<!-- 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_Up_Sampling_Sub_Category_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: 4.9368
- Accuracy: 0.6114
- F1: 0.6028
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 |
---|---|---|---|---|---|
0.9716 | 1.0 | 12171 | 2.5228 | 0.5722 | 0.5740 |
0.2857 | 2.0 | 24342 | 3.0558 | 0.5947 | 0.5923 |
0.1438 | 3.0 | 36513 | 3.3499 | 0.6038 | 0.6007 |
0.0842 | 4.0 | 48684 | 3.8879 | 0.5905 | 0.5875 |
0.0504 | 5.0 | 60855 | 4.1478 | 0.5905 | 0.5906 |
0.031 | 6.0 | 73026 | 4.5368 | 0.5924 | 0.5865 |
0.0192 | 7.0 | 85197 | 4.6596 | 0.6042 | 0.5980 |
0.01 | 8.0 | 97368 | 4.8874 | 0.6087 | 0.6005 |
0.0051 | 9.0 | 109539 | 5.0120 | 0.6118 | 0.6015 |
0.0022 | 10.0 | 121710 | 4.9368 | 0.6114 | 0.6028 |
Framework versions
- Transformers 4.22.2
- Pytorch 1.10.2
- Datasets 2.5.2
- Tokenizers 0.12.1