metadata
license: gpl-3.0
base_model: ckiplab/bert-base-chinese
tags:
- generated_from_trainer
model-index:
- name: clip-DIT-finetuned
results: []
clip-DIT-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: 0.7439
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: 1e-05
- train_batch_size: 64
- eval_batch_size: 100
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 100.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.648 | 10.0 | 780 | 2.4340 |
| 0.797 | 20.0 | 1560 | 1.5686 |
| 0.3112 | 30.0 | 2340 | 1.2473 |
| 0.1758 | 40.0 | 3120 | 1.0606 |
| 0.1176 | 50.0 | 3900 | 0.9469 |
| 0.09 | 60.0 | 4680 | 0.8606 |
| 0.0733 | 70.0 | 5460 | 0.8265 |
| 0.0631 | 80.0 | 6240 | 0.7704 |
| 0.0576 | 90.0 | 7020 | 0.7507 |
| 0.0545 | 100.0 | 7800 | 0.7439 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1