---
license: apache-2.0
base_model: hfl/chinese-macbert-base
tags:
- generated_from_trainer
datasets:
- clue
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: muliple_choice2
  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. -->

# muliple_choice2

This model is a fine-tuned version of [hfl/chinese-macbert-base](https://huggingface.co/hfl/chinese-macbert-base) on the clue dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3057
- Accuracy: 0.38
- Precision: 0.3923
- Recall: 0.3840
- F1: 0.3787

## 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: 2
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| No log        | 1.0   | 25   | 1.3834          | 0.38     | 0.4064    | 0.3803 | 0.3842 |
| 1.3946        | 2.0   | 50   | 1.3515          | 0.4      | 0.4211    | 0.3970 | 0.4002 |
| 1.3946        | 3.0   | 75   | 1.3057          | 0.38     | 0.3923    | 0.3840 | 0.3787 |


### Framework versions

- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2