|
--- |
|
license: apache-2.0 |
|
base_model: distilbert/distilroberta-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: distilroberta_base_twitter |
|
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. --> |
|
|
|
# distilroberta_base_twitter |
|
|
|
This model is a fine-tuned version of [distilbert/distilroberta-base](https://huggingface.co/distilbert/distilroberta-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4812 |
|
- Accuracy: 0.7721 |
|
- F1 Macro: 0.7373 |
|
- F1 Micro: 0.7721 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 2 |
|
- total_train_batch_size: 64 |
|
- total_eval_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Micro | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:| |
|
| 0.4863 | 0.37 | 50 | 0.4848 | 0.7583 | 0.7216 | 0.7583 | |
|
| 0.4736 | 0.74 | 100 | 0.4862 | 0.7629 | 0.7079 | 0.7629 | |
|
| 0.463 | 1.1 | 150 | 0.4935 | 0.7739 | 0.7356 | 0.7739 | |
|
| 0.4703 | 1.47 | 200 | 0.4812 | 0.7721 | 0.7373 | 0.7721 | |
|
| 0.4537 | 1.84 | 250 | 0.4855 | 0.7665 | 0.7305 | 0.7665 | |
|
| 0.4206 | 2.21 | 300 | 0.4880 | 0.7675 | 0.7283 | 0.7675 | |
|
| 0.4561 | 2.57 | 350 | 0.4913 | 0.7629 | 0.7299 | 0.7629 | |
|
| 0.3738 | 2.94 | 400 | 0.4950 | 0.7702 | 0.7359 | 0.7702 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.0.dev0 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
