diff --git a/README.md b/README.md
index 5986a91d14c723326a6508e8902e1c4662e5a44e..228c3bf9742ddcc9c08523725ff0a45a1d63ce74 100644
--- a/README.md
+++ b/README.md
@@ -1,8 +1,6 @@
---
tags:
- generated_from_trainer
-metrics:
-- wer
model-index:
- name: s300_shuff100
results: []
@@ -11,14 +9,19 @@ model-index:
-[
](https://wandb.ai/priyanshipal/huggingface/runs/0evkescz)
+[](https://wandb.ai/priyanshipal/huggingface/runs/jw39kyll)
# s300_shuff100
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
-- Loss: 1.5066
-- Cer: 0.3096
-- Wer: 0.4357
+- eval_loss: nan
+- eval_model_preparation_time: 0.0044
+- eval_cer: 1.0
+- eval_wer: 1.0
+- eval_runtime: 40.6214
+- eval_samples_per_second: 14.081
+- eval_steps_per_second: 0.886
+- step: 0
## Model description
@@ -49,13 +52,6 @@ The following hyperparameters were used during training:
- training_steps: 1000
- mixed_precision_training: Native AMP
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Cer | Wer |
-|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
-| 0.9856 | 1.6 | 1000 | 1.5066 | 0.3096 | 0.4357 |
-
-
### Framework versions
- Transformers 4.43.1
diff --git a/all_results.json b/all_results.json
index 23927b69e52af44f9a347c755e7017fb54b894a1..289965a605f8f829268bf1df3d899d89f3d167ee 100644
--- a/all_results.json
+++ b/all_results.json
@@ -1,12 +1,13 @@
{
"epoch": 1.6,
- "eval_cer": 0.30955352407101183,
- "eval_loss": 1.5066314935684204,
- "eval_runtime": 159.3193,
- "eval_samples": 3136,
- "eval_samples_per_second": 19.684,
- "eval_steps_per_second": 1.23,
- "eval_wer": 0.43571675485946765,
+ "eval_cer": 1.0,
+ "eval_loss": NaN,
+ "eval_model_preparation_time": 0.0044,
+ "eval_runtime": 40.6214,
+ "eval_samples": 572,
+ "eval_samples_per_second": 14.081,
+ "eval_steps_per_second": 0.886,
+ "eval_wer": 1.0,
"total_flos": 6.212261523683712e+18,
"train_loss": 3.21392811447382,
"train_runtime": 2133.1271,
diff --git a/config.json b/config.json
index a326971aec3b2ea9d498e53e86e3bc6497c54e07..068105693776ffe4c295de7f2459c38e57f5c298 100644
--- a/config.json
+++ b/config.json
@@ -9,7 +9,7 @@
"architectures": [
"Wav2Vec2ForCTC"
],
- "attention_dropout": 0.3,
+ "attention_dropout": 0.0,
"bos_token_id": 1,
"classifier_proj_size": 256,
"codevector_dim": 256,
@@ -50,11 +50,11 @@
"feat_extract_activation": "gelu",
"feat_extract_dropout": 0.0,
"feat_extract_norm": "layer",
- "feat_proj_dropout": 0.3,
+ "feat_proj_dropout": 0.0,
"feat_quantizer_dropout": 0.0,
"final_dropout": 0.0,
"hidden_act": "gelu",
- "hidden_dropout": 0.2,
+ "hidden_dropout": 0.0,
"hidden_dropout_prob": 0.1,
"hidden_size": 1024,
"initializer_range": 0.02,
diff --git a/eval_results.json b/eval_results.json
index 57063ea1c28a7a3311a9690f61168229a9d13a07..c2dcdc7fe060a035972d39716034503e9d8d54ad 100644
--- a/eval_results.json
+++ b/eval_results.json
@@ -1,10 +1,10 @@
{
- "epoch": 1.6,
- "eval_cer": 0.30955352407101183,
- "eval_loss": 1.5066314935684204,
- "eval_runtime": 159.3193,
- "eval_samples": 3136,
- "eval_samples_per_second": 19.684,
- "eval_steps_per_second": 1.23,
- "eval_wer": 0.43571675485946765
+ "eval_cer": 1.0,
+ "eval_loss": NaN,
+ "eval_model_preparation_time": 0.0044,
+ "eval_runtime": 40.6214,
+ "eval_samples": 572,
+ "eval_samples_per_second": 14.081,
+ "eval_steps_per_second": 0.886,
+ "eval_wer": 1.0
}
\ No newline at end of file
diff --git a/evalonly_indicwav2vec_MUCS_warmup500_s300shuff100_2142198.out b/evalonly_indicwav2vec_MUCS_warmup500_s300shuff100_2142198.out
new file mode 100644
index 0000000000000000000000000000000000000000..4ae17926dbd8924c63e2da9e70d7d04b054ca1a3
--- /dev/null
+++ b/evalonly_indicwav2vec_MUCS_warmup500_s300shuff100_2142198.out
@@ -0,0 +1,44 @@
+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_143902-r64ufk4q
+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/r64ufk4q
+/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: 0 examples [00:00, ? examples/s]
+Traceback (most recent call last):
+ File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/datasets/builder.py", line 1997, in _prepare_split_single
+ for _, table in generator:
+ File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/datasets/packaged_modules/json/json.py", line 98, in _generate_tables
+ dataset = dataset[self.config.field]
+ ~~~~~~~^^^^^^^^^^^^^^^^^^^
+KeyError: 'test'
+
+The above exception was the direct cause of the following exception:
+
+Traceback (most recent call last):
+ File "/scratch/elec/puhe/p/palp3/MUCS/eval_script_indicwav2vec.py", line 790, in
+ main()
+ File "/scratch/elec/puhe/p/palp3/MUCS/eval_script_indicwav2vec.py", line 427, in main
+ raw_datasets["eval"] = load_dataset(
+ ^^^^^^^^^^^^^
+ File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/datasets/load.py", line 2616, in load_dataset
+ builder_instance.download_and_prepare(
+ File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/datasets/builder.py", line 1029, in download_and_prepare
+ self._download_and_prepare(
+ File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/datasets/builder.py", line 1124, in _download_and_prepare
+ self._prepare_split(split_generator, **prepare_split_kwargs)
+ File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/datasets/builder.py", line 1884, in _prepare_split
+ for job_id, done, content in self._prepare_split_single(
+ File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/datasets/builder.py", line 2040, in _prepare_split_single
+ raise DatasetGenerationError("An error occurred while generating the dataset") from e
+datasets.exceptions.DatasetGenerationError: An error occurred while generating the dataset
+wandb: - 0.005 MB of 0.005 MB uploaded
wandb: \ 0.005 MB of 0.018 MB uploaded
wandb: | 0.018 MB of 0.018 MB uploaded
wandb: 🚀 View run eval_pd2000_s300_shuff100_hindi at: https://wandb.ai/priyanshipal/huggingface/runs/r64ufk4q
+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_143902-r64ufk4q/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.
diff --git a/evalonlyhindi_indicwav2vec_MUCS_warmup500_s300shuff100_2142336.out b/evalonlyhindi_indicwav2vec_MUCS_warmup500_s300shuff100_2142336.out
new file mode 100644
index 0000000000000000000000000000000000000000..7600d1552f2962fd5bad89be88d377fb6ab86dd0
--- /dev/null
+++ b/evalonlyhindi_indicwav2vec_MUCS_warmup500_s300shuff100_2142336.out
@@ -0,0 +1,463 @@
+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_145052-jw39kyll
+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/jw39kyll
+/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: 572 examples [00:00, 1536.67 examples/s]
Generating train split: 572 examples [00:00, 1460.76 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/configuration_utils.py:364: UserWarning: Passing `gradient_checkpointing` to a config initialization is deprecated and will be removed in v5 Transformers. Using `model.gradient_checkpointing_enable()` instead, or if you are using the `Trainer` API, pass `gradient_checkpointing=True` in your `TrainingArguments`.
+ 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': '', 'eos_token': '', '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("", 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=0.0, 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)
+)
+
preprocess datasets: 0%| | 0/572 [00:00
+ main()
+ File "/scratch/elec/puhe/p/palp3/MUCS/eval_script_indicwav2vec.py", line 427, in main
+ raw_datasets["eval"] = load_dataset(
+ ^^^^^^^^^^^^^
+ File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/datasets/load.py", line 2616, in load_dataset
+ builder_instance.download_and_prepare(
+ File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/datasets/builder.py", line 1029, in download_and_prepare
+ self._download_and_prepare(
+ File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/datasets/builder.py", line 1124, in _download_and_prepare
+ self._prepare_split(split_generator, **prepare_split_kwargs)
+ File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/datasets/builder.py", line 1884, in _prepare_split
+ for job_id, done, content in self._prepare_split_single(
+ File "/scratch/work/palp3/myenv/lib/python3.11/site-packages/datasets/builder.py", line 2040, in _prepare_split_single
+ raise DatasetGenerationError("An error occurred while generating the dataset") from e
+datasets.exceptions.DatasetGenerationError: An error occurred while generating the dataset
+wandb: - 0.005 MB of 0.005 MB uploaded
wandb: \ 0.005 MB of 0.018 MB uploaded
wandb: | 0.018 MB of 0.018 MB uploaded
wandb: 🚀 View run eval_pd2000_s300_shuff100_hindi at: https://wandb.ai/priyanshipal/huggingface/runs/be92xk0e
+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_144249-be92xk0e/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.
diff --git a/indicwav2vec_MUCS_warmup500_s300shuff100_2130813.out b/indicwav2vec_MUCS_warmup500_s300shuff100_2130813.out
index 773e8724dd9551f5e990cf493bcace1220608808..861f2006c8c841bf39e93657aa7bd636812cfdeb 100644
--- a/indicwav2vec_MUCS_warmup500_s300shuff100_2130813.out
+++ b/indicwav2vec_MUCS_warmup500_s300shuff100_2130813.out
@@ -1368,3 +1368,99 @@ last prediction string लता द्वारा अनुवादित ह
/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%| | 0/196 [00:00