metadata
base_model: nghuyong/ernie-1.0
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: Ernie-PoliticalBias-Finetune
results: []
Ernie-PoliticalBias-Finetune
This model is a fine-tuned version of nghuyong/ernie-1.0 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4782
- Accuracy: 0.8021
- F1: 0.7908
- Precision: 0.8155
- Recall: 0.7776
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: 16
- 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 |
|---|---|---|---|---|---|---|---|
| 0.587 | 1.0 | 3845 | 0.5531 | 0.7607 | 0.7532 | 0.7679 | 0.7454 |
| 0.7662 | 2.0 | 7690 | 0.5028 | 0.7948 | 0.7839 | 0.8301 | 0.7626 |
| 0.4928 | 3.0 | 11535 | 0.4782 | 0.8021 | 0.7908 | 0.8155 | 0.7776 |
| 0.414 | 4.0 | 15380 | 0.5139 | 0.8179 | 0.8043 | 0.8335 | 0.7878 |
| 0.2473 | 5.0 | 19225 | 0.5511 | 0.8218 | 0.8103 | 0.8193 | 0.8033 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.19.1