|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: distilbert-base-uncased-finetuned-zindi_tweets |
|
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. --> |
|
|
|
# distilbert-base-uncased-finetuned-zindi_tweets |
|
|
|
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: 0.3203 |
|
- Accuracy: 0.9168 |
|
- F1: 0.9168 |
|
|
|
## 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: 64 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 8 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
|
| 0.4224 | 1.0 | 67 | 0.2924 | 0.8894 | 0.8893 | |
|
| 0.2096 | 2.0 | 134 | 0.2632 | 0.9055 | 0.9055 | |
|
| 0.1329 | 3.0 | 201 | 0.2744 | 0.9102 | 0.9101 | |
|
| 0.1016 | 4.0 | 268 | 0.2868 | 0.9055 | 0.9054 | |
|
| 0.0752 | 5.0 | 335 | 0.2896 | 0.9140 | 0.9140 | |
|
| 0.0454 | 6.0 | 402 | 0.3077 | 0.9178 | 0.9178 | |
|
| 0.0305 | 7.0 | 469 | 0.3185 | 0.9149 | 0.9149 | |
|
| 0.0298 | 8.0 | 536 | 0.3203 | 0.9168 | 0.9168 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.20.1 |
|
- Pytorch 1.11.0+cu113 |
|
- Datasets 2.3.2 |
|
- Tokenizers 0.12.1 |
|
|
