---
base_model: bert-base-chinese
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: BERT_test_graident_accumulation_test3
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# BERT_test_graident_accumulation_test3

This model is a fine-tuned version of [bert-base-chinese](https://huggingface.co/bert-base-chinese) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0101
- Accuracy: 0.6102

## 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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log        | 1.0   | 94   | 0.9398          | 0.6007   |
| No log        | 2.0   | 188  | 0.9191          | 0.6183   |
| No log        | 3.0   | 282  | 1.0101          | 0.6102   |


### Framework versions

- Transformers 4.36.0
- Pytorch 2.1.1+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0