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/g7aicg5h)
+[<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/bhazmy67)
 # eval_cache
 
 This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 4.3269
-- eval_model_preparation_time: 0.0045
-- eval_cer: 0.6025
-- eval_wer: 0.8793
-- eval_runtime: 36.0147
-- eval_samples_per_second: 15.882
-- eval_steps_per_second: 1.0
+- eval_loss: 2.2164
+- eval_model_preparation_time: 0.0046
+- eval_cer: 0.4677
+- eval_wer: 0.5669
+- eval_runtime: 40.5673
+- eval_samples_per_second: 14.1
+- eval_steps_per_second: 0.887
 - step: 0
 
 ## Model description

all_results.json

@@ -1,10 +1,10 @@
 {
-    "eval_cer": 0.6025458851391355,
-    "eval_loss": 4.326878547668457,
-    "eval_model_preparation_time": 0.0045,
-    "eval_runtime": 36.0147,
+    "eval_cer": 0.4676731793960924,
+    "eval_loss": 2.216402530670166,
+    "eval_model_preparation_time": 0.0046,
+    "eval_runtime": 40.5673,
     "eval_samples": 572,
-    "eval_samples_per_second": 15.882,
-    "eval_steps_per_second": 1.0,
-    "eval_wer": 0.8793330408073716
+    "eval_samples_per_second": 14.1,
+    "eval_steps_per_second": 0.887,
+    "eval_wer": 0.5669153137340939
 }

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/scratch/elec/puhe/p/palp3/MUCS/indicwav2vec_outputs/pd_warmup_2000/s400_shuff42",
+  "_name_or_path": "/scratch/elec/puhe/p/palp3/MUCS/indicwav2vec_outputs/pd_warmup_2000/s300_shuff500",
   "activation_dropout": 0.0,
   "adapter_attn_dim": null,
   "adapter_kernel_size": 3,

eval_results.json

@@ -1,10 +1,10 @@
 {
-    "eval_cer": 0.6025458851391355,
-    "eval_loss": 4.326878547668457,
-    "eval_model_preparation_time": 0.0045,
-    "eval_runtime": 36.0147,
+    "eval_cer": 0.4676731793960924,
+    "eval_loss": 2.216402530670166,
+    "eval_model_preparation_time": 0.0046,
+    "eval_runtime": 40.5673,
     "eval_samples": 572,
-    "eval_samples_per_second": 15.882,
-    "eval_steps_per_second": 1.0,
-    "eval_wer": 0.8793330408073716
+    "eval_samples_per_second": 14.1,
+    "eval_steps_per_second": 0.887,
+    "eval_wer": 0.5669153137340939
 }

evalonlyhindi_indicwav2vec_MUCS_warmup2000_s300shuff500_2143808.out

@@ -0,0 +1,162 @@
+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_161651-bhazmy67
+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/bhazmy67
+/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=0.3, 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
+08/22/2024 16:17:04 - 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<00:28,  1.20it/s]
  8%|▊         | 3/36 [00:03<00:34,  1.04s/it]
 11%|█         | 4/36 [00:04<00:42,  1.32s/it]
 14%|█▍        | 5/36 [00:06<00:43,  1.40s/it]
 17%|█▋        | 6/36 [00:07<00:41,  1.39s/it]
 19%|█▉        | 7/36 [00:08<00:35,  1.23s/it]
 22%|██▏       | 8/36 [00:09<00:27,  1.02it/s]
 25%|██▌       | 9/36 [00:09<00:22,  1.19it/s]
 28%|██▊       | 10/36 [00:10<00:21,  1.24it/s]
 31%|███       | 11/36 [00:11<00:20,  1.21it/s]
 33%|███▎      | 12/36 [00:11<00:19,  1.23it/s]
 36%|███▌      | 13/36 [00:12<00:17,  1.29it/s]
 39%|███▉      | 14/36 [00:13<00:14,  1.48it/s]
 42%|████▏     | 15/36 [00:13<00:12,  1.67it/s]
 44%|████▍     | 16/36 [00:13<00:10,  1.82it/s]
 47%|████▋     | 17/36 [00:14<00:09,  1.92it/s]
 50%|█████     | 18/36 [00:14<00:09,  1.85it/s]
 53%|█████▎    | 19/36 [00:15<00:09,  1.77it/s]
 56%|█████▌    | 20/36 [00:16<00:08,  1.83it/s]
 58%|█████▊    | 21/36 [00:16<00:07,  1.97it/s]
 61%|██████    | 22/36 [00:17<00:07,  1.97it/s]
 64%|██████▍   | 23/36 [00:17<00:06,  1.93it/s]
 67%|██████▋   | 24/36 [00:18<00:06,  1.91it/s]
 69%|██████▉   | 25/36 [00:18<00:06,  1.82it/s]
 72%|███████▏  | 26/36 [00:19<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 [00:22<00:06,  1.08it/s]
 83%|████████▎ | 30/36 [00:23<00:06,  1.08s/it]
 86%|████████▌ | 31/36 [00:25<00:06,  1.34s/it]
 89%|████████▉ | 32/36 [00:26<00:04,  1.12s/it]
 92%|█████████▏| 33/36 [00:26<00:02,  1.04it/s]
 94%|█████████▍| 34/36 [00:27<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: mpl lauts मजद हहम उनका उपयोग ैसे ही कर सकते हं
+
+
+
+Sample 2:
+  Reference: अतः शीर्षक इस तरह से जोड़ सकते हैं
+######
+
+
+  Prediction: अ ीर
+
+
+
+Sample 3:
+  Reference: प्रेसेंटेशन के अंत में आपने स्लाइड की एक कॉपी बना ली है
+######
+
+
+  Prediction: prntation के अंत में पन
+
+
+
+Sample 4:
+  Reference: चलिए अब फोंट्स और फोंट्स को फॉर्मेट करने के कुछ तरीके देखते हैं
+######
+
+
+  Prediction: क cop ब चलिए fonts और fonts को format करने के कुछ तरीके ंं
+
+
+
+Sample 5:
+  Reference: यह एक डायलॉग बॉक्स खोलेगा जिसमें हम अपनी आवश्यकतानुसार फॉन्ट स्टाइल और साइज़ सेट कर सकते हैं
+######
+
+
+  Prediction: द कंयह एक dialog boxस खोलेगा जिसमें हम अपनी व्यक
+
+
+
+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 metrics *****
+  eval_cer                    =     0.4677
+  eval_loss                   =     2.2164
+  eval_model_preparation_time =     0.0046
+  eval_runtime                = 0:00:40.56
+  eval_samples                =        572
+  eval_samples_per_second     =       14.1
+  eval_steps_per_second       =      0.887
+  eval_wer                    =     0.5669
+
+
+
+
+
+
+

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1652bc6136498220e8e10b3cacbaabad0bb1a38be329d9722f49a67f271753b
+oid sha256:7eb487bdd3e20589cbadfa9613598ab0ecfa0a02e0d5db447642ffc85a0bb960
 size 1262426580

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc40ea5915cba28a074a9b6adf1b3f7b7943525a87ed03413e8be115e383ad12
+oid sha256:112f6e6b2734038b6cbd8a832070a364a365778c258759d59c07634dc399dde4
 size 5432