hatespeech_ast / README.md
Luca-Engel's picture
ast trainer push best model after 5 epochs fp16
d4786ea verified
|
raw
history blame
2.14 kB
metadata
license: bsd-3-clause
base_model: MIT/ast-finetuned-audioset-10-10-0.4593
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - recall
  - precision
  - f1
model-index:
  - name: DL_Audio_Hatespeech_ast_trainer_push
    results: []

DL_Audio_Hatespeech_ast_trainer_push

This model is a fine-tuned version of MIT/ast-finetuned-audioset-10-10-0.4593 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6336
  • Accuracy: 0.6431
  • Recall: 0.7452
  • Precision: 0.6237
  • F1: 0.6790

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: 16
  • eval_batch_size: 16
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 5
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy Recall Precision F1
0.6432 0.9987 387 0.6686 0.5992 0.6580 0.5944 0.6245
0.6414 2.0 775 0.6336 0.6431 0.7452 0.6237 0.6790
0.6079 2.9987 1162 0.6505 0.6328 0.5783 0.6561 0.6148
0.5088 4.0 1550 0.7122 0.6176 0.6624 0.6136 0.6371
0.3005 4.9935 1935 0.9250 0.6099 0.6038 0.6176 0.6106

Framework versions

  • Transformers 4.40.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.3.2
  • Tokenizers 0.19.1