<!-- 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. -->
distilbert-base-uncased_finetuned_Balance_Upsampling_SPEECH_TEXT_DISPLAY_v1
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.6982
- Accuracy: 0.7759
- F1: 0.7743
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: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
---|---|---|---|---|---|
0.5321 | 1.0 | 7958 | 1.3225 | 0.7271 | 0.7391 |
0.2967 | 2.0 | 15916 | 1.3868 | 0.7574 | 0.7601 |
0.1821 | 3.0 | 23874 | 1.4753 | 0.7513 | 0.7515 |
0.1193 | 4.0 | 31832 | 1.7028 | 0.7588 | 0.7596 |
0.0722 | 5.0 | 39790 | 1.8155 | 0.7615 | 0.7599 |
0.041 | 6.0 | 47748 | 2.1622 | 0.7695 | 0.7678 |
0.0258 | 7.0 | 55706 | 2.3871 | 0.75 | 0.7462 |
0.0149 | 8.0 | 63664 | 2.6135 | 0.7571 | 0.7524 |
0.0076 | 9.0 | 71622 | 2.7974 | 0.7648 | 0.7617 |
0.0051 | 10.0 | 79580 | 2.6982 | 0.7759 | 0.7743 |
Framework versions
- Transformers 4.22.2
- Pytorch 1.10.2
- Datasets 2.5.2
- Tokenizers 0.12.1