metadata
base_model: bert-base-chinese
metrics:
- accuracy
tags:
- generated_from_trainer
model-index:
- name: bert-base-chinese-climate-related-prediction-v2
results: []
bert-base-chinese-climate-related-prediction-v2
This model is a fine-tuned version of bert-base-chinese on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5613
- Accuracy: 0.96
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 175 | 0.4095 | 0.97 |
| No log | 2.0 | 350 | 0.4708 | 0.96 |
| 0.0 | 3.0 | 525 | 0.5164 | 0.96 |
| 0.0 | 4.0 | 700 | 0.5271 | 0.96 |
| 0.0 | 5.0 | 875 | 0.5314 | 0.96 |
| 0.0 | 6.0 | 1050 | 0.5414 | 0.96 |
| 0.0 | 7.0 | 1225 | 0.5507 | 0.96 |
| 0.0 | 8.0 | 1400 | 0.5575 | 0.96 |
| 0.0 | 9.0 | 1575 | 0.5597 | 0.96 |
| 0.0 | 10.0 | 1750 | 0.5613 | 0.96 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1