diff --git "a/transliteratedevalonlyhindi_indicwav2vec_MUCS_warmup500_s300shuff100_3711144.out" "b/transliteratedevalonlyhindi_indicwav2vec_MUCS_warmup500_s300shuff100_3711144.out"
new file mode 100644--- /dev/null
+++ "b/transliteratedevalonlyhindi_indicwav2vec_MUCS_warmup500_s300shuff100_3711144.out"
@@ -0,0 +1,15563 @@
+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-20241015_002010-6hswnhgq
+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/6hswnhgq
+/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': '', 'eos_token': '', '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("", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+ 150: AddedToken("", 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
+10/15/2024 00:20:23 - 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