Hugging Face's logo

fydhfzh
/
hubert-classifier-aug-fold-0-old

Audio Classification
Transformers
TensorBoard
Safetensors
hubert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
hubert-classifier-aug-fold-0-old / README.md
fydhfzh's picture
fydhfzh
End of training
c99a0e1 verified
preview code
|
raw
history blame
5.76 kB
metadata
license: apache-2.0
base_model: facebook/hubert-base-ls960
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: hubert-classifier-aug-fold-9
    results: []

hubert-classifier-aug-fold-9

This model is a fine-tuned version of facebook/hubert-base-ls960 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 4.4196
  • Accuracy: 0.0162
  • Precision: 0.0003
  • Recall: 0.0162
  • F1: 0.0005
  • Binary: 0.1388

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: 0.0001
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 128
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 30
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy Precision Recall F1 Binary
No log 0.19 50 4.4284 0.0162 0.0003 0.0162 0.0005 0.1321
No log 0.38 100 4.4249 0.0135 0.0002 0.0135 0.0004 0.1296
No log 0.58 150 4.4280 0.0135 0.0002 0.0135 0.0004 0.1353
No log 0.77 200 4.4229 0.0108 0.0001 0.0108 0.0002 0.1315
No log 0.96 250 4.4254 0.0162 0.0003 0.0162 0.0005 0.1321
4.4398 1.15 300 4.4262 0.0135 0.0002 0.0135 0.0004 0.1334
4.4398 1.34 350 4.4237 0.0162 0.0003 0.0162 0.0005 0.1321
4.4398 1.53 400 4.4237 0.0135 0.0002 0.0135 0.0004 0.1315
4.4398 1.73 450 4.4233 0.0135 0.0002 0.0135 0.0004 0.1315
4.4398 1.92 500 4.4241 0.0135 0.0002 0.0135 0.0004 0.1334
4.4196 2.11 550 4.4240 0.0162 0.0003 0.0162 0.0005 0.1321
4.4196 2.3 600 4.4236 0.0135 0.0002 0.0135 0.0004 0.1213
4.4196 2.49 650 4.4227 0.0162 0.0003 0.0162 0.0005 0.1321
4.4196 2.68 700 4.4235 0.0135 0.0002 0.0135 0.0004 0.1353
4.4196 2.88 750 4.4234 0.0135 0.0002 0.0135 0.0004 0.1334
4.4189 3.07 800 4.4234 0.0135 0.0002 0.0135 0.0004 0.1334
4.4189 3.26 850 4.4240 0.0135 0.0002 0.0135 0.0004 0.1334
4.4189 3.45 900 4.4230 0.0162 0.0003 0.0162 0.0005 0.1321
4.4189 3.64 950 4.4230 0.0162 0.0003 0.0162 0.0005 0.1321
4.4189 3.84 1000 4.4225 0.0135 0.0002 0.0135 0.0004 0.1315
4.4185 4.03 1050 4.4233 0.0135 0.0002 0.0135 0.0004 0.1334
4.4185 4.22 1100 4.4229 0.0135 0.0002 0.0135 0.0004 0.1334
4.4185 4.41 1150 4.4226 0.0162 0.0003 0.0162 0.0005 0.1321
4.4185 4.6 1200 4.4223 0.0135 0.0002 0.0135 0.0004 0.1334
4.4185 4.79 1250 4.4234 0.0135 0.0002 0.0135 0.0004 0.1334
4.4185 4.99 1300 4.4225 0.0135 0.0002 0.0135 0.0004 0.1302
4.4351 5.18 1350 4.4225 0.0162 0.0003 0.0162 0.0005 0.1321
4.4351 5.37 1400 4.4231 0.0135 0.0002 0.0135 0.0004 0.1334
4.4351 5.56 1450 4.4233 0.0135 0.0002 0.0135 0.0004 0.1334
4.4351 5.75 1500 4.4220 0.0135 0.0002 0.0135 0.0004 0.1334
4.4351 5.94 1550 4.4217 0.0135 0.0002 0.0135 0.0004 0.1334
4.4178 6.14 1600 4.4225 0.0162 0.0003 0.0162 0.0005 0.1321
4.4178 6.33 1650 4.4217 0.0162 0.0003 0.0162 0.0005 0.1321
4.4178 6.52 1700 4.4222 0.0135 0.0002 0.0135 0.0004 0.1334
4.4178 6.71 1750 4.4226 0.0135 0.0002 0.0135 0.0004 0.1334
4.4178 6.9 1800 4.4222 0.0135 0.0002 0.0135 0.0004 0.1334
4.4175 7.09 1850 4.4232 0.0135 0.0002 0.0135 0.0004 0.1334
4.4175 7.29 1900 4.4235 0.0135 0.0002 0.0135 0.0004 0.1334
4.4175 7.48 1950 4.4231 0.0135 0.0002 0.0135 0.0004 0.1334
4.4175 7.67 2000 4.4235 0.0135 0.0002 0.0135 0.0004 0.1334

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.3.0
  • Datasets 2.19.1
  • Tokenizers 0.15.1