metadata
library_name: transformers
license: apache-2.0
base_model: bert-base-chinese
tags:
- generated_from_trainer
model-index:
- name: classification_2
results: []
classification_2
This model is a fine-tuned version of bert-base-chinese on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0081
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 3 | 0.6010 |
| No log | 2.0 | 6 | 0.2707 |
| No log | 3.0 | 9 | 0.1115 |
| 0.4602 | 4.0 | 12 | 0.0587 |
| 0.4602 | 5.0 | 15 | 0.0362 |
| 0.4602 | 6.0 | 18 | 0.0200 |
| 0.0664 | 7.0 | 21 | 0.0138 |
| 0.0664 | 8.0 | 24 | 0.0104 |
| 0.0664 | 9.0 | 27 | 0.0087 |
| 0.0205 | 10.0 | 30 | 0.0081 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.9.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1