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: 1.2379
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: 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 |
|---|---|---|---|
| 2.6587 | 10.0 | 300 | 2.6721 |
| 0.5242 | 20.0 | 600 | 1.9951 |
| 0.1995 | 30.0 | 900 | 1.7767 |
| 0.1025 | 40.0 | 1200 | 1.6003 |
| 0.0609 | 50.0 | 1500 | 1.5020 |
| 0.042 | 60.0 | 1800 | 1.3372 |
| 0.0315 | 70.0 | 2100 | 1.3104 |
| 0.0271 | 80.0 | 2400 | 1.2715 |
| 0.0212 | 90.0 | 2700 | 1.2446 |
| 0.0202 | 100.0 | 3000 | 1.2379 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1