|
--- |
|
license: apache-2.0 |
|
base_model: distilbert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: aift-model-review-multiple-label-classification |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# aift-model-review-multiple-label-classification |
|
|
|
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.4463 |
|
- Accuracy Thresh: 0.9341 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------------:| |
|
| 1.9127 | 1.0 | 851 | 0.9906 | 0.8086 | |
|
| 0.8577 | 2.0 | 1702 | 1.0184 | 0.8701 | |
|
| 0.6468 | 3.0 | 2553 | 1.0851 | 0.8901 | |
|
| 0.494 | 4.0 | 3404 | 1.2894 | 0.9122 | |
|
| 0.3875 | 5.0 | 4255 | 1.6629 | 0.9232 | |
|
| 0.3422 | 6.0 | 5106 | 1.7630 | 0.9212 | |
|
| 0.3121 | 7.0 | 5957 | 1.9873 | 0.9274 | |
|
| 0.283 | 8.0 | 6808 | 2.3035 | 0.9328 | |
|
| 0.2385 | 9.0 | 7659 | 2.4651 | 0.9338 | |
|
| 0.1973 | 10.0 | 8510 | 2.4463 | 0.9341 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.1 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |
|
|
