metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: distilbert-base-uncased__sst2__train-8-5
results: []
distilbert-base-uncased__sst2__train-8-5
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: 0.6920
- Accuracy: 0.5129
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: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7057 | 1.0 | 3 | 0.6848 | 0.75 |
| 0.6681 | 2.0 | 6 | 0.6875 | 0.5 |
| 0.6591 | 3.0 | 9 | 0.6868 | 0.25 |
| 0.6052 | 4.0 | 12 | 0.6943 | 0.25 |
| 0.557 | 5.0 | 15 | 0.7078 | 0.25 |
| 0.4954 | 6.0 | 18 | 0.7168 | 0.25 |
Framework versions
- Transformers 4.15.0
- Pytorch 1.10.2+cu102
- Datasets 1.18.2
- Tokenizers 0.10.3