|
|
--- |
|
|
license: mit |
|
|
base_model: FacebookAI/roberta-base |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
- f1 |
|
|
- precision |
|
|
- recall |
|
|
model-index: |
|
|
- name: roberta-base-CD_baseline |
|
|
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. --> |
|
|
|
|
|
# roberta-base-CD_baseline |
|
|
|
|
|
This model is a fine-tuned version of [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 1.3012 |
|
|
- Accuracy: 0.5435 |
|
|
- F1: 0.5062 |
|
|
- Precision: 0.5113 |
|
|
- Recall: 0.5435 |
|
|
|
|
|
## 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: 16 |
|
|
- eval_batch_size: 16 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 5 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
|
| 1.6077 | 1.0 | 125 | 1.6378 | 0.4130 | 0.3268 | 0.2997 | 0.4130 | |
|
|
| 1.6016 | 2.0 | 250 | 1.4609 | 0.4870 | 0.4109 | 0.3904 | 0.4870 | |
|
|
| 1.2479 | 3.0 | 375 | 1.4185 | 0.5043 | 0.4485 | 0.4236 | 0.5043 | |
|
|
| 1.1542 | 4.0 | 500 | 1.3072 | 0.5435 | 0.5141 | 0.5397 | 0.5435 | |
|
|
| 1.1302 | 5.0 | 625 | 1.3012 | 0.5435 | 0.5062 | 0.5113 | 0.5435 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.38.0 |
|
|
- Pytorch 2.8.0+cu128 |
|
|
- Datasets 4.2.0 |
|
|
- Tokenizers 0.15.2 |
|
|
|
