metadata
base_model: nghuyong/ernie-2.0-base-en
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: ernie-2.0-base-en
results: []
ernie-2.0-base-en
This model is a fine-tuned version of nghuyong/ernie-2.0-base-en on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2022
- Precision: 0.7745
- Recall: 0.8255
- F1: 0.7992
- Accuracy: 0.9392
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2221 | 1.0 | 2078 | 0.2066 | 0.7130 | 0.8024 | 0.7551 | 0.9309 |
| 0.1813 | 2.0 | 4156 | 0.1972 | 0.7573 | 0.8224 | 0.7885 | 0.9362 |
| 0.1397 | 3.0 | 6234 | 0.2022 | 0.7745 | 0.8255 | 0.7992 | 0.9392 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1