metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: distilbert-base-uncased-finetuned-yahd
results: []
distilbert-base-uncased-finetuned-yahd
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: 2.4917
- Accuracy: 0.1472
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 |
|---|---|---|---|---|
| 2.7712 | 1.0 | 875 | 2.6037 | 0.1212 |
| 2.4896 | 2.0 | 1750 | 2.5123 | 0.1365 |
| 2.2153 | 3.0 | 2625 | 2.4918 | 0.142 |
| 1.93 | 4.0 | 3500 | 2.4917 | 0.1472 |
| 1.804 | 5.0 | 4375 | 2.5146 | 0.146 |
Framework versions
- Transformers 4.12.3
- Pytorch 1.9.0+cu102
- Datasets 1.15.1
- Tokenizers 0.10.3