, 'learning_rate': 0.00024839999999999997, 'epoch': 1.34}
{'loss': 0.9774, 'grad_norm': 1.9613844156265259, 'learning_rate': 0.0002487, 'epoch': 1.34}
{'loss': 1.0947, 'grad_norm': 1.3067349195480347, 'learning_rate': 0.000249, 'epoch': 1.34}
{'loss': 1.4792, 'grad_norm': 3.495009422302246, 'learning_rate': 0.0002493, 'epoch': 1.35}
{'loss': 1.2189, 'grad_norm': 2.386378526687622, 'learning_rate': 0.00024959999999999994, 'epoch': 1.35}
{'loss': 1.383, 'grad_norm': 1.2430686950683594, 'learning_rate': 0.00024989999999999995, 'epoch': 1.35}
{'loss': 1.1695, 'grad_norm': 1.1015182733535767, 'learning_rate': 0.00025019999999999996, 'epoch': 1.35}
{'loss': 1.4384, 'grad_norm': 1.2849568128585815, 'learning_rate': 0.00025049999999999996, 'epoch': 1.35}
{'loss': 1.2806, 'grad_norm': 0.9367717504501343, 'learning_rate': 0.00025079999999999997, 'epoch': 1.35}
{'loss': 1.9186, 'grad_norm': 1.9065661430358887, 'learning_rate': 0.0002511, 'epoch': 1.36}
{'loss': 1.2997, 'grad_norm': 1.8349933624267578, 'learning_rate': 0.0002514, 'epoch': 1.36}
{'loss': 1.7798, 'grad_norm': 2.411646604537964, 'learning_rate': 0.0002517, 'epoch': 1.36}
{'loss': 1.2455, 'grad_norm': 1.3963836431503296, 'learning_rate': 0.00025199999999999995, 'epoch': 1.36}
{'loss': 1.5101, 'grad_norm': 1.7644349336624146, 'learning_rate': 0.00025229999999999995, 'epoch': 1.36}
{'loss': 1.3869, 'grad_norm': 1.1302613019943237, 'learning_rate': 0.00025259999999999996, 'epoch': 1.36}
{'loss': 1.4488, 'grad_norm': 2.062229633331299, 'learning_rate': 0.00025289999999999997, 'epoch': 1.36}
{'loss': 1.0541, 'grad_norm': 1.800642967224121, 'learning_rate': 0.0002532, 'epoch': 1.37}
{'loss': 1.4694, 'grad_norm': 3.4561281204223633, 'learning_rate': 0.0002535, 'epoch': 1.37}
{'loss': 1.5959, 'grad_norm': 2.443664073944092, 'learning_rate': 0.0002538, 'epoch': 1.37}
{'loss': 1.3463, 'grad_norm': 1.2733495235443115, 'learning_rate': 0.0002541, 'epoch': 1.37}
{'loss': 1.3913, 'grad_norm': 1.4782954454421997, 'learning_rate': 0.00025439999999999995, 'epoch': 1.37}
{'loss': 1.4062, 'grad_norm': 1.355779767036438, 'learning_rate': 0.00025469999999999996, 'epoch': 1.37}
{'loss': 1.0575, 'grad_norm': 0.991340696811676, 'learning_rate': 0.00025499999999999996, 'epoch': 1.38}
{'loss': 1.4418, 'grad_norm': 1.4136706590652466, 'learning_rate': 0.00025529999999999997, 'epoch': 1.38}
{'loss': 1.909, 'grad_norm': 1.5610219240188599, 'learning_rate': 0.0002556, 'epoch': 1.38}
{'loss': 1.4926, 'grad_norm': 1.4637738466262817, 'learning_rate': 0.0002559, 'epoch': 1.38}
{'loss': 1.444, 'grad_norm': 1.174544095993042, 'learning_rate': 0.0002562, 'epoch': 1.38}
{'loss': 1.211, 'grad_norm': 1.295507550239563, 'learning_rate': 0.00025649999999999995, 'epoch': 1.38}
{'loss': 1.5489, 'grad_norm': 1.341482162475586, 'learning_rate': 0.00025679999999999995, 'epoch': 1.39}
{'loss': 1.304, 'grad_norm': 1.5005024671554565, 'learning_rate': 0.00025709999999999996, 'epoch': 1.39}
{'loss': 1.411, 'grad_norm': 1.7614165544509888, 'learning_rate': 0.00025739999999999997, 'epoch': 1.39}
{'loss': 1.5675, 'grad_norm': 2.1121573448181152, 'learning_rate': 0.0002577, 'epoch': 1.39}
{'loss': 1.2976, 'grad_norm': 1.4016284942626953, 'learning_rate': 0.000258, 'epoch': 1.39}
{'loss': 1.5295, 'grad_norm': 1.4677424430847168, 'learning_rate': 0.0002583, 'epoch': 1.39}
{'loss': 1.6782, 'grad_norm': 1.7327654361724854, 'learning_rate': 0.0002586, 'epoch': 1.4}
{'loss': 2.1258, 'grad_norm': 1.684560775756836, 'learning_rate': 0.00025889999999999995, 'epoch': 1.4}
{'loss': 1.2016, 'grad_norm': 1.1350618600845337, 'learning_rate': 0.00025919999999999996, 'epoch': 1.4}
{'loss': 2.2616, 'grad_norm': 1.8442115783691406, 'learning_rate': 0.00025949999999999997, 'epoch': 1.4}
{'loss': 3.7807, 'grad_norm': 15.330982208251953, 'learning_rate': 0.00025979999999999997, 'epoch': 1.4}
{'loss': 2.7959, 'grad_norm': 9.512137413024902, 'learning_rate': 0.0002601, 'epoch': 1.4}
{'loss': 2.2513, 'grad_norm': 4.83724308013916, 'learning_rate': 0.0002604, 'epoch': 1.4}
{'loss': 1.1761, 'grad_norm': 1.0789581537246704, 'learning_rate': 0.0002607, 'epoch': 1.41}
{'loss': 1.3131, 'grad_norm': 1.283165693283081, 'learning_rate': 0.000261, 'epoch': 1.41}
{'loss': 1.4793, 'grad_norm': 1.3923134803771973, 'learning_rate': 0.00026129999999999995, 'epoch': 1.41}
{'loss': 1.4069, 'grad_norm': 1.2186331748962402, 'learning_rate': 0.00026159999999999996, 'epoch': 1.41}
{'loss': 1.6623, 'grad_norm': 1.7576051950454712, 'learning_rate': 0.00026189999999999997, 'epoch': 1.41}
{'loss': 0.9214, 'grad_norm': 2.6093623638153076, 'learning_rate': 0.0002622, 'epoch': 1.41}
{'loss': 1.4146, 'grad_norm': 1.0863568782806396, 'learning_rate': 0.0002625, 'epoch': 1.42}
{'loss': 1.8021, 'grad_norm': 2.363821506500244, 'learning_rate': 0.0002628, 'epoch': 1.42}
{'loss': 1.1834, 'grad_norm': 1.1821964979171753, 'learning_rate': 0.0002631, 'epoch': 1.42}
{'loss': 1.192, 'grad_norm': 1.32361900806427, 'learning_rate': 0.00026339999999999995, 'epoch': 1.42}
{'loss': 1.0575, 'grad_norm': 1.3281641006469727, 'learning_rate': 0.00026369999999999996, 'epoch': 1.42}
{'loss': 1.1708, 'grad_norm': 1.5585789680480957, 'learning_rate': 0.00026399999999999997, 'epoch': 1.42}
{'loss': 1.1794, 'grad_norm': 2.31046462059021, 'learning_rate': 0.0002643, 'epoch': 1.43}
{'loss': 1.3221, 'grad_norm': 1.7033979892730713, 'learning_rate': 0.0002646, 'epoch': 1.43}
{'loss': 1.4937, 'grad_norm': 2.653367519378662, 'learning_rate': 0.0002649, 'epoch': 1.43}
{'loss': 1.078, 'grad_norm': 0.9184427261352539, 'learning_rate': 0.0002652, 'epoch': 1.43}
{'loss': 1.186, 'grad_norm': 0.9819865226745605, 'learning_rate': 0.0002655, 'epoch': 1.43}
{'loss': 1.0641, 'grad_norm': 1.0578396320343018, 'learning_rate': 0.00026579999999999996, 'epoch': 1.43}
{'loss': 1.373, 'grad_norm': 1.4637776613235474, 'learning_rate': 0.00026609999999999996, 'epoch': 1.44}
{'loss': 1.1442, 'grad_norm': 0.9520303606987, 'learning_rate': 0.00026639999999999997, 'epoch': 1.44}
{'loss': 1.4782, 'grad_norm': 1.6817363500595093, 'learning_rate': 0.0002667, 'epoch': 1.44}
{'loss': 1.8022, 'grad_norm': 2.1572883129119873, 'learning_rate': 0.000267, 'epoch': 1.44}
{'loss': 1.4329, 'grad_norm': 0.8815500736236572, 'learning_rate': 0.0002673, 'epoch': 1.44}
{'loss': 1.1709, 'grad_norm': 1.2165837287902832, 'learning_rate': 0.0002676, 'epoch': 1.44}
{'loss': 1.3277, 'grad_norm': 2.121063470840454, 'learning_rate': 0.0002679, 'epoch': 1.44}
{'loss': 1.5098, 'grad_norm': 1.4610421657562256, 'learning_rate': 0.00026819999999999996, 'epoch': 1.45}
{'loss': 1.3525, 'grad_norm': 2.9947142601013184, 'learning_rate': 0.00026849999999999997, 'epoch': 1.45}
{'loss': 1.1726, 'grad_norm': 1.1811401844024658, 'learning_rate': 0.0002688, 'epoch': 1.45}
{'loss': 1.2433, 'grad_norm': 1.4365415573120117, 'learning_rate': 0.0002691, 'epoch': 1.45}
{'loss': 1.0205, 'grad_norm': 1.34075927734375, 'learning_rate': 0.0002694, 'epoch': 1.45}
{'loss': 1.0883, 'grad_norm': 2.7684597969055176, 'learning_rate': 0.0002697, 'epoch': 1.45}
{'loss': 1.6006, 'grad_norm': 1.557430624961853, 'learning_rate': 0.00027, 'epoch': 1.46}
{'loss': 1.4207, 'grad_norm': 1.616085410118103, 'learning_rate': 0.00027029999999999996, 'epoch': 1.46}
{'loss': 1.6985, 'grad_norm': 5.76104211807251, 'learning_rate': 0.00027059999999999996, 'epoch': 1.46}
{'loss': 1.1576, 'grad_norm': 1.2783349752426147, 'learning_rate': 0.00027089999999999997, 'epoch': 1.46}
{'loss': 1.4433, 'grad_norm': 1.2653543949127197, 'learning_rate': 0.0002712, 'epoch': 1.46}
{'loss': 1.5359, 'grad_norm': 1.2063896656036377, 'learning_rate': 0.0002715, 'epoch': 1.46}
{'loss': 1.5251, 'grad_norm': 2.794680118560791, 'learning_rate': 0.0002718, 'epoch': 1.47}
{'loss': 1.9892, 'grad_norm': 3.2242326736450195, 'learning_rate': 0.0002721, 'epoch': 1.47}
{'loss': 1.8354, 'grad_norm': 1.8846021890640259, 'learning_rate': 0.0002724, 'epoch': 1.47}
{'loss': 1.5269, 'grad_norm': 2.0368640422821045, 'learning_rate': 0.00027269999999999996, 'epoch': 1.47}
{'loss': 1.6935, 'grad_norm': 1.5392261743545532, 'learning_rate': 0.00027299999999999997, 'epoch': 1.47}
{'loss': 1.7796, 'grad_norm': 1.5438854694366455, 'learning_rate': 0.0002733, 'epoch': 1.47}
{'loss': 1.3982, 'grad_norm': 1.796651005744934, 'learning_rate': 0.0002736, 'epoch': 1.48}
{'loss': 1.7769, 'grad_norm': 2.2069437503814697, 'learning_rate': 0.0002739, 'epoch': 1.48}
{'loss': 1.4909, 'grad_norm': 1.9683245420455933, 'learning_rate': 0.0002742, 'epoch': 1.48}
{'loss': 2.0897, 'grad_norm': 1.911014199256897, 'learning_rate': 0.0002745, 'epoch': 1.48}
{'loss': 2.1389, 'grad_norm': 5.754384994506836, 'learning_rate': 0.0002748, 'epoch': 1.48}
{'loss': 1.5023, 'grad_norm': 1.59812331199646, 'learning_rate': 0.00027509999999999996, 'epoch': 1.48}
{'loss': 2.156, 'grad_norm': 3.8509624004364014, 'learning_rate': 0.00027539999999999997, 'epoch': 1.48}
{'loss': 1.6978, 'grad_norm': 1.6457704305648804, 'learning_rate': 0.0002757, 'epoch': 1.49}
{'loss': 3.222, 'grad_norm': 9.261984825134277, 'learning_rate': 0.000276, 'epoch': 1.49}
{'loss': 2.7299, 'grad_norm': 10.191606521606445, 'learning_rate': 0.0002763, 'epoch': 1.49}
{'loss': 1.363, 'grad_norm': 2.034604072570801, 'learning_rate': 0.0002766, 'epoch': 1.49}
{'loss': 1.4561, 'grad_norm': 2.7943766117095947, 'learning_rate': 0.0002769, 'epoch': 1.49}
{'loss': 1.5289, 'grad_norm': 2.739060640335083, 'learning_rate': 0.0002772, 'epoch': 1.49}
{'loss': 1.3459, 'grad_norm': 2.6572391986846924, 'learning_rate': 0.00027749999999999997, 'epoch': 1.5}
{'loss': 1.409, 'grad_norm': 2.4692184925079346, 'learning_rate': 0.0002778, 'epoch': 1.5}
{'loss': 1.1897, 'grad_norm': 1.569419264793396, 'learning_rate': 0.0002781, 'epoch': 1.5}
{'loss': 1.1971, 'grad_norm': 0.9803001880645752, 'learning_rate': 0.0002784, 'epoch': 1.5}
{'loss': 1.1573, 'grad_norm': 1.3759132623672485, 'learning_rate': 0.0002787, 'epoch': 1.5}
{'loss': 1.2441, 'grad_norm': 1.4470410346984863, 'learning_rate': 0.000279, 'epoch': 1.5}
{'loss': 1.2325, 'grad_norm': 1.9103741645812988, 'learning_rate': 0.0002793, 'epoch': 1.51}
{'loss': 1.0402, 'grad_norm': 1.5558336973190308, 'learning_rate': 0.00027959999999999997, 'epoch': 1.51}
{'loss': 1.2751, 'grad_norm': 2.0115926265716553, 'learning_rate': 0.0002799, 'epoch': 1.51}
{'loss': 1.6149, 'grad_norm': 1.6013593673706055, 'learning_rate': 0.0002802, 'epoch': 1.51}
{'loss': 1.2308, 'grad_norm': 1.3492580652236938, 'learning_rate': 0.0002805, 'epoch': 1.51}
{'loss': 1.1674, 'grad_norm': 1.3978670835494995, 'learning_rate': 0.0002808, 'epoch': 1.51}
{'loss': 1.2999, 'grad_norm': 1.257152795791626, 'learning_rate': 0.0002811, 'epoch': 1.52}
{'loss': 1.2184, 'grad_norm': 1.3785860538482666, 'learning_rate': 0.00028139999999999996, 'epoch': 1.52}
{'loss': 1.4197, 'grad_norm': 2.098989963531494, 'learning_rate': 0.00028169999999999996, 'epoch': 1.52}
{'loss': 1.3696, 'grad_norm': 1.411068320274353, 'learning_rate': 0.00028199999999999997, 'epoch': 1.52}
{'loss': 1.4752, 'grad_norm': 1.1803005933761597, 'learning_rate': 0.0002823, 'epoch': 1.52}
{'loss': 1.2319, 'grad_norm': 1.4621422290802002, 'learning_rate': 0.0002826, 'epoch': 1.52}
{'loss': 1.3185, 'grad_norm': 2.065951108932495, 'learning_rate': 0.00028289999999999994, 'epoch': 1.52}
{'loss': 1.3232, 'grad_norm': 2.077345371246338, 'learning_rate': 0.00028319999999999994, 'epoch': 1.53}
{'loss': 1.1082, 'grad_norm': 2.0758562088012695, 'learning_rate': 0.00028349999999999995, 'epoch': 1.53}
{'loss': 1.3383, 'grad_norm': 2.724622964859009, 'learning_rate': 0.00028379999999999996, 'epoch': 1.53}
{'loss': 1.514, 'grad_norm': 1.9979689121246338, 'learning_rate': 0.00028409999999999997, 'epoch': 1.53}
{'loss': 1.2723, 'grad_norm': 1.9366734027862549, 'learning_rate': 0.0002844, 'epoch': 1.53}
{'loss': 1.4332, 'grad_norm': 2.198087215423584, 'learning_rate': 0.0002847, 'epoch': 1.53}
{'loss': 1.3232, 'grad_norm': 1.5621610879898071, 'learning_rate': 0.000285, 'epoch': 1.54}
{'loss': 1.292, 'grad_norm': 1.4429649114608765, 'learning_rate': 0.00028529999999999994, 'epoch': 1.54}
{'loss': 1.3802, 'grad_norm': 1.7527788877487183, 'learning_rate': 0.00028559999999999995, 'epoch': 1.54}
{'loss': 1.5058, 'grad_norm': 2.562932252883911, 'learning_rate': 0.00028589999999999996, 'epoch': 1.54}
{'loss': 1.4053, 'grad_norm': 2.0278782844543457, 'learning_rate': 0.00028619999999999996, 'epoch': 1.54}
{'loss': 1.5985, 'grad_norm': 2.133039712905884, 'learning_rate': 0.00028649999999999997, 'epoch': 1.54}
{'loss': 1.7425, 'grad_norm': 1.7495462894439697, 'learning_rate': 0.0002868, 'epoch': 1.55}
{'loss': 1.1744, 'grad_norm': 1.314456582069397, 'learning_rate': 0.0002871, 'epoch': 1.55}
{'loss': 1.199, 'grad_norm': 1.5634371042251587, 'learning_rate': 0.00028739999999999994, 'epoch': 1.55}
{'loss': 1.3761, 'grad_norm': 1.5051501989364624, 'learning_rate': 0.00028769999999999995, 'epoch': 1.55}
{'loss': 1.7574, 'grad_norm': 1.4913947582244873, 'learning_rate': 0.00028799999999999995, 'epoch': 1.55}
{'loss': 1.6131, 'grad_norm': 2.0032637119293213, 'learning_rate': 0.00028829999999999996, 'epoch': 1.55}
{'loss': 1.5788, 'grad_norm': 1.4599378108978271, 'learning_rate': 0.00028859999999999997, 'epoch': 1.56}
{'loss': 1.4599, 'grad_norm': 1.526383638381958, 'learning_rate': 0.0002889, 'epoch': 1.56}
{'loss': 1.7604, 'grad_norm': 3.349010705947876, 'learning_rate': 0.0002892, 'epoch': 1.56}
{'loss': 2.0222, 'grad_norm': 3.1439058780670166, 'learning_rate': 0.0002895, 'epoch': 1.56}
{'loss': 2.2708, 'grad_norm': 5.448111057281494, 'learning_rate': 0.00028979999999999994, 'epoch': 1.56}
{'loss': 2.3857, 'grad_norm': 3.330211877822876, 'learning_rate': 0.00029009999999999995, 'epoch': 1.56}
{'loss': 1.8033, 'grad_norm': 1.844307541847229, 'learning_rate': 0.00029039999999999996, 'epoch': 1.56}
{'loss': 1.8416, 'grad_norm': 2.17771053314209, 'learning_rate': 0.00029069999999999996, 'epoch': 1.57}
{'loss': 1.4765, 'grad_norm': 1.889838695526123, 'learning_rate': 0.00029099999999999997, 'epoch': 1.57}
{'loss': 1.5771, 'grad_norm': 1.280713677406311, 'learning_rate': 0.0002913, 'epoch': 1.57}
{'loss': 1.4645, 'grad_norm': 1.2217782735824585, 'learning_rate': 0.0002916, 'epoch': 1.57}
{'loss': 1.3598, 'grad_norm': 1.493486762046814, 'learning_rate': 0.0002919, 'epoch': 1.57}
{'loss': 1.5287, 'grad_norm': 1.8840752840042114, 'learning_rate': 0.00029219999999999995, 'epoch': 1.57}
{'loss': 1.2946, 'grad_norm': 1.965975046157837, 'learning_rate': 0.00029249999999999995, 'epoch': 1.58}
{'loss': 1.0137, 'grad_norm': 1.5697219371795654, 'learning_rate': 0.00029279999999999996, 'epoch': 1.58}
{'loss': 1.1297, 'grad_norm': 1.665776014328003, 'learning_rate': 0.00029309999999999997, 'epoch': 1.58}
{'loss': 1.1271, 'grad_norm': 1.9357331991195679, 'learning_rate': 0.0002934, 'epoch': 1.58}
{'loss': 1.3413, 'grad_norm': 0.922601044178009, 'learning_rate': 0.0002937, 'epoch': 1.58}
{'loss': 1.1785, 'grad_norm': 1.0412627458572388, 'learning_rate': 0.000294, 'epoch': 1.58}
{'loss': 1.4531, 'grad_norm': 1.292492151260376, 'learning_rate': 0.00029429999999999994, 'epoch': 1.59}
{'loss': 1.4747, 'grad_norm': 1.4930530786514282, 'learning_rate': 0.00029459999999999995, 'epoch': 1.59}
{'loss': 1.2275, 'grad_norm': 1.398553729057312, 'learning_rate': 0.00029489999999999996, 'epoch': 1.59}
{'loss': 1.3404, 'grad_norm': 1.1149609088897705, 'learning_rate': 0.00029519999999999997, 'epoch': 1.59}
{'loss': 1.4117, 'grad_norm': 2.243300676345825, 'learning_rate': 0.00029549999999999997, 'epoch': 1.59}
{'loss': 1.2791, 'grad_norm': 0.9678653478622437, 'learning_rate': 0.0002958, 'epoch': 1.59}
{'loss': 1.54, 'grad_norm': 0.9126372337341309, 'learning_rate': 0.0002961, 'epoch': 1.6}
{'loss': 1.2979, 'grad_norm': 1.447344422340393, 'learning_rate': 0.0002964, 'epoch': 1.6}
{'loss': 1.6844, 'grad_norm': 2.5969924926757812, 'learning_rate': 0.00029669999999999995, 'epoch': 1.6}
{'loss': 1.2633, 'grad_norm': 1.3566679954528809, 'learning_rate': 0.00029699999999999996, 'epoch': 1.6}


  0%|          | 0/196 [00:00<?, ?it/s]

  1%|          | 2/196 [00:00<01:16,  2.53it/s]

  2%|▏         | 3/196 [00:01<01:41,  1.89it/s]

  2%|▏         | 4/196 [00:02<01:58,  1.63it/s]

  3%|▎         | 5/196 [00:03<02:08,  1.48it/s]

  3%|▎         | 6/196 [00:04<02:27,  1.29it/s]

  4%|▎         | 7/196 [00:04<02:28,  1.28it/s]

  4%|▍         | 8/196 [00:05<02:37,  1.20it/s]

  5%|▍         | 9/196 [00:07<03:27,  1.11s/it]

  5%|▌         | 10/196 [00:09<03:59,  1.29s/it]

  6%|▌         | 11/196 [00:11<04:38,  1.50s/it]

  6%|▌         | 12/196 [00:12<04:40,  1.53s/it]

  7%|▋         | 13/196 [00:13<04:02,  1.33s/it]

  7%|▋         | 14/196 [00:14<03:25,  1.13s/it]

  8%|▊         | 15/196 [00:14<02:54,  1.04it/s]

  8%|▊         | 16/196 [00:15<02:42,  1.11it/s]

  9%|▊         | 17/196 [00:16<02:40,  1.11it/s]

  9%|▉         | 18/196 [00:17<03:04,  1.04s/it]

 10%|▉         | 19/196 [00:19<03:52,  1.31s/it]

 10%|█         | 20/196 [00:21<04:02,  1.38s/it]

 11%|█         | 21/196 [00:22<04:10,  1.43s/it]

 11%|█         | 22/196 [00:24<03:53,  1.34s/it]

 12%|█▏        | 23/196 [00:24<03:27,  1.20s/it]

 12%|█▏        | 24/196 [00:25<02:47,  1.03it/s]

 13%|█▎        | 25/196 [00:25<02:28,  1.15it/s]

 13%|█▎        | 26/196 [00:26<02:10,  1.30it/s]

 14%|█▍        | 27/196 [00:27<02:01,  1.39it/s]

 14%|█▍        | 28/196 [00:27<01:56,  1.44it/s]

 15%|█▍        | 29/196 [00:28<01:57,  1.43it/s]

 15%|█▌        | 30/196 [00:29<01:55,  1.44it/s]

 16%|█▌        | 31/196 [00:29<01:43,  1.59it/s]

 16%|█▋        | 32/196 [00:30<01:44,  1.57it/s]

 17%|█▋        | 33/196 [00:31<01:58,  1.38it/s]

 17%|█▋        | 34/196 [00:32<02:24,  1.12it/s]

 18%|█▊        | 35/196 [00:33<02:35,  1.03it/s]

 18%|█▊        | 36/196 [00:34<02:51,  1.07s/it]

 19%|█▉        | 37/196 [00:35<02:44,  1.04s/it]

 19%|█▉        | 38/196 [00:36<02:33,  1.03it/s]

 20%|█▉        | 39/196 [00:37<02:21,  1.11it/s]

 20%|██        | 40/196 [00:38<02:12,  1.18it/s]

 21%|██        | 41/196 [00:38<02:01,  1.28it/s]

 21%|██▏       | 42/196 [00:39<01:56,  1.32it/s]

 22%|██▏       | 43/196 [00:40<01:54,  1.34it/s]

 22%|██▏       | 44/196 [00:40<01:49,  1.39it/s]

 23%|██▎       | 45/196 [00:41<01:41,  1.48it/s]

 23%|██▎       | 46/196 [00:42<01:37,  1.53it/s]

 24%|██▍       | 47/196 [00:42<01:36,  1.54it/s]

 24%|██▍       | 48/196 [00:43<01:33,  1.59it/s]

 25%|██▌       | 49/196 [00:43<01:32,  1.59it/s]

 26%|██▌       | 50/196 [00:44<01:30,  1.61it/s]

 26%|██▌       | 51/196 [00:45<01:28,  1.64it/s]

 27%|██▋       | 52/196 [00:45<01:29,  1.61it/s]

 27%|██▋       | 53/196 [00:46<01:29,  1.59it/s]

 28%|██▊       | 54/196 [00:47<01:29,  1.58it/s]

 28%|██▊       | 55/196 [00:47<01:38,  1.43it/s]

 29%|██▊       | 56/196 [00:48<01:46,  1.32it/s]

 29%|██▉       | 57/196 [00:49<01:51,  1.25it/s]

 30%|██▉       | 58/196 [00:50<01:52,  1.23it/s]

 30%|███       | 59/196 [00:51<01:49,  1.25it/s]

 31%|███       | 60/196 [00:51<01:38,  1.38it/s]

 31%|███       | 61/196 [00:52<01:32,  1.46it/s]

 32%|███▏      | 62/196 [00:53<01:39,  1.34it/s]

 32%|███▏      | 63/196 [00:54<01:39,  1.34it/s]

 33%|███▎      | 64/196 [00:54<01:37,  1.36it/s]

 33%|███▎      | 65/196 [00:55<01:34,  1.38it/s]

 34%|███▎      | 66/196 [00:56<01:40,  1.29it/s]

 34%|███▍      | 67/196 [00:57<01:41,  1.26it/s]

 35%|███▍      | 68/196 [00:58<01:52,  1.13it/s]

 35%|███▌      | 69/196 [00:59<01:49,  1.16it/s]

 36%|███▌      | 70/196 [00:59<01:42,  1.23it/s]

 36%|███▌      | 71/196 [01:00<01:35,  1.31it/s]

 37%|███▋      | 72/196 [01:01<01:29,  1.38it/s]

 37%|███▋      | 73/196 [01:01<01:22,  1.49it/s]

 38%|███▊      | 74/196 [01:02<01:17,  1.57it/s]

 38%|███▊      | 75/196 [01:02<01:15,  1.60it/s]

 39%|███▉      | 76/196 [01:03<01:13,  1.63it/s]

 39%|███▉      | 77/196 [01:04<01:17,  1.54it/s]

 40%|███▉      | 78/196 [01:04<01:18,  1.51it/s]

 40%|████      | 79/196 [01:05<01:16,  1.53it/s]

 41%|████      | 80/196 [01:06<01:20,  1.44it/s]

 41%|████▏     | 81/196 [01:07<01:22,  1.40it/s]

 42%|████▏     | 82/196 [01:07<01:20,  1.41it/s]

 42%|████▏     | 83/196 [01:08<01:22,  1.37it/s]

 43%|████▎     | 84/196 [01:09<01:21,  1.37it/s]

 43%|████▎     | 85/196 [01:09<01:21,  1.37it/s]

 44%|████▍     | 86/196 [01:10<01:22,  1.33it/s]

 44%|████▍     | 87/196 [01:11<01:21,  1.34it/s]

 45%|████▍     | 88/196 [01:12<01:22,  1.30it/s]

 45%|████▌     | 89/196 [01:13<01:24,  1.27it/s]

 46%|████▌     | 90/196 [01:13<01:22,  1.29it/s]

 46%|████▋     | 91/196 [01:14<01:17,  1.36it/s]

 47%|████▋     | 92/196 [01:15<01:14,  1.40it/s]

 47%|████▋     | 93/196 [01:16<01:17,  1.33it/s]

 48%|████▊     | 94/196 [01:16<01:16,  1.34it/s]

 48%|████▊     | 95/196 [01:17<01:14,  1.36it/s]

 49%|████▉     | 96/196 [01:18<01:17,  1.30it/s]

 49%|████▉     | 97/196 [01:18<01:13,  1.35it/s]

 50%|█████     | 98/196 [01:19<01:14,  1.32it/s]

 51%|█████     | 99/196 [01:20<01:08,  1.42it/s]

 51%|█████     | 100/196 [01:20<01:00,  1.59it/s]

 52%|█████▏    | 101/196 [01:21<00:58,  1.62it/s]

 52%|█████▏    | 102/196 [01:22<01:02,  1.51it/s]

 53%|█████▎    | 103/196 [01:23<01:08,  1.36it/s]

 53%|█████▎    | 104/196 [01:24<01:15,  1.22it/s]

 54%|█████▎    | 105/196 [01:24<01:15,  1.20it/s]

 54%|█████▍    | 106/196 [01:25<01:13,  1.23it/s]

 55%|█████▍    | 107/196 [01:26<01:08,  1.31it/s]

 55%|█████▌    | 108/196 [01:26<01:00,  1.45it/s]

 56%|█████▌    | 109/196 [01:27<00:57,  1.50it/s]

 56%|█████▌    | 110/196 [01:28<00:56,  1.52it/s]

 57%|█████▋    | 111/196 [01:28<00:56,  1.50it/s]

 57%|█████▋    | 112/196 [01:29<00:58,  1.45it/s]

 58%|█████▊    | 113/196 [01:30<00:56,  1.47it/s]

 58%|█████▊    | 114/196 [01:30<00:52,  1.56it/s]

 59%|█████▊    | 115/196 [01:31<00:51,  1.59it/s]

 59%|█████▉    | 116/196 [01:32<00:50,  1.60it/s]

 60%|█████▉    | 117/196 [01:32<00:46,  1.71it/s]

 60%|██████    | 118/196 [01:32<00:41,  1.87it/s]

 61%|██████    | 119/196 [01:33<00:44,  1.72it/s]

 61%|██████    | 120/196 [01:34<00:45,  1.66it/s]

 62%|██████▏   | 121/196 [01:34<00:46,  1.63it/s]

 62%|██████▏   | 122/196 [01:35<00:46,  1.59it/s]

 63%|██████▎   | 123/196 [01:36<00:44,  1.63it/s]

 63%|██████▎   | 124/196 [01:36<00:45,  1.59it/s]

 64%|██████▍   | 125/196 [01:37<00:47,  1.49it/s]

 64%|██████▍   | 126/196 [01:38<00:52,  1.33it/s]

 65%|██████▍   | 127/196 [01:39<00:49,  1.38it/s]

 65%|██████▌   | 128/196 [01:39<00:46,  1.46it/s]

 66%|██████▌   | 129/196 [01:40<00:45,  1.48it/s]

 66%|██████▋   | 130/196 [01:41<00:45,  1.45it/s]

 67%|██████▋   | 131/196 [01:41<00:43,  1.49it/s]

 67%|██████▋   | 132/196 [01:42<00:40,  1.58it/s]

 68%|██████▊   | 133/196 [01:42<00:39,  1.58it/s]

 68%|██████▊   | 134/196 [01:43<00:40,  1.53it/s]

 69%|██████▉   | 135/196 [01:44<00:39,  1.56it/s]

 69%|██████▉   | 136/196 [01:44<00:38,  1.56it/s]

 70%|██████▉   | 137/196 [01:45<00:37,  1.56it/s]

 70%|███████   | 138/196 [01:46<00:36,  1.58it/s]

 71%|███████   | 139/196 [01:46<00:37,  1.53it/s]

 71%|███████▏  | 140/196 [01:47<00:35,  1.58it/s]

 72%|███████▏  | 141/196 [01:48<00:34,  1.61it/s]

 72%|███████▏  | 142/196 [01:48<00:34,  1.55it/s]

 73%|███████▎  | 143/196 [01:49<00:35,  1.49it/s]

 73%|███████▎  | 144/196 [01:50<00:33,  1.55it/s]

 74%|███████▍  | 145/196 [01:50<00:30,  1.68it/s]

 74%|███████▍  | 146/196 [01:51<00:28,  1.74it/s]

 75%|███████▌  | 147/196 [01:51<00:27,  1.75it/s]

 76%|███████▌  | 148/196 [01:52<00:27,  1.72it/s]

 76%|███████▌  | 149/196 [01:52<00:25,  1.82it/s]

 77%|███████▋  | 150/196 [01:53<00:27,  1.67it/s]

 77%|███████▋  | 151/196 [01:54<00:28,  1.60it/s]

 78%|███████▊  | 152/196 [01:54<00:27,  1.60it/s]

 78%|███████▊  | 153/196 [01:55<00:26,  1.60it/s]

 79%|███████▊  | 154/196 [01:55<00:26,  1.60it/s]

 79%|███████▉  | 155/196 [01:56<00:27,  1.48it/s]

 80%|███████▉  | 156/196 [01:57<00:29,  1.35it/s]

 80%|████████  | 157/196 [01:58<00:30,  1.29it/s]

 81%|████████  | 158/196 [01:59<00:26,  1.43it/s]

 81%|████████  | 159/196 [01:59<00:24,  1.53it/s]

 82%|████████▏ | 160/196 [02:00<00:23,  1.56it/s]

 82%|████████▏ | 161/196 [02:00<00:22,  1.53it/s]

 83%|████████▎ | 162/196 [02:01<00:21,  1.56it/s]

 83%|████████▎ | 163/196 [02:02<00:20,  1.58it/s]

 84%|████████▎ | 164/196 [02:02<00:20,  1.58it/s]

 84%|████████▍ | 165/196 [02:03<00:20,  1.53it/s]

 85%|████████▍ | 166/196 [02:04<00:19,  1.58it/s]

 85%|████████▌ | 167/196 [02:04<00:17,  1.61it/s]

 86%|████████▌ | 168/196 [02:05<00:16,  1.70it/s]

 86%|████████▌ | 169/196 [02:05<00:16,  1.61it/s]

 87%|████████▋ | 170/196 [02:06<00:17,  1.52it/s]

 87%|████████▋ | 171/196 [02:07<00:16,  1.54it/s]

 88%|████████▊ | 172/196 [02:07<00:15,  1.51it/s]

 88%|████████▊ | 173/196 [02:08<00:15,  1.51it/s]

 89%|████████▉ | 174/196 [02:09<00:15,  1.43it/s]

 89%|████████▉ | 175/196 [02:10<00:18,  1.13it/s]

 90%|████████▉ | 176/196 [02:12<00:26,  1.30s/it]

 90%|█████████ | 177/196 [02:14<00:28,  1.48s/it]

 91%|█████████ | 178/196 [02:16<00:29,  1.66s/it]

 91%|█████████▏| 179/196 [02:18<00:28,  1.65s/it]

 92%|█████████▏| 180/196 [02:19<00:21,  1.35s/it]

 92%|█████████▏| 181/196 [02:19<00:17,  1.14s/it]

 93%|█████████▎| 182/196 [02:20<00:13,  1.00it/s]

 93%|█████████▎| 183/196 [02:21<00:12,  1.02it/s]

 94%|█████████▍| 184/196 [02:22<00:10,  1.14it/s]

 94%|█████████▍| 185/196 [02:22<00:09,  1.18it/s]

 95%|█████████▍| 186/196 [02:23<00:08,  1.17it/s]

 95%|█████████▌| 187/196 [02:24<00:07,  1.22it/s]

 96%|█████████▌| 188/196 [02:25<00:06,  1.26it/s]

 96%|█████████▋| 189/196 [02:25<00:05,  1.32it/s]

 97%|█████████▋| 190/196 [02:26<00:04,  1.38it/s]

 97%|█████████▋| 191/196 [02:27<00:03,  1.47it/s]

 98%|█████████▊| 192/196 [02:27<00:02,  1.46it/s]

 98%|█████████▊| 193/196 [02:28<00:02,  1.46it/s]

 99%|█████████▉| 194/196 [02:29<00:01,  1.50it/s]

 99%|█████████▉| 195/196 [02:29<00:00,  1.54it/s]

100%|██████████| 196/196 [02:29<00:00,  1.92it/s]
                                                   

                                                 

100%|██████████| 1000/1000 [34:52<00:00,  1.68s/it]

100%|██████████| 196/196 [02:37<00:00,  1.92it/s]

                                                 
                                                   

100%|██████████| 1000/1000 [35:00<00:00,  1.68s/it]
100%|██████████| 1000/1000 [35:00<00:00,  2.10s/it]
Printing predictions for a few samples:
Sample 1:
  Reference: लिबर ऑफिस impress में एक प्रस्तुति document बनाना और बुनियादी formatting के इस spoken tutorial में आपका स्वागत है
######


  Prediction: liber ofis impres में एक प्रस्तुति document बनाना और बुनियादी formating के इस spoken tutorial में आपका



Sample 2:
  Reference: इस tutorial में हम impress window के भागों के बारे में सीखेंगे और कैसे स्लाइड इन्सर्ट करें और कॉपी करें फॉन्ट तथा फॉन्ट को फॉर्मेट करना सीखेंगे
######


  Prediction: इस tutorial में हम impres windw के भागों के बारे में सीखेंगे और कैसे slide insert करें और copy करेंfornt तथा font को format करना सीखेंगे



Sample 3:
  Reference: यहाँ हम अपने ऑपरेटिंग सिस्टम के रूप में gnu/linux और लिबरऑफिस वर्जन 334 का उपयोग कर रहे हैं
######


  Prediction: यहाँ हम अपने operेting सिstem के रूप में gnu linixस और libr ofis version 34 का उपयोग कर रह हं



Sample 4:
  Reference: चलिए अपनी प्रस्तुति प्रेजैटेशन sample impress open करते हैं जिसे पिछले tutorial में बनाया था
######


  Prediction: चलिए अपनी प्रस्तुति sampal impres open करते हैं जसेपछले



Sample 5:
  Reference: चलिए देखते हैं कि screen पर क्या क्या है
######


  Prediction: ाया थाचलिए देखते हैं कि सकrीन पर क्या क्या है



last Reference string यह स्क्रिप्ट लता द्वारा अनुवादित है आईआईटी मुंबई की ओर से मैं रवि कुमार अब आपसे विदा लेता हूँहमसे जुड़ने के लिए धन्यवाद


last prediction string lता द्वारा अनुवादित है आईआईटी मुमंबई की ओर से मैं रवि कुमार अब आपसे विदा लेता हूँ हमसे जड़ने के लिए धन्यवाद
{'eval_loss': 1.7065902948379517, 'eval_cer': 0.342703815793579, 'eval_wer': 0.5115005185204882, 'eval_runtime': 159.4221, 'eval_samples_per_second': 19.671, 'eval_steps_per_second': 1.229, 'epoch': 1.6}
{'train_runtime': 2101.2175, 'train_samples_per_second': 15.229, 'train_steps_per_second': 0.476, 'train_loss': 4.768421524226666, 'epoch': 1.6}
***** train metrics *****
  epoch                    =          1.6
  total_flos               = 5777637581GF
  train_loss               =       4.7684
  train_runtime            =   0:35:01.21
  train_samples            =        20000
  train_samples_per_second =       15.229
  train_steps_per_second   =        0.476
08/21/2024 15:46:10 - INFO - __main__ - *** Evaluate ***
/scratch/work/palp3/myenv/lib/python3.11/site-packages/transformers/models/wav2vec2/processing_wav2vec2.py:157: UserWarning: `as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.
  warnings.warn(

  0%|          | 0/196 [00:00<?, ?it/s]
  1%|          | 2/196 [00:00<01:03,  3.08it/s]
  2%|▏         | 3/196 [00:01<01:31,  2.12it/s]
  2%|▏         | 4/196 [00:02<01:51,  1.72it/s]
  3%|▎         | 5/196 [00:02<02:05,  1.53it/s]
  3%|▎         | 6/196 [00:03<02:22,  1.34it/s]
  4%|▎         | 7/196 [00:04<02:24,  1.31it/s]
  4%|▍         | 8/196 [00:05<02:34,  1.22it/s]
  5%|▍         | 9/196 [00:07<03:23,  1.09s/it]
  5%|▌         | 10/196 [00:08<03:55,  1.27s/it]
  6%|▌         | 11/196 [00:10<04:29,  1.46s/it]
  6%|▌         | 12/196 [00:12<04:34,  1.49s/it]
  7%|▋         | 13/196 [00:13<03:58,  1.30s/it]
  7%|▋         | 14/196 [00:13<03:22,  1.11s/it]
  8%|▊         | 15/196 [00:14<02:52,  1.05it/s]
  8%|▊         | 16/196 [00:15<02:41,  1.11it/s]
  9%|▊         | 17/196 [00:16<02:40,  1.11it/s]
  9%|▉         | 18/196 [00:17<03:05,  1.04s/it]
 10%|▉         | 19/196 [00:19<03:52,  1.31s/it]
 10%|█         | 20/196 [00:21<04:02,  1.38s/it]
 11%|█         | 21/196 [00:22<04:09,  1.43s/it]
 11%|█         | 22/196 [00:23<03:53,  1.34s/it]
 12%|█▏        | 23/196 [00:24<03:26,  1.19s/it]
 12%|█▏        | 24/196 [00:25<02:47,  1.03it/s]
 13%|█▎        | 25/196 [00:25<02:25,  1.17it/s]
 13%|█▎        | 26/196 [00:26<02:09,  1.32it/s]
 14%|█▍        | 27/196 [00:26<01:59,  1.41it/s]
 14%|█▍        | 28/196 [00:27<01:55,  1.45it/s]
 15%|█▍        | 29/196 [00:28<01:56,  1.43it/s]
 15%|█▌        | 30/196 [00:28<01:54,  1.45it/s]
 16%|█▌        | 31/196 [00:29<01:43,  1.59it/s]
 16%|█▋        | 32/196 [00:29<01:44,  1.57it/s]
 17%|█▋        | 33/196 [00:30<01:59,  1.36it/s]
 17%|█▋        | 34/196 [00:32<02:24,  1.12it/s]
 18%|█▊        | 35/196 [00:33<02:35,  1.04it/s]
 18%|█▊        | 36/196 [00:34<02:51,  1.07s/it]
 19%|█▉        | 37/196 [00:35<02:44,  1.03s/it]
 19%|█▉        | 38/196 [00:36<02:33,  1.03it/s]
 20%|█▉        | 39/196 [00:37<02:21,  1.11it/s]
 20%|██        | 40/196 [00:37<02:12,  1.17it/s]
 21%|██        | 41/196 [00:38<02:01,  1.28it/s]
 21%|██▏       | 42/196 [00:39<01:56,  1.32it/s]
 22%|██▏       | 43/196 [00:39<01:53,  1.35it/s]
 22%|██▏       | 44/196 [00:40<01:49,  1.39it/s]
 23%|██▎       | 45/196 [00:41<01:41,  1.50it/s]
 23%|██▎       | 46/196 [00:41<01:37,  1.54it/s]
 24%|██▍       | 47/196 [00:42<01:36,  1.54it/s]
 24%|██▍       | 48/196 [00:42<01:32,  1.59it/s]
 25%|██▌       | 49/196 [00:43<01:32,  1.60it/s]
 26%|██▌       | 50/196 [00:44<01:30,  1.61it/s]
 26%|██▌       | 51/196 [00:44<01:28,  1.64it/s]
 27%|██▋       | 52/196 [00:45<01:29,  1.61it/s]
 27%|██▋       | 53/196 [00:46<01:30,  1.59it/s]
 28%|██▊       | 54/196 [00:46<01:30,  1.58it/s]
 28%|██▊       | 55/196 [00:47<01:38,  1.43it/s]
 29%|██▊       | 56/196 [00:48<01:46,  1.32it/s]
 29%|██▉       | 57/196 [00:49<01:51,  1.25it/s]
 30%|██▉       | 58/196 [00:50<01:52,  1.23it/s]
 30%|███       | 59/196 [00:50<01:49,  1.25it/s]
 31%|███       | 60/196 [00:51<01:37,  1.39it/s]
 31%|███       | 61/196 [00:52<01:32,  1.47it/s]
 32%|███▏      | 62/196 [00:52<01:33,  1.44it/s]
 32%|███▏      | 63/196 [00:53<01:34,  1.41it/s]
 33%|███▎      | 64/196 [00:54<01:33,  1.41it/s]
 33%|███▎      | 65/196 [00:54<01:31,  1.43it/s]
 34%|███▎      | 66/196 [00:55<01:37,  1.34it/s]
 34%|███▍      | 67/196 [00:56<01:39,  1.30it/s]
 35%|███▍      | 68/196 [00:57<01:50,  1.16it/s]
 35%|███▌      | 69/196 [00:58<01:48,  1.17it/s]
 36%|███▌      | 70/196 [00:59<01:41,  1.24it/s]
 36%|███▌      | 71/196 [00:59<01:35,  1.32it/s]
 37%|███▋      | 72/196 [01:00<01:29,  1.39it/s]
 37%|███▋      | 73/196 [01:01<01:21,  1.50it/s]
 38%|███▊      | 74/196 [01:01<01:17,  1.57it/s]
 38%|███▊      | 75/196 [01:02<01:15,  1.60it/s]
 39%|███▉      | 76/196 [01:02<01:13,  1.62it/s]
 39%|███▉      | 77/196 [01:03<01:17,  1.54it/s]
 40%|███▉      | 78/196 [01:04<01:18,  1.51it/s]
 40%|████      | 79/196 [01:04<01:16,  1.53it/s]
 41%|████      | 80/196 [01:05<01:20,  1.43it/s]
 41%|████▏     | 81/196 [01:06<01:21,  1.42it/s]
 42%|████▏     | 82/196 [01:07<01:19,  1.43it/s]
 42%|████▏     | 83/196 [01:07<01:21,  1.38it/s]
 43%|████▎     | 84/196 [01:08<01:21,  1.38it/s]
 43%|████▎     | 85/196 [01:09<01:20,  1.37it/s]
 44%|████▍     | 86/196 [01:10<01:22,  1.33it/s]
 44%|████▍     | 87/196 [01:10<01:21,  1.34it/s]
 45%|████▍     | 88/196 [01:11<01:22,  1.31it/s]
 45%|████▌     | 89/196 [01:12<01:24,  1.27it/s]
 46%|████▌     | 90/196 [01:13<01:22,  1.29it/s]
 46%|████▋     | 91/196 [01:13<01:17,  1.36it/s]
 47%|████▋     | 92/196 [01:14<01:13,  1.41it/s]
 47%|████▋     | 93/196 [01:15<01:17,  1.33it/s]
 48%|████▊     | 94/196 [01:16<01:15,  1.34it/s]
 48%|████▊     | 95/196 [01:16<01:14,  1.36it/s]
 49%|████▉     | 96/196 [01:17<01:16,  1.30it/s]
 49%|████▉     | 97/196 [01:18<01:13,  1.35it/s]
 50%|█████     | 98/196 [01:19<01:13,  1.33it/s]
 51%|█████     | 99/196 [01:19<01:09,  1.39it/s]
 51%|█████     | 100/196 [01:20<01:01,  1.57it/s]
 52%|█████▏    | 101/196 [01:20<00:59,  1.60it/s]
 52%|█████▏    | 102/196 [01:21<01:02,  1.50it/s]
 53%|█████▎    | 103/196 [01:22<01:08,  1.36it/s]
 53%|█████▎    | 104/196 [01:23<01:15,  1.22it/s]
 54%|█████▎    | 105/196 [01:24<01:15,  1.20it/s]
 54%|█████▍    | 106/196 [01:25<01:13,  1.22it/s]
 55%|█████▍    | 107/196 [01:25<01:08,  1.30it/s]
 55%|█████▌    | 108/196 [01:26<01:01,  1.44it/s]
 56%|█████▌    | 109/196 [01:26<00:57,  1.51it/s]
 56%|█████▌    | 110/196 [01:27<00:56,  1.52it/s]
 57%|█████▋    | 111/196 [01:28<00:56,  1.51it/s]
 57%|█████▋    | 112/196 [01:28<00:57,  1.45it/s]
 58%|█████▊    | 113/196 [01:29<00:56,  1.47it/s]
 58%|█████▊    | 114/196 [01:30<00:52,  1.57it/s]
 59%|█████▊    | 115/196 [01:30<00:50,  1.59it/s]
 59%|█████▉    | 116/196 [01:31<00:49,  1.60it/s]
 60%|█████▉    | 117/196 [01:31<00:46,  1.70it/s]
 60%|██████    | 118/196 [01:32<00:41,  1.86it/s]
 61%|██████    | 119/196 [01:32<00:44,  1.72it/s]
 61%|██████    | 120/196 [01:33<00:45,  1.66it/s]
 62%|██████▏   | 121/196 [01:34<00:46,  1.63it/s]
 62%|██████▏   | 122/196 [01:34<00:46,  1.59it/s]
 63%|██████▎   | 123/196 [01:35<00:44,  1.63it/s]
 63%|██████▎   | 124/196 [01:36<00:45,  1.58it/s]
 64%|██████▍   | 125/196 [01:36<00:45,  1.57it/s]
 64%|██████▍   | 126/196 [01:37<00:51,  1.37it/s]
 65%|██████▍   | 127/196 [01:38<00:48,  1.41it/s]
 65%|██████▌   | 128/196 [01:39<00:46,  1.47it/s]
 66%|██████▌   | 129/196 [01:39<00:44,  1.49it/s]
 66%|██████▋   | 130/196 [01:40<00:45,  1.46it/s]
 67%|██████▋   | 131/196 [01:41<00:43,  1.49it/s]
 67%|██████▋   | 132/196 [01:41<00:40,  1.58it/s]
 68%|██████▊   | 133/196 [01:42<00:39,  1.58it/s]
 68%|██████▊   | 134/196 [01:42<00:40,  1.53it/s]
 69%|██████▉   | 135/196 [01:43<00:39,  1.56it/s]
 69%|██████▉   | 136/196 [01:44<00:38,  1.57it/s]
 70%|██████▉   | 137/196 [01:44<00:37,  1.57it/s]
 70%|███████   | 138/196 [01:45<00:36,  1.58it/s]
 71%|███████   | 139/196 [01:46<00:37,  1.53it/s]
 71%|███████▏  | 140/196 [01:46<00:35,  1.58it/s]
 72%|███████▏  | 141/196 [01:47<00:34,  1.61it/s]
 72%|███████▏  | 142/196 [01:47<00:34,  1.57it/s]
 73%|███████▎  | 143/196 [01:48<00:35,  1.50it/s]
 73%|███████▎  | 144/196 [01:49<00:33,  1.55it/s]
 74%|███████▍  | 145/196 [01:49<00:31,  1.63it/s]
 74%|███████▍  | 146/196 [01:50<00:29,  1.70it/s]
 75%|███████▌  | 147/196 [01:50<00:28,  1.72it/s]
 76%|███████▌  | 148/196 [01:51<00:28,  1.70it/s]
 76%|███████▌  | 149/196 [01:52<00:26,  1.79it/s]
 77%|███████▋  | 150/196 [01:52<00:27,  1.65it/s]
 77%|███████▋  | 151/196 [01:53<00:28,  1.60it/s]
 78%|███████▊  | 152/196 [01:54<00:27,  1.59it/s]
 78%|███████▊  | 153/196 [01:54<00:27,  1.59it/s]
 79%|███████▊  | 154/196 [01:55<00:26,  1.59it/s]
 79%|███████▉  | 155/196 [01:56<00:27,  1.47it/s]
 80%|███████▉  | 156/196 [01:57<00:29,  1.35it/s]
 80%|████████  | 157/196 [01:57<00:30,  1.30it/s]
 81%|████████  | 158/196 [01:58<00:26,  1.44it/s]
 81%|████████  | 159/196 [01:58<00:23,  1.54it/s]
 82%|████████▏ | 160/196 [01:59<00:22,  1.57it/s]
 82%|████████▏ | 161/196 [02:00<00:22,  1.54it/s]
 83%|████████▎ | 162/196 [02:00<00:21,  1.57it/s]
 83%|████████▎ | 163/196 [02:01<00:20,  1.59it/s]
 84%|████████▎ | 164/196 [02:02<00:20,  1.59it/s]
 84%|████████▍ | 165/196 [02:02<00:20,  1.54it/s]
 85%|████████▍ | 166/196 [02:03<00:19,  1.58it/s]
 85%|████████▌ | 167/196 [02:03<00:18,  1.61it/s]
 86%|████████▌ | 168/196 [02:04<00:16,  1.70it/s]
 86%|████████▌ | 169/196 [02:05<00:16,  1.61it/s]
 87%|████████▋ | 170/196 [02:05<00:17,  1.51it/s]
 87%|████████▋ | 171/196 [02:06<00:16,  1.53it/s]
 88%|████████▊ | 172/196 [02:07<00:16,  1.50it/s]
 88%|████████▊ | 173/196 [02:07<00:15,  1.50it/s]
 89%|████████▉ | 174/196 [02:08<00:15,  1.42it/s]
 89%|████████▉ | 175/196 [02:09<00:18,  1.14it/s]
 90%|████████▉ | 176/196 [02:12<00:25,  1.28s/it]
 90%|█████████ | 177/196 [02:14<00:27,  1.45s/it]
 91%|█████████ | 178/196 [02:16<00:29,  1.62s/it]
 91%|█████████▏| 179/196 [02:17<00:27,  1.62s/it]
 92%|█████████▏| 180/196 [02:18<00:21,  1.33s/it]
 92%|█████████▏| 181/196 [02:18<00:16,  1.13s/it]
 93%|█████████▎| 182/196 [02:19<00:13,  1.01it/s]
 93%|█████████▎| 183/196 [02:20<00:12,  1.02it/s]
 94%|█████████▍| 184/196 [02:21<00:10,  1.14it/s]
 94%|█████████▍| 185/196 [02:22<00:09,  1.18it/s]
 95%|█████████▍| 186/196 [02:22<00:08,  1.17it/s]
 95%|█████████▌| 187/196 [02:23<00:07,  1.26it/s]
 96%|█████████▌| 188/196 [02:24<00:05,  1.34it/s]
 96%|█████████▋| 189/196 [02:24<00:05,  1.38it/s]
 97%|█████████▋| 190/196 [02:25<00:04,  1.46it/s]
 97%|█████████▋| 191/196 [02:26<00:03,  1.53it/s]
 98%|█████████▊| 192/196 [02:26<00:02,  1.51it/s]
 98%|█████████▊| 193/196 [02:27<00:02,  1.50it/s]
 99%|█████████▉| 194/196 [02:28<00:01,  1.52it/s]
 99%|█████████▉| 195/196 [02:28<00:00,  1.57it/s]
100%|██████████| 196/196 [02:28<00:00,  1.95it/s]
100%|██████████| 196/196 [02:36<00:00,  1.26it/s]