metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: aift-model-review-multiple-label-classification
results: []
aift-model-review-multiple-label-classification
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: 2.2623
- Accuracy Thresh: 0.9380
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 |
|---|---|---|---|---|
| 1.6787 | 1.0 | 845 | 0.8456 | 0.8252 |
| 0.749 | 2.0 | 1690 | 0.8447 | 0.8887 |
| 0.5849 | 3.0 | 2535 | 0.9489 | 0.8968 |
| 0.4312 | 4.0 | 3380 | 1.1496 | 0.9084 |
| 0.3469 | 5.0 | 4225 | 1.4157 | 0.9260 |
| 0.2633 | 6.0 | 5070 | 1.8314 | 0.9277 |
| 0.2498 | 7.0 | 5915 | 1.9466 | 0.9355 |
| 0.1782 | 8.0 | 6760 | 1.9609 | 0.9336 |
| 0.1763 | 9.0 | 7605 | 2.2429 | 0.9350 |
| 0.1489 | 10.0 | 8450 | 2.2623 | 0.9380 |
Framework versions
- Transformers 4.37.1
- Pytorch 2.0.0+cu118
- Datasets 2.16.1
- Tokenizers 0.15.0