metadata
base_model: nghuyong/ernie-3.0-base-zh
tags:
- generated_from_trainer
model-index:
- name: ernie-3.0-base-zh-RETACRED-1114
results: []
ernie-3.0-base-zh-RETACRED-1114
This model is a fine-tuned version of nghuyong/ernie-3.0-base-zh on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5717
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: 32
- eval_batch_size: 32
- 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 |
|---|---|---|---|
| 0.7051 | 1.0 | 1828 | 0.8364 |
| 0.4123 | 2.0 | 3656 | 0.5858 |
| 0.2877 | 3.0 | 5484 | 0.5529 |
| 0.2104 | 4.0 | 7312 | 0.5543 |
| 0.1484 | 5.0 | 9140 | 0.5717 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1