shevek's picture
End of training
2ec55e0 verified
|
raw
history blame
3.81 kB
metadata
library_name: transformers
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: my_awesome_speach_model
    results: []

my_awesome_speach_model

This model is a fine-tuned version of facebook/wav2vec2-base on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.8215
  • Accuracy: 0.6154

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 3e-05
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 16
  • optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 40

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 0.8889 6 0.6905 0.6923
0.6936 1.9259 13 0.7083 0.3077
0.6859 2.9630 20 0.7061 0.3846
0.6859 4.0 27 0.7065 0.4615
0.6738 4.8889 33 0.7058 0.5385
0.6487 5.9259 40 0.7190 0.5385
0.6487 6.9630 47 0.6488 0.6154
0.5804 8.0 54 0.6696 0.6154
0.6227 8.8889 60 0.7988 0.3846
0.6227 9.9259 67 0.6253 0.6923
0.6318 10.9630 74 0.6760 0.6154
0.6617 12.0 81 0.9642 0.3077
0.6617 12.8889 87 0.7761 0.5385
0.6052 13.9259 94 0.8490 0.4615
0.5238 14.9630 101 0.7963 0.4615
0.5238 16.0 108 0.7485 0.5385
0.452 16.8889 114 0.7720 0.5385
0.3813 17.9259 121 0.7478 0.6154
0.3813 18.9630 128 0.8406 0.6154
0.4809 20.0 135 0.6624 0.6923
0.3698 20.8889 141 0.7520 0.6154
0.3698 21.9259 148 0.8275 0.5385
0.2959 22.9630 155 0.8472 0.5385
0.3976 24.0 162 1.0899 0.4615
0.3976 24.8889 168 0.8758 0.5385
0.3788 25.9259 175 0.5872 0.7692
0.3511 26.9630 182 0.7996 0.6154
0.3511 28.0 189 0.7726 0.6154
0.2797 28.8889 195 0.7310 0.6923
0.2445 29.9259 202 0.7223 0.6154
0.2445 30.9630 209 0.7139 0.6923
0.2299 32.0 216 0.7540 0.6923
0.2101 32.8889 222 0.7878 0.6154
0.2101 33.9259 229 0.7942 0.6154
0.2043 34.9630 236 0.8193 0.6154
0.1638 35.5556 240 0.8215 0.6154

Framework versions

  • Transformers 4.46.3
  • Pytorch 2.5.1+cu121
  • Datasets 3.2.0
  • Tokenizers 0.20.3