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: 2.8670
- Accuracy: 0.1863
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: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.6746 | 1.0 | 919 | 2.5961 | 0.1324 |
| 2.3991 | 2.0 | 1838 | 2.5052 | 0.1448 |
| 2.036 | 3.0 | 2757 | 2.5028 | 0.1554 |
| 1.6838 | 4.0 | 3676 | 2.6002 | 0.1614 |
| 1.3583 | 5.0 | 4595 | 2.7135 | 0.1783 |
| 1.17 | 6.0 | 5514 | 2.8161 | 0.1787 |
| 1.0365 | 7.0 | 6433 | 2.8670 | 0.1863 |
Framework versions
- Transformers 4.12.3
- Pytorch 1.9.0+cu102
- Datasets 1.15.1
- Tokenizers 0.10.3