metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: distilbert-base-uncased-finetuned-yahd-twval
results: []
distilbert-base-uncased-finetuned-yahd-twval
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: 2.5919
- Accuracy: 0.3810
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.4726 | 1.0 | 10001 | 2.9721 | 0.3051 |
1.5319 | 2.0 | 20002 | 2.5919 | 0.3810 |
1.1895 | 3.0 | 30003 | 3.9355 | 0.2664 |
0.8886 | 4.0 | 40004 | 4.6847 | 0.2515 |
0.7142 | 5.0 | 50005 | 4.8659 | 0.2604 |
Framework versions
- Transformers 4.12.3
- Pytorch 1.9.0+cu102
- Datasets 1.15.1
- Tokenizers 0.10.3