|
--- |
|
license: mit |
|
base_model: roberta-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: roberta-base_topic_classification_nyt_news |
|
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_topic_classification_nyt_news |
|
|
|
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3797 |
|
- Accuracy: 0.9094 |
|
- F1: 0.9092 |
|
- Precision: 0.9098 |
|
- Recall: 0.9094 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 500 |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |
|
|:-------------:|:-----:|:------:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| 0.3192 | 1.0 | 20480 | 0.4078 | 0.8865 | 0.8859 | 0.8892 | 0.8865 | |
|
| 0.2863 | 2.0 | 40960 | 0.4271 | 0.8972 | 0.8970 | 0.8982 | 0.8972 | |
|
| 0.1979 | 3.0 | 61440 | 0.3797 | 0.9094 | 0.9092 | 0.9098 | 0.9094 | |
|
| 0.1239 | 4.0 | 81920 | 0.3981 | 0.9117 | 0.9113 | 0.9114 | 0.9117 | |
|
| 0.1472 | 5.0 | 102400 | 0.4033 | 0.9137 | 0.9135 | 0.9134 | 0.9137 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.32.1 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.2 |
|
|