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-20240822_172108-s5ed6d0k
wandb: Run `wandb offline` to turn off syncing.
wandb: Syncing run eval_pd2000_s300_shuff500_hindi
wandb: ⭐️ View project at https://wandb.ai/priyanshipal/huggingface
wandb: 🚀 View run at https://wandb.ai/priyanshipal/huggingface/runs/s5ed6d0k
/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(

Generating train split: 0 examples [00:00, ? examples/s]
Generating train split: 2564 examples [00:00, 6589.90 examples/s]
Generating train split: 2564 examples [00:00, 6548.28 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/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(
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%|          | 0/2564 [00:00<?, ? examples/s]
preprocess datasets:   0%|          | 1/2564 [00:06<4:28:27,  6.28s/ examples]
preprocess datasets:   0%|          | 9/2564 [00:06<22:06,  1.93 examples/s]  
preprocess datasets:   1%|          | 17/2564 [00:06<09:50,  4.31 examples/s]
preprocess datasets:   1%|          | 25/2564 [00:06<05:41,  7.44 examples/s]
preprocess datasets:   1%|▏         | 33/2564 [00:06<03:41, 11.41 examples/s]
preprocess datasets:   2%|▏         | 41/2564 [00:06<02:33, 16.41 examples/s]
preprocess datasets:   2%|▏         | 50/2564 [00:06<01:49, 23.05 examples/s]
preprocess datasets:   2%|▏         | 63/2564 [00:07<01:11, 34.86 examples/s]
preprocess datasets:   3%|▎         | 74/2564 [00:07<00:55, 44.58 examples/s]
preprocess datasets:   3%|▎         | 84/2564 [00:07<00:47, 52.64 examples/s]
preprocess datasets:   4%|▎         | 95/2564 [00:07<00:43, 56.60 examples/s]
preprocess datasets:   4%|▍         | 106/2564 [00:07<00:39, 62.87 examples/s]
preprocess datasets:   5%|▍         | 118/2564 [00:07<00:34, 71.56 examples/s]
preprocess datasets:   5%|▍         | 127/2564 [00:07<00:33, 72.28 examples/s]
preprocess datasets:   5%|▌         | 139/2564 [00:08<00:33, 71.82 examples/s]
preprocess datasets:   6%|▌         | 153/2564 [00:08<00:32, 74.80 examples/s]
preprocess datasets:   6%|▋         | 162/2564 [00:08<00:32, 73.47 examples/s]
preprocess datasets:   7%|▋         | 172/2564 [00:08<00:30, 78.99 examples/s]
preprocess datasets:   7%|▋         | 182/2564 [00:08<00:28, 82.29 examples/s]
preprocess datasets:   7%|▋         | 192/2564 [00:08<00:28, 82.78 examples/s]
preprocess datasets:   8%|▊         | 205/2564 [00:08<00:25, 91.00 examples/s]
preprocess datasets:   8%|▊         | 216/2564 [00:08<00:26, 89.02 examples/s]
preprocess datasets:   9%|▉         | 226/2564 [00:09<00:26, 86.94 examples/s]
preprocess datasets:   9%|▉         | 235/2564 [00:09<00:28, 82.50 examples/s]
preprocess datasets:  10%|▉         | 249/2564 [00:09<00:24, 93.62 examples/s]
preprocess datasets:  10%|█         | 259/2564 [00:09<00:24, 94.93 examples/s]
preprocess datasets:  11%|█         | 275/2564 [00:09<00:20, 111.42 examples/s]
preprocess datasets:  11%|█▏        | 289/2564 [00:09<00:20, 111.23 examples/s]
preprocess datasets:  12%|█▏        | 301/2564 [00:09<00:20, 108.81 examples/s]
preprocess datasets:  12%|█▏        | 315/2564 [00:09<00:19, 116.79 examples/s]
preprocess datasets:  13%|█▎        | 330/2564 [00:09<00:21, 104.23 examples/s]
preprocess datasets:  13%|█▎        | 345/2564 [00:10<00:19, 113.78 examples/s]
preprocess datasets:  14%|█▍        | 360/2564 [00:10<00:18, 118.32 examples/s]
preprocess datasets:  15%|█▍        | 374/2564 [00:10<00:21, 100.59 examples/s]
preprocess datasets:  15%|█▌        | 390/2564 [00:10<00:21, 101.27 examples/s]
preprocess datasets:  16%|█▌        | 403/2564 [00:10<00:20, 107.41 examples/s]
preprocess datasets:  16%|█▋        | 417/2564 [00:10<00:19, 109.17 examples/s]
preprocess datasets:  17%|█▋        | 434/2564 [00:10<00:17, 121.46 examples/s]
preprocess datasets:  18%|█▊        | 451/2564 [00:10<00:16, 130.28 examples/s]
preprocess datasets:  18%|█▊        | 465/2564 [00:11<00:16, 129.82 examples/s]
preprocess datasets:  19%|█▉        | 481/2564 [00:11<00:15, 134.80 examples/s]
preprocess datasets:  20%|█▉        | 503/2564 [00:11<00:16, 128.05 examples/s]
preprocess datasets:  20%|██        | 520/2564 [00:11<00:15, 135.11 examples/s]
preprocess datasets:  21%|██        | 538/2564 [00:11<00:14, 136.85 examples/s]
preprocess datasets:  22%|██▏       | 553/2564 [00:11<00:15, 130.90 examples/s]
preprocess datasets:  22%|██▏       | 568/2564 [00:11<00:15, 132.85 examples/s]
preprocess datasets:  23%|██▎       | 586/2564 [00:11<00:14, 140.95 examples/s]
preprocess datasets:  24%|██▎       | 606/2564 [00:12<00:13, 149.19 examples/s]
preprocess datasets:  24%|██▍       | 627/2564 [00:12<00:11, 161.50 examples/s]
preprocess datasets:  25%|██▌       | 646/2564 [00:12<00:11, 161.62 examples/s]
preprocess datasets:  26%|██▌       | 666/2564 [00:12<00:13, 141.21 examples/s]
preprocess datasets:  27%|██▋       | 683/2564 [00:12<00:13, 143.02 examples/s]
preprocess datasets:  27%|██▋       | 702/2564 [00:12<00:13, 137.77 examples/s]
preprocess datasets:  28%|██▊       | 723/2564 [00:12<00:12, 150.66 examples/s]
preprocess datasets:  29%|██▉       | 741/2564 [00:12<00:11, 153.89 examples/s]
preprocess datasets:  30%|██▉       | 761/2564 [00:13<00:11, 163.28 examples/s]
preprocess datasets:  30%|███       | 780/2564 [00:13<00:10, 164.26 examples/s]
preprocess datasets:  31%|███▏      | 803/2564 [00:13<00:12, 135.87 examples/s]
preprocess datasets:  32%|███▏      | 825/2564 [00:13<00:13, 132.25 examples/s]
preprocess datasets:  33%|███▎      | 841/2564 [00:13<00:12, 135.20 examples/s]
preprocess datasets:  33%|███▎      | 858/2564 [00:13<00:12, 135.10 examples/s]
preprocess datasets:  34%|███▍      | 873/2564 [00:13<00:13, 126.05 examples/s]
preprocess datasets:  35%|███▍      | 892/2564 [00:14<00:11, 140.40 examples/s]
preprocess datasets:  35%|███▌      | 907/2564 [00:14<00:11, 141.28 examples/s]
preprocess datasets:  36%|███▋      | 932/2564 [00:14<00:10, 162.79 examples/s]
preprocess datasets:  37%|███▋      | 957/2564 [00:14<00:09, 177.23 examples/s]
preprocess datasets:  38%|███▊      | 981/2564 [00:14<00:09, 166.19 examples/s]
preprocess datasets:  39%|███▉      | 1000/2564 [00:15<00:29, 53.83 examples/s]
preprocess datasets:  40%|███▉      | 1018/2564 [00:15<00:23, 65.85 examples/s]
preprocess datasets:  40%|████      | 1038/2564 [00:15<00:18, 81.55 examples/s]
preprocess datasets:  41%|████▏     | 1062/2564 [00:15<00:15, 95.85 examples/s]
preprocess datasets:  42%|████▏     | 1089/2564 [00:16<00:12, 122.00 examples/s]
preprocess datasets:  43%|████▎     | 1110/2564 [00:16<00:11, 131.36 examples/s]
preprocess datasets:  44%|████▍     | 1132/2564 [00:16<00:10, 130.37 examples/s]
preprocess datasets:  45%|████▌     | 1155/2564 [00:16<00:10, 133.30 examples/s]
preprocess datasets:  46%|████▌     | 1173/2564 [00:16<00:09, 142.00 examples/s]
preprocess datasets:  47%|████▋     | 1205/2564 [00:16<00:07, 180.13 examples/s]
preprocess datasets:  48%|████▊     | 1232/2564 [00:16<00:07, 175.93 examples/s]
preprocess datasets:  49%|████▉     | 1256/2564 [00:17<00:06, 190.42 examples/s]
preprocess datasets:  50%|█████     | 1286/2564 [00:17<00:06, 184.52 examples/s]
preprocess datasets:  51%|█████     | 1308/2564 [00:17<00:06, 191.06 examples/s]
preprocess datasets:  52%|█████▏    | 1341/2564 [00:17<00:06, 190.42 examples/s]
preprocess datasets:  53%|█████▎    | 1364/2564 [00:17<00:06, 198.32 examples/s]
preprocess datasets:  54%|█████▍    | 1387/2564 [00:17<00:06, 173.46 examples/s]
preprocess datasets:  55%|█████▍    | 1407/2564 [00:17<00:07, 152.57 examples/s]
preprocess datasets:  56%|█████▌    | 1427/2564 [00:18<00:07, 156.97 examples/s]
preprocess datasets:  57%|█████▋    | 1452/2564 [00:18<00:06, 171.95 examples/s]
preprocess datasets:  57%|█████▋    | 1470/2564 [00:18<00:06, 168.43 examples/s]
preprocess datasets:  58%|█████▊    | 1497/2564 [00:18<00:05, 189.43 examples/s]
preprocess datasets:  59%|█████▉    | 1522/2564 [00:18<00:05, 204.59 examples/s]
preprocess datasets:  61%|██████    | 1553/2564 [00:18<00:05, 197.18 examples/s]
preprocess datasets:  62%|██████▏   | 1577/2564 [00:18<00:05, 180.88 examples/s]
preprocess datasets:  63%|██████▎   | 1603/2564 [00:18<00:04, 197.31 examples/s]
preprocess datasets:  63%|██████▎   | 1624/2564 [00:19<00:04, 190.15 examples/s]
preprocess datasets:  64%|██████▍   | 1652/2564 [00:19<00:04, 186.03 examples/s]
preprocess datasets:  66%|██████▌   | 1683/2564 [00:19<00:04, 213.71 examples/s]
preprocess datasets:  67%|██████▋   | 1709/2564 [00:19<00:03, 222.11 examples/s]
preprocess datasets:  68%|██████▊   | 1742/2564 [00:19<00:03, 209.36 examples/s]
preprocess datasets:  69%|██████▉   | 1772/2564 [00:19<00:03, 200.23 examples/s]
preprocess datasets:  70%|███████   | 1798/2564 [00:19<00:04, 184.88 examples/s]
preprocess datasets:  71%|███████▏  | 1827/2564 [00:20<00:03, 184.64 examples/s]
preprocess datasets:  72%|███████▏  | 1854/2564 [00:20<00:03, 179.24 examples/s]
preprocess datasets:  73%|███████▎  | 1877/2564 [00:20<00:04, 162.20 examples/s]
preprocess datasets:  74%|███████▍  | 1904/2564 [00:20<00:03, 182.83 examples/s]
preprocess datasets:  76%|███████▌  | 1938/2564 [00:20<00:03, 187.44 examples/s]
preprocess datasets:  77%|███████▋  | 1962/2564 [00:20<00:03, 194.36 examples/s]
preprocess datasets:  77%|███████▋  | 1983/2564 [00:20<00:03, 162.70 examples/s]
preprocess datasets:  78%|███████▊  | 2007/2564 [00:21<00:08, 68.91 examples/s] 
preprocess datasets:  79%|███████▉  | 2029/2564 [00:21<00:06, 83.19 examples/s]
preprocess datasets:  80%|███████▉  | 2047/2564 [00:22<00:05, 95.22 examples/s]
preprocess datasets:  81%|████████  | 2069/2564 [00:22<00:04, 108.74 examples/s]
preprocess datasets:  82%|████████▏ | 2105/2564 [00:22<00:03, 151.49 examples/s]
preprocess datasets:  83%|████████▎ | 2128/2564 [00:22<00:02, 164.39 examples/s]
preprocess datasets:  84%|████████▍ | 2153/2564 [00:22<00:02, 159.80 examples/s]
preprocess datasets:  85%|████████▍ | 2178/2564 [00:22<00:02, 176.01 examples/s]
preprocess datasets:  86%|████████▌ | 2207/2564 [00:22<00:02, 150.06 examples/s]
preprocess datasets:  87%|████████▋ | 2229/2564 [00:23<00:02, 162.29 examples/s]
preprocess datasets:  88%|████████▊ | 2252/2564 [00:23<00:01, 173.29 examples/s]
preprocess datasets:  89%|████████▊ | 2275/2564 [00:23<00:01, 185.31 examples/s]
preprocess datasets:  90%|████████▉ | 2298/2564 [00:23<00:01, 173.62 examples/s]
preprocess datasets:  90%|█████████ | 2317/2564 [00:23<00:01, 173.10 examples/s]
preprocess datasets:  91%|█████████ | 2336/2564 [00:23<00:01, 176.79 examples/s]
preprocess datasets:  92%|█████████▏| 2355/2564 [00:23<00:01, 175.53 examples/s]
preprocess datasets:  93%|█████████▎| 2377/2564 [00:23<00:01, 129.10 examples/s]
preprocess datasets:  93%|█████████▎| 2395/2564 [00:24<00:01, 133.50 examples/s]
preprocess datasets:  94%|█████████▍| 2411/2564 [00:24<00:01, 134.91 examples/s]
preprocess datasets:  95%|█████████▍| 2430/2564 [00:24<00:00, 142.74 examples/s]
preprocess datasets:  95%|█████████▌| 2446/2564 [00:24<00:00, 142.36 examples/s]
preprocess datasets:  96%|█████████▌| 2465/2564 [00:24<00:00, 147.32 examples/s]
preprocess datasets:  97%|█████████▋| 2482/2564 [00:24<00:00, 149.64 examples/s]
preprocess datasets:  98%|█████████▊| 2503/2564 [00:24<00:00, 164.26 examples/s]
preprocess datasets:  98%|█████████▊| 2524/2564 [00:24<00:00, 146.52 examples/s]
preprocess datasets:  99%|█████████▉| 2541/2564 [00:25<00:00, 131.95 examples/s]
preprocess datasets: 100%|█████████▉| 2561/2564 [00:25<00:00, 143.40 examples/s]
preprocess datasets: 100%|██████████| 2564/2564 [00:25<00:00, 99.60 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
check the eval set length 2564
08/22/2024 17:21:47 - 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%|          | 0/161 [00:00<?, ?it/s]
  1%|          | 2/161 [00:00<01:06,  2.39it/s]
  2%|▏         | 3/161 [00:01<01:24,  1.86it/s]
  2%|▏         | 4/161 [00:02<01:45,  1.48it/s]
  3%|▎         | 5/161 [00:03<01:56,  1.34it/s]
  4%|▎         | 6/161 [00:04<02:00,  1.28it/s]
  4%|▍         | 7/161 [00:05<02:27,  1.05it/s]
  5%|▍         | 8/161 [00:07<03:20,  1.31s/it]
  6%|▌         | 9/161 [00:09<03:43,  1.47s/it]
  6%|▌         | 10/161 [00:10<03:16,  1.30s/it]
  7%|▋         | 11/161 [00:11<02:46,  1.11s/it]
  7%|▋         | 12/161 [00:11<02:21,  1.05it/s]
  8%|▊         | 13/161 [00:12<02:16,  1.08it/s]
  9%|▊         | 14/161 [00:13<02:35,  1.06s/it]
  9%|▉         | 15/161 [00:15<02:54,  1.19s/it]
 10%|▉         | 16/161 [00:16<02:42,  1.12s/it]
 11%|█         | 17/161 [00:16<02:18,  1.04it/s]
 11%|█         | 18/161 [00:17<02:03,  1.15it/s]
 12%|█▏        | 19/161 [00:18<01:54,  1.24it/s]
 12%|█▏        | 20/161 [00:18<01:51,  1.26it/s]
 13%|█▎        | 21/161 [00:19<01:40,  1.39it/s]
 14%|█▎        | 22/161 [00:20<01:45,  1.32it/s]
 14%|█▍        | 23/161 [00:22<02:23,  1.04s/it]
 15%|█▍        | 24/161 [00:23<02:23,  1.05s/it]
 16%|█▌        | 25/161 [00:23<02:13,  1.02it/s]
 16%|█▌        | 26/161 [00:24<02:04,  1.09it/s]
 17%|█▋        | 27/161 [00:25<01:55,  1.16it/s]
 17%|█▋        | 28/161 [00:26<01:49,  1.21it/s]
 18%|█▊        | 29/161 [00:26<01:44,  1.26it/s]
 19%|█▊        | 30/161 [00:27<01:40,  1.30it/s]
 19%|█▉        | 31/161 [00:28<01:32,  1.41it/s]
 20%|█▉        | 32/161 [00:28<01:27,  1.48it/s]
 20%|██        | 33/161 [00:29<01:26,  1.48it/s]
 21%|██        | 34/161 [00:30<01:23,  1.52it/s]
 22%|██▏       | 35/161 [00:30<01:21,  1.55it/s]
 22%|██▏       | 36/161 [00:31<01:18,  1.59it/s]
 23%|██▎       | 37/161 [00:31<01:16,  1.63it/s]
 24%|██▎       | 38/161 [00:32<01:16,  1.61it/s]
 24%|██▍       | 39/161 [00:33<01:20,  1.51it/s]
 25%|██▍       | 40/161 [00:34<01:26,  1.40it/s]
 25%|██▌       | 41/161 [00:34<01:32,  1.29it/s]
 26%|██▌       | 42/161 [00:35<01:37,  1.22it/s]
 27%|██▋       | 43/161 [00:36<01:36,  1.22it/s]
 27%|██▋       | 44/161 [00:37<01:37,  1.20it/s]
 28%|██▊       | 45/161 [00:38<01:29,  1.29it/s]
 29%|██▊       | 46/161 [00:38<01:24,  1.37it/s]
 29%|██▉       | 47/161 [00:39<01:24,  1.35it/s]
 30%|██▉       | 48/161 [00:40<01:24,  1.34it/s]
 30%|███       | 49/161 [00:41<01:23,  1.35it/s]
 31%|███       | 50/161 [00:41<01:23,  1.32it/s]
 32%|███▏      | 51/161 [00:42<01:25,  1.29it/s]
 32%|███▏      | 52/161 [00:43<01:29,  1.21it/s]
 33%|███▎      | 53/161 [00:44<01:33,  1.15it/s]
 34%|███▎      | 54/161 [00:45<01:30,  1.18it/s]
 34%|███▍      | 55/161 [00:46<01:23,  1.27it/s]
 35%|███▍      | 56/161 [00:46<01:16,  1.37it/s]
 35%|███▌      | 57/161 [00:47<01:11,  1.45it/s]
 36%|███▌      | 58/161 [00:47<01:08,  1.50it/s]
 37%|███▋      | 59/161 [00:48<01:06,  1.54it/s]
 37%|███▋      | 60/161 [00:49<01:03,  1.60it/s]
 38%|███▊      | 61/161 [00:49<01:05,  1.53it/s]
 39%|███▊      | 62/161 [00:50<01:05,  1.51it/s]
 39%|███▉      | 63/161 [00:51<01:04,  1.51it/s]
 40%|███▉      | 64/161 [00:51<01:06,  1.45it/s]
 40%|████      | 65/161 [00:52<01:07,  1.42it/s]
 41%|████      | 66/161 [00:53<01:09,  1.37it/s]
 42%|████▏     | 67/161 [00:54<01:09,  1.36it/s]
 42%|████▏     | 68/161 [00:54<01:10,  1.33it/s]
 43%|████▎     | 69/161 [00:55<01:08,  1.34it/s]
 43%|████▎     | 70/161 [00:56<01:10,  1.29it/s]
 44%|████▍     | 71/161 [00:57<01:09,  1.30it/s]
 45%|████▍     | 72/161 [00:58<01:11,  1.24it/s]
 45%|████▌     | 73/161 [00:59<01:11,  1.23it/s]
 46%|████▌     | 74/161 [00:59<01:09,  1.25it/s]
 47%|████▋     | 75/161 [01:00<01:03,  1.36it/s]
 47%|████▋     | 76/161 [01:01<01:02,  1.36it/s]
 48%|████▊     | 77/161 [01:01<01:03,  1.32it/s]
 48%|████▊     | 78/161 [01:02<01:04,  1.28it/s]
 49%|████▉     | 79/161 [01:03<01:05,  1.26it/s]
 50%|████▉     | 80/161 [01:04<01:02,  1.29it/s]
 50%|█████     | 81/161 [01:05<01:02,  1.28it/s]
 51%|█████     | 82/161 [01:05<00:57,  1.38it/s]
 52%|█████▏    | 83/161 [01:06<00:50,  1.53it/s]
 52%|█████▏    | 84/161 [01:06<00:48,  1.59it/s]
 53%|█████▎    | 85/161 [01:07<00:51,  1.48it/s]
 53%|█████▎    | 86/161 [01:08<00:53,  1.41it/s]
 54%|█████▍    | 87/161 [01:09<00:57,  1.29it/s]
 55%|█████▍    | 88/161 [01:10<01:01,  1.20it/s]
 55%|█████▌    | 89/161 [01:11<01:00,  1.20it/s]
 56%|█████▌    | 90/161 [01:11<00:56,  1.25it/s]
 57%|█████▋    | 91/161 [01:12<00:52,  1.34it/s]
 57%|█████▋    | 92/161 [01:13<00:49,  1.39it/s]
 58%|█████▊    | 93/161 [01:13<00:48,  1.40it/s]
 58%|█████▊    | 94/161 [01:14<00:47,  1.42it/s]
 59%|█████▉    | 95/161 [01:15<00:46,  1.43it/s]
 60%|█████▉    | 96/161 [01:15<00:42,  1.54it/s]
 60%|██████    | 97/161 [01:16<00:42,  1.52it/s]
 61%|██████    | 98/161 [01:16<00:41,  1.51it/s]
 61%|██████▏   | 99/161 [01:17<00:40,  1.52it/s]
 62%|██████▏   | 100/161 [01:18<00:40,  1.50it/s]
 63%|██████▎   | 101/161 [01:18<00:38,  1.56it/s]
 63%|██████▎   | 102/161 [01:19<00:38,  1.52it/s]
 64%|██████▍   | 103/161 [01:20<00:38,  1.49it/s]
 65%|██████▍   | 104/161 [01:21<00:41,  1.38it/s]
 65%|██████▌   | 105/161 [01:21<00:41,  1.36it/s]
 66%|██████▌   | 106/161 [01:22<00:38,  1.44it/s]
 66%|██████▋   | 107/161 [01:23<00:35,  1.50it/s]
 67%|██████▋   | 108/161 [01:23<00:36,  1.47it/s]
 68%|██████▊   | 109/161 [01:24<00:35,  1.47it/s]
 68%|██████▊   | 110/161 [01:25<00:34,  1.48it/s]
 69%|██████▉   | 111/161 [01:25<00:34,  1.43it/s]
 70%|██████▉   | 112/161 [01:26<00:33,  1.45it/s]
 70%|███████   | 113/161 [01:27<00:32,  1.47it/s]
 71%|███████   | 114/161 [01:27<00:31,  1.50it/s]
 71%|███████▏  | 115/161 [01:28<00:30,  1.51it/s]
 72%|███████▏  | 116/161 [01:29<00:30,  1.48it/s]
 73%|███████▎  | 117/161 [01:29<00:30,  1.46it/s]
 73%|███████▎  | 118/161 [01:30<00:27,  1.59it/s]
 74%|███████▍  | 119/161 [01:31<00:25,  1.65it/s]
 75%|███████▍  | 120/161 [01:31<00:24,  1.68it/s]
 75%|███████▌  | 121/161 [01:32<00:23,  1.67it/s]
 76%|███████▌  | 122/161 [01:32<00:22,  1.75it/s]
 76%|███████▋  | 123/161 [01:33<00:23,  1.60it/s]
 77%|███████▋  | 124/161 [01:34<00:24,  1.54it/s]
 78%|███████▊  | 125/161 [01:34<00:22,  1.57it/s]
 78%|███████▊  | 126/161 [01:35<00:22,  1.57it/s]
 79%|███████▉  | 127/161 [01:36<00:22,  1.53it/s]
 80%|███████▉  | 128/161 [01:36<00:22,  1.49it/s]
 80%|████████  | 129/161 [01:37<00:24,  1.33it/s]
 81%|████████  | 130/161 [01:38<00:23,  1.30it/s]
 81%|████████▏ | 131/161 [01:39<00:21,  1.42it/s]
 82%|████████▏ | 132/161 [01:39<00:19,  1.47it/s]
 83%|████████▎ | 133/161 [01:40<00:18,  1.51it/s]
 83%|████████▎ | 134/161 [01:41<00:18,  1.49it/s]
 84%|████████▍ | 135/161 [01:41<00:17,  1.50it/s]
 84%|████████▍ | 136/161 [01:42<00:16,  1.51it/s]
 85%|████████▌ | 137/161 [01:43<00:16,  1.48it/s]
 86%|████████▌ | 138/161 [01:43<00:15,  1.52it/s]
 86%|████████▋ | 139/161 [01:44<00:13,  1.57it/s]
 87%|████████▋ | 140/161 [01:44<00:13,  1.56it/s]
 88%|████████▊ | 141/161 [01:45<00:13,  1.48it/s]
 88%|████████▊ | 142/161 [01:46<00:12,  1.46it/s]
 89%|████████▉ | 143/161 [01:47<00:12,  1.48it/s]
 89%|████████▉ | 144/161 [01:47<00:11,  1.47it/s]
 90%|█████████ | 145/161 [01:48<00:10,  1.47it/s]
 91%|█████████ | 146/161 [01:49<00:10,  1.38it/s]
 91%|█████████▏| 147/161 [01:51<00:14,  1.06s/it]
 92%|█████████▏| 148/161 [01:53<00:17,  1.36s/it]
 93%|█████████▎| 149/161 [01:54<00:15,  1.27s/it]
 93%|█████████▎| 150/161 [01:54<00:12,  1.11s/it]
 94%|█████████▍| 151/161 [01:55<00:09,  1.04it/s]
 94%|█████████▍| 152/161 [01:56<00:07,  1.15it/s]
 95%|█████████▌| 153/161 [01:57<00:07,  1.11it/s]
 96%|█████████▌| 154/161 [01:58<00:06,  1.13it/s]
 96%|█████████▋| 155/161 [01:58<00:05,  1.12it/s]
 97%|█████████▋| 156/161 [01:59<00:04,  1.21it/s]
 98%|█████████▊| 157/161 [02:00<00:03,  1.28it/s]
 98%|█████████▊| 158/161 [02:01<00:02,  1.31it/s]
 99%|█████████▉| 159/161 [02:01<00:01,  1.43it/s]
 99%|█████████▉| 160/161 [02:01<00:00,  1.73it/s]
100%|██████████| 161/161 [02:02<00:00,  2.04it/s]
100%|██████████| 161/161 [02:07<00:00,  1.26it/s]
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 इस mission पर अधिक जानकारी दिए गए लिंक पर उपलब्ध है


last prediction string दिए गयए linक पर उपलब्ध हैspoken hypen tutorial  org slaश nmct hypenintro
***** eval metrics *****
  eval_cer                    =     0.3161
  eval_loss                   =     1.5929
  eval_model_preparation_time =     0.0054
  eval_runtime                = 0:02:18.43
  eval_samples                =       2564
  eval_samples_per_second     =     18.522
  eval_steps_per_second       =      1.163
  eval_wer                    =     0.4992

json-train.arrow:   0%|          | 0.00/633k [00:00<?, ?B/s]

Upload 3 LFS files:   0%|          | 0/3 [00:00<?, ?it/s]


model.safetensors:   0%|          | 0.00/1.26G [00:00<?, ?B/s]



training_args.bin:   0%|          | 0.00/5.43k [00:00<?, ?B/s]


model.safetensors:   0%|          | 2.26M/1.26G [00:00<01:10, 18.0MB/s]
training_args.bin: 100%|██████████| 5.43k/5.43k [00:00<00:00, 26.1kB/s]



model.safetensors:   0%|          | 4.06M/1.26G [00:00<02:34, 8.15MB/s]


model.safetensors:   0%|          | 5.13M/1.26G [00:00<02:35, 8.10MB/s]


model.safetensors:   1%|          | 6.88M/1.26G [00:00<02:00, 10.4MB/s]
json-train.arrow: 100%|██████████| 633k/633k [00:00<00:00, 866kB/s]



model.safetensors:   1%|          | 11.4M/1.26G [00:00<01:07, 18.6MB/s]

Upload 3 LFS files:  33%|███▎      | 1/3 [00:00<00:01,  1.03it/s]


model.safetensors:   1%|▏         | 16.0M/1.26G [00:01<01:27, 14.2MB/s]


model.safetensors:   2%|▏         | 19.1M/1.26G [00:01<01:16, 16.2MB/s]


model.safetensors:   2%|▏         | 21.1M/1.26G [00:01<01:16, 16.1MB/s]


model.safetensors:   2%|▏         | 23.1M/1.26G [00:01<01:24, 14.8MB/s]


model.safetensors:   2%|▏         | 24.7M/1.26G [00:02<02:28, 8.36MB/s]


model.safetensors:   2%|▏         | 27.6M/1.26G [00:02<01:55, 10.7MB/s]


model.safetensors:   2%|▏         | 30.5M/1.26G [00:02<01:30, 13.6MB/s]


model.safetensors:   3%|▎         | 32.4M/1.26G [00:02<02:33, 8.03MB/s]


model.safetensors:   4%|▍         | 47.7M/1.26G [00:03<00:46, 26.0MB/s]


model.safetensors:   4%|▍         | 52.9M/1.26G [00:03<00:57, 20.9MB/s]


model.safetensors:   5%|▍         | 56.9M/1.26G [00:03<01:02, 19.3MB/s]


model.safetensors:   5%|▍         | 60.2M/1.26G [00:04<01:41, 11.9MB/s]


model.safetensors:   5%|▍         | 63.0M/1.26G [00:04<01:29, 13.4MB/s]


model.safetensors:   5%|▌         | 65.5M/1.26G [00:04<01:59, 9.98MB/s]


model.safetensors:   5%|▌         | 68.2M/1.26G [00:05<01:48, 11.0MB/s]


model.safetensors:   6%|▌         | 70.1M/1.26G [00:05<01:42, 11.6MB/s]


model.safetensors:   6%|▌         | 72.2M/1.26G [00:05<02:28, 8.02MB/s]


model.safetensors:   6%|▌         | 73.7M/1.26G [00:05<02:22, 8.36MB/s]


model.safetensors:   6%|▌         | 75.1M/1.26G [00:06<02:10, 9.11MB/s]


model.safetensors:   6%|▋         | 79.0M/1.26G [00:06<01:27, 13.5MB/s]


model.safetensors:   6%|▋         | 80.9M/1.26G [00:06<02:03, 9.58MB/s]


model.safetensors:   8%|▊         | 95.6M/1.26G [00:06<00:39, 29.3MB/s]


model.safetensors:   8%|▊         | 101M/1.26G [00:06<00:43, 27.0MB/s] 


model.safetensors:   9%|▉         | 112M/1.26G [00:07<00:43, 26.2MB/s]


model.safetensors:  10%|▉         | 126M/1.26G [00:07<00:27, 41.2MB/s]


model.safetensors:  11%|█         | 133M/1.26G [00:07<00:38, 29.1MB/s]


model.safetensors:  11%|█         | 138M/1.26G [00:08<01:07, 16.8MB/s]


model.safetensors:  11%|█         | 142M/1.26G [00:08<01:03, 17.7MB/s]


model.safetensors:  12%|█▏        | 145M/1.26G [00:09<01:21, 13.6MB/s]


model.safetensors:  13%|█▎        | 159M/1.26G [00:09<00:43, 25.6MB/s]


model.safetensors:  13%|█▎        | 165M/1.26G [00:09<00:49, 22.3MB/s]


model.safetensors:  14%|█▍        | 176M/1.26G [00:10<00:48, 22.6MB/s]


model.safetensors:  15%|█▌        | 191M/1.26G [00:10<00:30, 35.6MB/s]


model.safetensors:  16%|█▌        | 198M/1.26G [00:10<00:32, 33.2MB/s]


model.safetensors:  16%|█▋        | 208M/1.26G [00:11<00:35, 29.8MB/s]


model.safetensors:  18%|█▊        | 223M/1.26G [00:11<00:23, 44.1MB/s]


model.safetensors:  18%|█▊        | 231M/1.26G [00:11<00:26, 38.3MB/s]


model.safetensors:  19%|█▉        | 240M/1.26G [00:11<00:30, 33.7MB/s]


model.safetensors:  20%|█▉        | 252M/1.26G [00:11<00:22, 44.6MB/s]


model.safetensors:  21%|██        | 259M/1.26G [00:12<00:29, 34.0MB/s]


model.safetensors:  21%|██▏       | 270M/1.26G [00:12<00:22, 44.0MB/s]


model.safetensors:  22%|██▏       | 277M/1.26G [00:12<00:30, 32.2MB/s]


model.safetensors:  23%|██▎       | 288M/1.26G [00:13<00:29, 33.1MB/s]


model.safetensors:  24%|██▍       | 303M/1.26G [00:13<00:19, 48.0MB/s]


model.safetensors:  25%|██▍       | 311M/1.26G [00:13<00:25, 37.7MB/s]


model.safetensors:  25%|██▌       | 320M/1.26G [00:13<00:27, 33.9MB/s]


model.safetensors:  27%|██▋       | 335M/1.26G [00:14<00:19, 48.7MB/s]


model.safetensors:  27%|██▋       | 343M/1.26G [00:14<00:24, 37.2MB/s]


model.safetensors:  28%|██▊       | 352M/1.26G [00:15<00:42, 21.4MB/s]


model.safetensors:  29%|██▉       | 367M/1.26G [00:15<00:27, 32.4MB/s]


model.safetensors:  30%|██▉       | 375M/1.26G [00:15<00:30, 29.1MB/s]


model.safetensors:  30%|███       | 384M/1.26G [00:16<00:31, 27.8MB/s]


model.safetensors:  32%|███▏      | 399M/1.26G [00:16<00:21, 40.9MB/s]


model.safetensors:  32%|███▏      | 407M/1.26G [00:16<00:24, 35.2MB/s]


model.safetensors:  33%|███▎      | 416M/1.26G [00:16<00:27, 31.0MB/s]


model.safetensors:  34%|███▍      | 431M/1.26G [00:17<00:18, 45.0MB/s]


model.safetensors:  35%|███▍      | 439M/1.26G [00:17<00:19, 41.9MB/s]


model.safetensors:  35%|███▌      | 448M/1.26G [00:17<00:26, 31.0MB/s]


model.safetensors:  37%|███▋      | 462M/1.26G [00:17<00:18, 43.7MB/s]


model.safetensors:  37%|███▋      | 470M/1.26G [00:18<00:26, 29.7MB/s]


model.safetensors:  38%|███▊      | 475M/1.26G [00:18<00:35, 22.1MB/s]


model.safetensors:  38%|███▊      | 480M/1.26G [00:19<00:33, 23.7MB/s]


model.safetensors:  38%|███▊      | 484M/1.26G [00:19<00:40, 19.3MB/s]


model.safetensors:  39%|███▉      | 495M/1.26G [00:19<00:25, 29.9MB/s]


model.safetensors:  40%|███▉      | 501M/1.26G [00:19<00:30, 25.1MB/s]


model.safetensors:  41%|████      | 512M/1.26G [00:20<00:25, 29.8MB/s]


model.safetensors:  42%|████▏     | 527M/1.26G [00:20<00:16, 45.7MB/s]


model.safetensors:  42%|████▏     | 535M/1.26G [00:21<00:30, 24.1MB/s]


model.safetensors:  43%|████▎     | 540M/1.26G [00:21<00:35, 20.5MB/s]


model.safetensors:  43%|████▎     | 544M/1.26G [00:22<00:46, 15.4MB/s]


model.safetensors:  43%|████▎     | 549M/1.26G [00:22<00:42, 16.7MB/s]


model.safetensors:  44%|████▎     | 552M/1.26G [00:22<00:45, 15.5MB/s]


model.safetensors:  44%|████▍     | 554M/1.26G [00:22<00:49, 14.2MB/s]


model.safetensors:  44%|████▍     | 557M/1.26G [00:22<00:46, 15.3MB/s]


model.safetensors:  44%|████▍     | 560M/1.26G [00:23<01:02, 11.2MB/s]


model.safetensors:  45%|████▍     | 565M/1.26G [00:23<00:48, 14.4MB/s]


model.safetensors:  45%|████▍     | 567M/1.26G [00:23<00:52, 13.1MB/s]


model.safetensors:  45%|████▌     | 568M/1.26G [00:23<00:56, 12.2MB/s]


model.safetensors:  45%|████▌     | 571M/1.26G [00:24<00:55, 12.6MB/s]


model.safetensors:  46%|████▌     | 576M/1.26G [00:24<00:38, 17.9MB/s]


model.safetensors:  46%|████▌     | 578M/1.26G [00:24<00:58, 11.8MB/s]


model.safetensors:  46%|████▌     | 581M/1.26G [00:24<00:57, 11.9MB/s]


model.safetensors:  46%|████▌     | 582M/1.26G [00:25<01:05, 10.4MB/s]


model.safetensors:  46%|████▌     | 584M/1.26G [00:25<01:04, 10.5MB/s]


model.safetensors:  46%|████▋     | 585M/1.26G [00:25<01:00, 11.2MB/s]


model.safetensors:  47%|████▋     | 589M/1.26G [00:25<00:45, 14.8MB/s]


model.safetensors:  47%|████▋     | 592M/1.26G [00:25<01:01, 10.9MB/s]


model.safetensors:  48%|████▊     | 607M/1.26G [00:26<00:20, 31.7MB/s]


model.safetensors:  49%|████▊     | 613M/1.26G [00:26<00:32, 20.2MB/s]


model.safetensors:  49%|████▉     | 617M/1.26G [00:26<00:37, 17.1MB/s]


model.safetensors:  49%|████▉     | 620M/1.26G [00:27<00:37, 17.1MB/s]


model.safetensors:  49%|████▉     | 622M/1.26G [00:27<00:35, 18.1MB/s]


model.safetensors:  50%|████▉     | 625M/1.26G [00:27<00:56, 11.2MB/s]


model.safetensors:  50%|████▉     | 629M/1.26G [00:27<00:46, 13.5MB/s]


model.safetensors:  50%|████▉     | 631M/1.26G [00:28<00:47, 13.2MB/s]


model.safetensors:  50%|█████     | 633M/1.26G [00:28<00:49, 12.7MB/s]


model.safetensors:  50%|█████     | 635M/1.26G [00:28<00:50, 12.5MB/s]


model.safetensors:  51%|█████     | 638M/1.26G [00:28<00:40, 15.4MB/s]


model.safetensors:  51%|█████     | 640M/1.26G [00:28<00:58, 10.6MB/s]


model.safetensors:  52%|█████▏    | 655M/1.26G [00:29<00:19, 31.7MB/s]


model.safetensors:  52%|█████▏    | 661M/1.26G [00:29<00:22, 26.6MB/s]


model.safetensors:  53%|█████▎    | 672M/1.26G [00:29<00:19, 29.6MB/s]


model.safetensors:  54%|█████▍    | 687M/1.26G [00:29<00:12, 46.6MB/s]


model.safetensors:  55%|█████▌    | 694M/1.26G [00:30<00:18, 30.0MB/s]


model.safetensors:  56%|█████▌    | 704M/1.26G [00:30<00:18, 29.8MB/s]


model.safetensors:  57%|█████▋    | 719M/1.26G [00:30<00:12, 44.1MB/s]


model.safetensors:  58%|█████▊    | 727M/1.26G [00:30<00:13, 40.0MB/s]


model.safetensors:  58%|█████▊    | 736M/1.26G [00:31<00:15, 34.1MB/s]


model.safetensors:  60%|█████▉    | 751M/1.26G [00:31<00:10, 49.2MB/s]


model.safetensors:  60%|██████    | 759M/1.26G [00:31<00:15, 32.2MB/s]


model.safetensors:  61%|██████    | 768M/1.26G [00:32<00:17, 29.0MB/s]


model.safetensors:  62%|██████▏   | 783M/1.26G [00:32<00:11, 42.3MB/s]


model.safetensors:  63%|██████▎   | 791M/1.26G [00:32<00:13, 36.2MB/s]


model.safetensors:  63%|██████▎   | 800M/1.26G [00:33<00:14, 31.8MB/s]


model.safetensors:  65%|██████▍   | 815M/1.26G [00:33<00:09, 45.9MB/s]


model.safetensors:  65%|██████▌   | 823M/1.26G [00:33<00:11, 39.2MB/s]


model.safetensors:  66%|██████▌   | 832M/1.26G [00:34<00:13, 31.5MB/s]


model.safetensors:  66%|██████▋   | 838M/1.26G [00:34<00:13, 31.1MB/s]


model.safetensors:  67%|██████▋   | 843M/1.26G [00:34<00:16, 24.9MB/s]


model.safetensors:  67%|██████▋   | 846M/1.26G [00:34<00:17, 23.7MB/s]


model.safetensors:  67%|██████▋   | 849M/1.26G [00:35<00:30, 13.7MB/s]


model.safetensors:  68%|██████▊   | 863M/1.26G [00:35<00:14, 26.7MB/s]


model.safetensors:  69%|██████▉   | 869M/1.26G [00:35<00:15, 25.8MB/s]


model.safetensors:  70%|██████▉   | 880M/1.26G [00:36<00:14, 27.0MB/s]


model.safetensors:  71%|███████   | 895M/1.26G [00:36<00:08, 42.0MB/s]


model.safetensors:  71%|███████▏  | 903M/1.26G [00:36<00:11, 32.2MB/s]


model.safetensors:  72%|███████▏  | 912M/1.26G [00:36<00:11, 31.3MB/s]


model.safetensors:  73%|███████▎  | 928M/1.26G [00:37<00:07, 46.0MB/s]


model.safetensors:  74%|███████▍  | 935M/1.26G [00:37<00:09, 33.1MB/s]


model.safetensors:  75%|███████▍  | 944M/1.26G [00:37<00:10, 29.9MB/s]


model.safetensors:  76%|███████▌  | 959M/1.26G [00:38<00:06, 43.7MB/s]


model.safetensors:  77%|███████▋  | 967M/1.26G [00:38<00:08, 35.4MB/s]


model.safetensors:  77%|███████▋  | 976M/1.26G [00:38<00:09, 30.7MB/s]


model.safetensors:  79%|███████▊  | 991M/1.26G [00:38<00:06, 44.7MB/s]


model.safetensors:  79%|███████▉  | 999M/1.26G [00:39<00:06, 40.4MB/s]


model.safetensors:  80%|███████▉  | 1.01G/1.26G [00:39<00:07, 33.6MB/s]


model.safetensors:  81%|████████  | 1.02G/1.26G [00:39<00:04, 48.3MB/s]


model.safetensors:  82%|████████▏ | 1.03G/1.26G [00:40<00:06, 34.8MB/s]


model.safetensors:  82%|████████▏ | 1.04G/1.26G [00:40<00:06, 32.2MB/s]


model.safetensors:  84%|████████▎ | 1.06G/1.26G [00:40<00:04, 46.6MB/s]


model.safetensors:  84%|████████▍ | 1.06G/1.26G [00:40<00:05, 37.0MB/s]


model.safetensors:  85%|████████▍ | 1.07G/1.26G [00:41<00:05, 32.3MB/s]


model.safetensors:  86%|████████▌ | 1.09G/1.26G [00:41<00:03, 46.8MB/s]


model.safetensors:  87%|████████▋ | 1.10G/1.26G [00:41<00:04, 33.6MB/s]


model.safetensors:  87%|████████▋ | 1.10G/1.26G [00:42<00:04, 32.0MB/s]


model.safetensors:  89%|████████▊ | 1.12G/1.26G [00:42<00:03, 46.5MB/s]


model.safetensors:  89%|████████▉ | 1.13G/1.26G [00:42<00:04, 32.9MB/s]


model.safetensors:  90%|████████▉ | 1.13G/1.26G [00:43<00:05, 24.0MB/s]


model.safetensors:  90%|█████████ | 1.14G/1.26G [00:43<00:06, 18.3MB/s]


model.safetensors:  90%|█████████ | 1.14G/1.26G [00:43<00:06, 19.3MB/s]


model.safetensors:  91%|█████████ | 1.14G/1.26G [00:43<00:05, 20.1MB/s]


model.safetensors:  91%|█████████ | 1.15G/1.26G [00:44<00:07, 15.8MB/s]


model.safetensors:  91%|█████████ | 1.15G/1.26G [00:44<00:06, 16.4MB/s]


model.safetensors:  91%|█████████▏| 1.15G/1.26G [00:45<00:14, 7.59MB/s]


model.safetensors:  92%|█████████▏| 1.17G/1.26G [00:45<00:04, 19.8MB/s]


model.safetensors:  93%|█████████▎| 1.17G/1.26G [00:46<00:06, 13.9MB/s]


model.safetensors:  94%|█████████▍| 1.18G/1.26G [00:46<00:04, 18.2MB/s]


model.safetensors:  95%|█████████▌| 1.20G/1.26G [00:46<00:02, 30.2MB/s]


model.safetensors:  96%|█████████▌| 1.21G/1.26G [00:47<00:01, 28.5MB/s]


model.safetensors:  96%|█████████▋| 1.22G/1.26G [00:47<00:01, 28.9MB/s]


model.safetensors:  98%|█████████▊| 1.23G/1.26G [00:47<00:00, 43.1MB/s]


model.safetensors:  98%|█████████▊| 1.24G/1.26G [00:48<00:00, 29.2MB/s]


model.safetensors:  99%|█████████▉| 1.25G/1.26G [00:48<00:00, 23.1MB/s]
model.safetensors: 100%|██████████| 1.26G/1.26G [00:49<00:00, 25.8MB/s]


Upload 3 LFS files:  67%|██████▋   | 2/3 [00:49<00:28, 28.81s/it]
Upload 3 LFS files: 100%|██████████| 3/3 [00:49<00:00, 16.42s/it]