metadata
library_name: transformers
license: apache-2.0
base_model: bert-base-chinese
tags:
- generated_from_trainer
model-index:
- name: EasyCard
results: []
EasyCard
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: 0.0046
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_steps: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 5 | 0.0792 |
| 0.4505 | 2.0 | 10 | 0.0441 |
| 0.4505 | 3.0 | 15 | 0.0246 |
| 0.1388 | 4.0 | 20 | 0.0155 |
| 0.1388 | 5.0 | 25 | 0.0098 |
| 0.0600 | 6.0 | 30 | 0.0075 |
| 0.0600 | 7.0 | 35 | 0.0087 |
| 0.0358 | 8.0 | 40 | 0.0065 |
| 0.0358 | 9.0 | 45 | 0.0050 |
| 0.0260 | 10.0 | 50 | 0.0046 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2