metadata
license: gpl-3.0
base_model: ckiplab/bert-base-chinese
tags:
- generated_from_trainer
model-index:
- name: clip-roberta-finetuned
results: []
clip-roberta-finetuned
This model is a fine-tuned version of ckiplab/bert-base-chinese on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 7.7902
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: 80
- eval_batch_size: 150
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 150.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.2125 | 15.0 | 240 | 7.3975 |
| 0.2662 | 30.0 | 480 | 7.6902 |
| 0.0878 | 45.0 | 720 | 7.7278 |
| 0.0478 | 60.0 | 960 | 7.7675 |
| 0.0271 | 75.0 | 1200 | 7.8001 |
| 0.0204 | 90.0 | 1440 | 7.7704 |
| 0.0153 | 105.0 | 1680 | 7.7562 |
| 0.0144 | 120.0 | 1920 | 7.7687 |
| 0.0118 | 135.0 | 2160 | 7.7854 |
| 0.0109 | 150.0 | 2400 | 7.7902 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1