End of training

README.md

@@ -9,18 +9,18 @@ model-index:
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/priyanshipal/huggingface/runs/1kodfy70)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/priyanshipal/huggingface/runs/64250v6u)
 # s300_shuff100
 
 This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
 - eval_loss: nan
-- eval_model_preparation_time: 0.0046
+- eval_model_preparation_time: 0.0045
 - eval_cer: 1.0
 - eval_wer: 1.0
-- eval_runtime: 39.8895
-- eval_samples_per_second: 14.34
-- eval_steps_per_second: 0.902
+- eval_runtime: 30.9217
+- eval_samples_per_second: 18.498
+- eval_steps_per_second: 1.164
 - step: 0
 
 ## Model description

all_results.json

@@ -2,11 +2,11 @@
     "epoch": 1.6,
     "eval_cer": 1.0,
     "eval_loss": NaN,
-    "eval_model_preparation_time": 0.0046,
-    "eval_runtime": 39.8895,
+    "eval_model_preparation_time": 0.0045,
+    "eval_runtime": 30.9217,
     "eval_samples": 572,
-    "eval_samples_per_second": 14.34,
-    "eval_steps_per_second": 0.902,
+    "eval_samples_per_second": 18.498,
+    "eval_steps_per_second": 1.164,
     "eval_wer": 1.0,
     "total_flos": 6.212261523683712e+18,
     "train_loss": 3.21392811447382,

eval_results.json

@@ -1,10 +1,10 @@
 {
     "eval_cer": 1.0,
     "eval_loss": NaN,
-    "eval_model_preparation_time": 0.0046,
-    "eval_runtime": 39.8895,
+    "eval_model_preparation_time": 0.0045,
+    "eval_runtime": 30.9217,
     "eval_samples": 572,
-    "eval_samples_per_second": 14.34,
-    "eval_steps_per_second": 0.902,
+    "eval_samples_per_second": 18.498,
+    "eval_steps_per_second": 1.164,
     "eval_wer": 1.0
 }

evalonlyhindi_indicwav2vec_MUCS_warmup500_s300shuff100_2142383.out

@@ -152,3 +152,43 @@ last prediction string
   eval_steps_per_second       =      0.902
   eval_wer                    =        1.0
 
+wandb: - 0.005 MB of 0.005 MB uploaded
+wandb: Run history:
+wandb:                    eval/cer ▁
+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_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 1.0
+wandb:                   eval/loss nan
+wandb: eval/model_preparation_time 0.0046
+wandb:                eval/runtime 39.8895
+wandb:     eval/samples_per_second 14.34
+wandb:       eval/steps_per_second 0.902
+wandb:                    eval/wer 1.0
+wandb:                    eval_cer 1.0
+wandb:                   eval_loss nan
+wandb: eval_model_preparation_time 0.0046
+wandb:                eval_runtime 39.8895
+wandb:                eval_samples 572
+wandb:     eval_samples_per_second 14.34
+wandb:       eval_steps_per_second 0.902
+wandb:                    eval_wer 1.0
+wandb:           train/global_step 0
+wandb: 
+wandb: 🚀 View run eval_pd2000_s300_shuff100_hindi at: https://wandb.ai/priyanshipal/huggingface/runs/1kodfy70
+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-20240822_150154-1kodfy70/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.

evalonlyhindi_indicwav2vec_MUCS_warmup500_s300shuff100_2142409.out

@@ -0,0 +1,110 @@
+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_151437-2b363w6i
+wandb: Run `wandb offline` to turn off syncing.
+wandb: Syncing run eval_pd2000_s300_shuff100_hindi
+wandb: ⭐️ View project at https://wandb.ai/priyanshipal/huggingface
+wandb: 🚀 View run at https://wandb.ai/priyanshipal/huggingface/runs/2b363w6i
+/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(
+/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=0.0, 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=0.0, 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=0.0, 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=0.0, 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)
+)
+
+Traceback (most recent call last):
+  File "/scratch/elec/puhe/p/palp3/MUCS/eval_script_indicwav2vec.py", line 790, in <module>
+    main()
+  File "/scratch/elec/puhe/p/palp3/MUCS/eval_script_indicwav2vec.py", line 637, in main
+    print("check the eval set length", len(vectorized_datasets["eval"]["audio_id"]))
+                                           ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/datasets/arrow_dataset.py", line 2866, in __getitem__
+    return self._getitem(key)
+           ^^^^^^^^^^^^^^^^^^
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/datasets/arrow_dataset.py", line 2850, in _getitem
+    pa_subtable = query_table(self._data, key, indices=self._indices)
+                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/datasets/formatting/formatting.py", line 584, in query_table
+    _check_valid_column_key(key, table.column_names)
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/datasets/formatting/formatting.py", line 521, in _check_valid_column_key
+    raise KeyError(f"Column {key} not in the dataset. Current columns in the dataset: {columns}")
+KeyError: "Column audio_id not in the dataset. Current columns in the dataset: ['input_values', 'input_length', 'labels']"
+wandb: - 0.011 MB of 0.011 MB uploaded
+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-20240822_151437-2b363w6i/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.

evalonlyhindi_indicwav2vec_MUCS_warmup500_s300shuff100_2142421.out

@@ -0,0 +1,175 @@
+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_151726-alv0f5i7
+wandb: Run `wandb offline` to turn off syncing.
+wandb: Syncing run eval_pd2000_s300_shuff100_hindi
+wandb: ⭐️ View project at https://wandb.ai/priyanshipal/huggingface
+wandb: 🚀 View run at https://wandb.ai/priyanshipal/huggingface/runs/alv0f5i7
+/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(
+/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(
+/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=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=0.0, 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=0.0, 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=0.0, 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=0.0, 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
+08/22/2024 15:17:37 - 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<00:31,  1.07it/s]
  8%|▊         | 3/36 [00:03<00:42,  1.28s/it]
 11%|█         | 4/36 [00:05<00:52,  1.65s/it]
 14%|█▍        | 5/36 [00:07<00:53,  1.72s/it]
 17%|█▋        | 6/36 [00:09<00:51,  1.72s/it]
 19%|█▉        | 7/36 [00:10<00:42,  1.48s/it]
 22%|██▏       | 8/36 [00:11<00:33,  1.20s/it]
 25%|██▌       | 9/36 [00:11<00:28,  1.06s/it]
 28%|██▊       | 10/36 [00:12<00:27,  1.04s/it]
 31%|███       | 11/36 [00:13<00:26,  1.06s/it]
 33%|███▎      | 12/36 [00:14<00:25,  1.05s/it]
 36%|███▌      | 13/36 [00:15<00:23,  1.00s/it]
 39%|███▉      | 14/36 [00:16<00:19,  1.15it/s]
 42%|████▏     | 15/36 [00:16<00:16,  1.28it/s]
 44%|████▍     | 16/36 [00:17<00:14,  1.36it/s]
 47%|████▋     | 17/36 [00:18<00:13,  1.41it/s]
 50%|█████     | 18/36 [00:19<00:13,  1.35it/s]
 53%|█████▎    | 19/36 [00:19<00:13,  1.30it/s]
 56%|█████▌    | 20/36 [00:20<00:11,  1.35it/s]
 58%|█████▊    | 21/36 [00:21<00:10,  1.45it/s]
 61%|██████    | 22/36 [00:21<00:09,  1.43it/s]
 64%|██████▍   | 23/36 [00:22<00:09,  1.40it/s]
 67%|██████▋   | 24/36 [00:23<00:08,  1.38it/s]
 69%|██████▉   | 25/36 [00:24<00:08,  1.31it/s]
 72%|███████▏  | 26/36 [00:24<00:07,  1.35it/s]
 75%|███████▌  | 27/36 [00:25<00:06,  1.45it/s]
 78%|███████▊  | 28/36 [00:26<00:06,  1.18it/s]
 81%|████████  | 29/36 [00:28<00:08,  1.22s/it]
 83%|████████▎ | 30/36 [00:30<00:08,  1.37s/it]Traceback (most recent call last):
+  File "/scratch/elec/puhe/p/palp3/MUCS/eval_script_indicwav2vec.py", line 790, in <module>
+    main()
+  File "/scratch/elec/puhe/p/palp3/MUCS/eval_script_indicwav2vec.py", line 759, in main
+    metrics = trainer.evaluate()
+              ^^^^^^^^^^^^^^^^^^
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/transformers/trainer.py", line 3666, in evaluate
+    output = eval_loop(
+             ^^^^^^^^^^
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/transformers/trainer.py", line 3857, in evaluation_loop
+    losses, logits, labels = self.prediction_step(model, inputs, prediction_loss_only, ignore_keys=ignore_keys)
+                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/transformers/trainer.py", line 4075, in prediction_step
+    loss, outputs = self.compute_loss(model, inputs, return_outputs=True)
+                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/transformers/trainer.py", line 3363, in compute_loss
+    outputs = model(**inputs)
+              ^^^^^^^^^^^^^^^
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
+    return self._call_impl(*args, **kwargs)
+           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
+    return forward_call(*args, **kwargs)
+           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/accelerate/utils/operations.py", line 819, in forward
+    return model_forward(*args, **kwargs)
+           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/accelerate/utils/operations.py", line 807, in __call__
+    return convert_to_fp32(self.model_forward(*args, **kwargs))
+                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/torch/amp/autocast_mode.py", line 43, in decorate_autocast
+    return func(*args, **kwargs)
+           ^^^^^^^^^^^^^^^^^^^^^
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/transformers/models/wav2vec2/modeling_wav2vec2.py", line 2228, in forward
+    outputs = self.wav2vec2(
+              ^^^^^^^^^^^^^^
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
+    return self._call_impl(*args, **kwargs)
+           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
+    return forward_call(*args, **kwargs)
+           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/transformers/models/wav2vec2/modeling_wav2vec2.py", line 1809, in forward
+    extract_features = self.feature_extractor(input_values)
+                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
+    return self._call_impl(*args, **kwargs)
+           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
+    return forward_call(*args, **kwargs)
+           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/transformers/models/wav2vec2/modeling_wav2vec2.py", line 463, in forward
+    hidden_states = conv_layer(hidden_states)
+                    ^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
+    return self._call_impl(*args, **kwargs)
+           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
+    return forward_call(*args, **kwargs)
+           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/transformers/models/wav2vec2/modeling_wav2vec2.py", line 335, in forward
+    hidden_states = self.layer_norm(hidden_states)
+                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
+    return self._call_impl(*args, **kwargs)
+           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
+    return forward_call(*args, **kwargs)
+           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/torch/nn/modules/normalization.py", line 202, in forward
+    return F.layer_norm(
+           ^^^^^^^^^^^^^
+  File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/torch/nn/functional.py", line 2576, in layer_norm
+    return torch.layer_norm(input, normalized_shape, weight, bias, eps, torch.backends.cudnn.enabled)
+           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 4.00 GiB. GPU 0 has a total capacity of 15.77 GiB of which 1.55 GiB is free. Including non-PyTorch memory, this process has 14.21 GiB memory in use. Of the allocated memory 11.68 GiB is allocated by PyTorch, and 2.17 GiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation.  See documentation for Memory Management  (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
+wandb: - 0.011 MB of 0.011 MB uploaded
+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-20240822_151726-alv0f5i7/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.

evalonlyhindi_indicwav2vec_MUCS_warmup500_s300shuff100_2142429.out

@@ -0,0 +1,155 @@
+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_152047-64250v6u
+wandb: Run `wandb offline` to turn off syncing.
+wandb: Syncing run eval_pd2000_s300_shuff100_hindi
+wandb: ⭐️ View project at https://wandb.ai/priyanshipal/huggingface
+wandb: 🚀 View run at https://wandb.ai/priyanshipal/huggingface/runs/64250v6u
+/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(
+/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(
+/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=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=0.0, 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=0.0, 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=0.0, 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=0.0, 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
+08/22/2024 15:20:57 - 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<00:23,  1.44it/s]
  8%|▊         | 3/36 [00:02<00:31,  1.05it/s]
 11%|█         | 4/36 [00:04<00:40,  1.26s/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,  1.19s/it]
 22%|██▏       | 8/36 [00:08<00:26,  1.05it/s]
 25%|██▌       | 9/36 [00:09<00:22,  1.21it/s]
 28%|██▊       | 10/36 [00:09<00:20,  1.26it/s]
 31%|███       | 11/36 [00:10<00:20,  1.22it/s]
 33%|███▎      | 12/36 [00:11<00:19,  1.23it/s]
 36%|███▌      | 13/36 [00:12<00:17,  1.35it/s]
 39%|███▉      | 14/36 [00:12<00:14,  1.53it/s]
 42%|████▏     | 15/36 [00:13<00:12,  1.73it/s]
 44%|████▍     | 16/36 [00:13<00:10,  1.87it/s]
 47%|████▋     | 17/36 [00:13<00:09,  1.96it/s]
 50%|█████     | 18/36 [00:14<00:09,  1.89it/s]
 53%|█████▎    | 19/36 [00:15<00:09,  1.80it/s]
 56%|█████▌    | 20/36 [00:15<00:08,  1.85it/s]
 58%|█████▊    | 21/36 [00:16<00:07,  2.00it/s]
 61%|██████    | 22/36 [00:16<00:07,  1.99it/s]
 64%|██████▍   | 23/36 [00:17<00:06,  1.96it/s]
 67%|██████▋   | 24/36 [00:17<00:06,  1.94it/s]
 69%|██████▉   | 25/36 [00:18<00:05,  1.85it/s]
 72%|███████▏  | 26/36 [00:18<00:05,  1.87it/s]
 75%|███████▌  | 27/36 [00:19<00:04,  1.97it/s]
 78%|███████▊  | 28/36 [00:20<00:05,  1.59it/s]
 81%|████████  | 29/36 [00:21<00:06,  1.08it/s]
 83%|████████▎ | 30/36 [00:23<00:06,  1.08s/it]
 86%|████████▌ | 31/36 [00:25<00:06,  1.35s/it]
 89%|████████▉ | 32/36 [00:25<00:04,  1.12s/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]
+Printing predictions for a few samples:
+Sample 1:
+  Reference: हम उनका उपयोग ऐसे ही कर सकते हैं या आवश्यकता अनुसार कुछ बदलाव करके उपयोग कर सकते हैं
+######
+
+
+  Prediction: 
+
+
+
+Sample 2:
+  Reference: अतः शीर्षक इस तरह से जोड़ सकते हैं
+######
+
+
+  Prediction: 
+
+
+
+Sample 3:
+  Reference: प्रेसेंटेशन के अंत में आपने स्लाइड की एक कॉपी बना ली है
+######
+
+
+  Prediction: 
+
+
+
+Sample 4:
+  Reference: चलिए अब फोंट्स और फोंट्स को फॉर्मेट करने के कुछ तरीके देखते हैं
+######
+
+
+  Prediction: 
+
+
+
+Sample 5:
+  Reference: यह एक डायलॉग बॉक्स खोलेगा जिसमें हम अपनी आवश्यकतानुसार फॉन्ट स्टाइल और साइज़ सेट कर सकते हैं
+######
+
+
+  Prediction: 
+
+
+
+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 
+***** eval metrics *****
+  eval_cer                    =        1.0
+  eval_loss                   =        nan
+  eval_model_preparation_time =     0.0045
+  eval_runtime                = 0:00:30.92
+  eval_samples                =        572
+  eval_samples_per_second     =     18.498
+  eval_steps_per_second       =      1.164
+  eval_wer                    =        1.0
+

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ac994ec93d9297038ccd8f0941bd5189ab98d5a22407edafc2b896159805ce1
+oid sha256:17f546c82c9065a6469d28f2bf552ce06c87b07db0f04de15435295aa0a8a04d
 size 5432