transliteratedevalonlyhindi_indicwav2vec_MUCS_warmup500_s300shuff100_3709578.out

wandb: Currently logged in as: priyanshi-pal (priyanshipal). Use `wandb login --relogin` to force relogin
wandb: wandb version 0.18.3 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-20241014_235124-o0k52lvl
wandb: Run `wandb offline` to turn off syncing.
wandb: Syncing run transliterated_wer_glamorous_tree_37
wandb: ⭐️ View project at https://wandb.ai/priyanshipal/huggingface
wandb: 🚀 View run at https://wandb.ai/priyanshipal/huggingface/runs/o0k52lvl
/scratch/work/palp3/myenv/lib/python3.11/site-packages/transformers/training_args.py:1545: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of 🤗 Transformers. Use `eval_strategy` instead
  warnings.warn(
/scratch/work/palp3/myenv/lib/python3.11/site-packages/transformers/models/auto/configuration_auto.py:991: 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:331: 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/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
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=False),  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)
)
check the eval set length 572
10/14/2024 23:51:37 - 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%|          | 0/36 [00:00<?, ?it/s]
  6%|▌         | 2/36 [00:01<00:26,  1.28it/s]
  8%|▊         | 3/36 [00:02<00:33,  1.00s/it]
 11%|█         | 4/36 [00:04<00:40,  1.28s/it]
 14%|█▍        | 5/36 [00:06<00:42,  1.36s/it]
 17%|█▋        | 6/36 [00:07<00:40,  1.35s/it]
 19%|█▉        | 7/36 [00:08<00:34,  1.20s/it]
 22%|██▏       | 8/36 [00:08<00:26,  1.04it/s]
 25%|██▌       | 9/36 [00:09<00:22,  1.21it/s]
 28%|██▊       | 10/36 [00:10<00:20,  1.26it/s]
 31%|███       | 11/36 [00:10<00:20,  1.23it/s]
 33%|███▎      | 12/36 [00:11<00:19,  1.24it/s]
 36%|███▌      | 13/36 [00:12<00:17,  1.33it/s]
 39%|███▉      | 14/36 [00:12<00:14,  1.51it/s]
 42%|████▏     | 15/36 [00:13<00:12,  1.71it/s]
 44%|████▍     | 16/36 [00:13<00:10,  1.86it/s]
 47%|████▋     | 17/36 [00:14<00:09,  1.95it/s]
 50%|█████     | 18/36 [00:14<00:09,  1.87it/s]
 53%|█████▎    | 19/36 [00:15<00:09,  1.79it/s]
 56%|█████▌    | 20/36 [00:15<00:08,  1.83it/s]
 58%|█████▊    | 21/36 [00:16<00:07,  1.99it/s]
 61%|██████    | 22/36 [00:16<00:07,  1.98it/s]
 64%|██████▍   | 23/36 [00:17<00:06,  1.93it/s]
 67%|██████▋   | 24/36 [00:17<00:06,  1.92it/s]
 69%|██████▉   | 25/36 [00:18<00:06,  1.83it/s]
 72%|███████▏  | 26/36 [00:18<00:05,  1.85it/s]
 75%|███████▌  | 27/36 [00:19<00:04,  1.95it/s]
 78%|███████▊  | 28/36 [00:20<00:04,  1.62it/s]
 81%|████████  | 29/36 [00:21<00:06,  1.09it/s]
 83%|████████▎ | 30/36 [00:23<00:06,  1.07s/it]
 86%|████████▌ | 31/36 [00:25<00:06,  1.34s/it]
 89%|████████▉ | 32/36 [00:25<00:04,  1.11s/it]
 92%|█████████▏| 33/36 [00:26<00:02,  1.04it/s]
 94%|█████████▍| 34/36 [00:26<00:01,  1.21it/s]
 97%|█████████▋| 35/36 [00:27<00:00,  1.36it/s]
100%|██████████| 36/36 [00:27<00:00,  1.65it/s]
100%|██████████| 36/36 [00:29<00:00,  1.24it/s]
/scratch/work/palp3/myenv/lib/python3.11/site-packages/huggingface_hub/hf_api.py:3889: UserWarning: It seems that you are about to commit a data file (json/default-b60d5edd0f197c71/0.0.0/7483f22a71512872c377524b97484f6d20c275799bb9e7cd8fb3198178d8220a/json-train.arrow) to a model repository. You are sure this is intended? If you are trying to upload a dataset, please set `repo_type='dataset'` or `--repo-type=dataset` in a CLI.
  warnings.warn(
Printing predictions for a few samples:
Sample 1:
  Reference (English): हम उनका उपयोग ऐसे ही कर सकते हैं या आवश्यकता अनुसार कुछ बदलाव करके उपयोग कर सकते हैं
 True Reference: हम उनका उपयोग ऐसे ही कर सकते हैं या आवश्यकता अनुसार कुछ बदलाव करके उपयोग कर सकते हैं
######
  Prediction (English): हम उनका उपयोग ऐसे ही कर सकते हैं
 True Prediction: हम उनका उपयोग ऐसे ही कर सकते हैं



Sample 2:
  Reference (English): अतः शीर्षक इस तरह से जोड़ सकते हैं
 True Reference: अतः शीर्षक इस तरह से जोड़ सकते हैं
######
  Prediction (English): अतः शीर्ष है
 True Prediction: अतः शीर्ष है



Sample 3:
  Reference (English): n के अंत में आपने e की एक y बना ली है
 True Reference: प्रेसेंटेशन के अंत में आपने स्लाइड की एक कॉपी बना ली है
######
  Prediction (English): presentation के अंत में आपने स ैंैं
 True Prediction: presentation के अंत में आपने स ैंैं



Sample 4:
  Reference (English): चलिए अब s और s को t करने के कुछ तरीके देखते हैं
 True Reference: चलिए अब फोंट्स और फोंट्स को फॉर्मेट करने के कुछ तरीके देखते हैं
######
  Prediction (English): चलिए अब fonts और fonts को format करने के कुछ तरीके देेहं
 True Prediction: चलिए अब fonts और fonts को format करने के कुछ तरीके देेहं



Sample 5:
  Reference (English): यह एक g x खोलेगा जिसमें हम अपनी आवश्यकतानुसार t e और e t कर सकते हैं
 True Reference: यह एक डायलॉग बॉक्स खोलेगा जिसमें हम अपनी आवश्यकतानुसार फॉन्ट स्टाइल और साइज़ सेट कर सकते हैं
######
  Prediction (English): यह एक dialog box खोलेगा जिसमें हम अपनी आवश्यकत हैहै
 True Prediction: यह एक dialog box खोलेगा जिसमें हम अपनी आवश्यकत हैहै



Last Reference string यह t लता द्वारा अनुवादित है t i की ओर से मैं रवि कुमार अब आपसे विदा लेता हूँहमसे जुड़ने के लिए धन्यवाद


Last Prediction string लता द्वारा अनुवादित है i i t मुmबई की ओर से मैं रवि कुमार अब आपसे विदा लेता हूँ हमसे जुड़ने के लिए धन्यवाद
***** eval metrics *****
  eval_cer                    =      0.463
  eval_loss                   =     2.2188
  eval_model_preparation_time =     0.0043
  eval_runtime                = 0:00:39.38
  eval_samples                =        572
  eval_samples_per_second     =     14.524
  eval_steps_per_second       =      0.914
  eval_wer                    =     0.5242

training_args.bin:   0%|          | 0.00/5.50k [00:00<?, ?B/s]
training_args.bin: 100%|██████████| 5.50k/5.50k [00:00<00:00, 10.5kB/s]
wandb: - 0.005 MB of 0.039 MB uploaded
wandb: \ 0.005 MB of 0.039 MB uploaded
wandb: | 0.039 MB of 0.039 MB uploaded
wandb: 
wandb: Run history:
wandb:                    eval/cer ▁
wandb:                   eval/loss ▁
wandb: eval/model_preparation_time ▁
wandb:                eval/runtime ▁
wandb:     eval/samples_per_second ▁
wandb:       eval/steps_per_second ▁
wandb:                    eval/wer ▁
wandb:                    eval_cer ▁
wandb:                   eval_loss ▁
wandb: eval_model_preparation_time ▁
wandb:                eval_runtime ▁
wandb:                eval_samples ▁
wandb:     eval_samples_per_second ▁
wandb:       eval_steps_per_second ▁
wandb:                    eval_wer ▁
wandb:           train/global_step ▁▁
wandb: 
wandb: Run summary:
wandb:                    eval/cer 0.46299
wandb:                   eval/loss 2.21876
wandb: eval/model_preparation_time 0.0043
wandb:                eval/runtime 39.3844
wandb:     eval/samples_per_second 14.524
wandb:       eval/steps_per_second 0.914
wandb:                    eval/wer 0.52421
wandb:                    eval_cer 0.46299
wandb:                   eval_loss 2.21876
wandb: eval_model_preparation_time 0.0043
wandb:                eval_runtime 39.3844
wandb:                eval_samples 572
wandb:     eval_samples_per_second 14.524
wandb:       eval_steps_per_second 0.914
wandb:                    eval_wer 0.52421
wandb:           train/global_step 0
wandb: 
wandb: 🚀 View run transliterated_wer_glamorous_tree_37 at: https://wandb.ai/priyanshipal/huggingface/runs/o0k52lvl
wandb: ⭐️ View project at: https://wandb.ai/priyanshipal/huggingface
wandb: Synced 6 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)
wandb: Find logs at: ./wandb/run-20241014_235124-o0k52lvl/logs
wandb: WARNING The new W&B backend becomes opt-out in version 0.18.0; try it out with `wandb.require("core")`! See https://wandb.me/wandb-core for more information.