metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: aift-model
results: []
aift-model
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: 2.1529
- Accuracy Thresh: 0.9374
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: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: tpu
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy Thresh |
---|---|---|---|---|
1.7187 | 1.0 | 845 | 0.8176 | 0.8261 |
0.7417 | 2.0 | 1690 | 0.7961 | 0.8918 |
0.5647 | 3.0 | 2535 | 0.9633 | 0.9031 |
0.441 | 4.0 | 3380 | 1.1189 | 0.9162 |
0.3397 | 5.0 | 4225 | 1.4119 | 0.9260 |
0.2637 | 6.0 | 5070 | 1.8281 | 0.9270 |
0.2387 | 7.0 | 5915 | 1.8851 | 0.9309 |
0.1711 | 8.0 | 6760 | 1.8036 | 0.9349 |
0.1723 | 9.0 | 7605 | 2.1980 | 0.9373 |
0.1573 | 10.0 | 8450 | 2.1529 | 0.9374 |
Framework versions
- Transformers 4.37.1
- Pytorch 2.0.0+cu118
- Datasets 2.16.1
- Tokenizers 0.15.0