metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: distilbert-base-uncased__sst2__train-8-0
results: []
distilbert-base-uncased__sst2__train-8-0
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: 0.6527
- Accuracy: 0.6150
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 |
---|---|---|---|---|
0.7204 | 1.0 | 4 | 0.6917 | 0.5074 |
0.6649 | 2.0 | 8 | 0.6879 | 0.6118 |
0.6472 | 3.0 | 12 | 0.6838 | 0.6035 |
0.6176 | 4.0 | 16 | 0.6774 | 0.6299 |
0.5697 | 5.0 | 20 | 0.6697 | 0.6326 |
0.508 | 6.0 | 24 | 0.6615 | 0.6310 |
0.4138 | 7.0 | 28 | 0.6553 | 0.6222 |
0.345 | 8.0 | 32 | 0.6527 | 0.6150 |
0.2653 | 9.0 | 36 | 0.6583 | 0.6200 |
0.2017 | 10.0 | 40 | 0.6712 | 0.6145 |
0.1492 | 11.0 | 44 | 0.6842 | 0.6145 |
Framework versions
- Transformers 4.15.0
- Pytorch 1.10.2+cu102
- Datasets 1.18.2
- Tokenizers 0.10.3