|
|
--- |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
base_model: google-bert/bert-large-uncased |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
- precision |
|
|
- recall |
|
|
- f1 |
|
|
model-index: |
|
|
- name: math_question_grade_detection_Bert_databalanced_v2 |
|
|
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. --> |
|
|
|
|
|
# math_question_grade_detection_Bert_databalanced_v2 |
|
|
|
|
|
This model is a fine-tuned version of [google-bert/bert-large-uncased](https://huggingface.co/google-bert/bert-large-uncased) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.5945 |
|
|
- Accuracy: 0.8127 |
|
|
- Precision: 0.8116 |
|
|
- Recall: 0.8127 |
|
|
- F1: 0.8110 |
|
|
|
|
|
## 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: 16 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 2 |
|
|
- total_train_batch_size: 32 |
|
|
- optimizer: Use adamw_torch 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: 200 |
|
|
- training_steps: 1000 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | |
|
|
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:| |
|
|
| No log | 0.2817 | 50 | 2.1406 | 0.1698 | 0.1183 | 0.1698 | 0.1327 | |
|
|
| No log | 0.5634 | 100 | 1.8833 | 0.3540 | 0.3387 | 0.3540 | 0.2911 | |
|
|
| No log | 0.8451 | 150 | 1.5465 | 0.4365 | 0.4580 | 0.4365 | 0.4060 | |
|
|
| No log | 1.1268 | 200 | 1.2969 | 0.4937 | 0.4950 | 0.4937 | 0.4471 | |
|
|
| No log | 1.4085 | 250 | 1.0146 | 0.6143 | 0.6253 | 0.6143 | 0.5906 | |
|
|
| No log | 1.6901 | 300 | 0.8713 | 0.6778 | 0.6771 | 0.6778 | 0.6476 | |
|
|
| No log | 1.9718 | 350 | 0.7740 | 0.7016 | 0.7000 | 0.7016 | 0.6896 | |
|
|
| No log | 2.2535 | 400 | 0.7760 | 0.6968 | 0.7068 | 0.6968 | 0.6872 | |
|
|
| No log | 2.5352 | 450 | 0.6579 | 0.7619 | 0.7726 | 0.7619 | 0.7590 | |
|
|
| 1.2792 | 2.8169 | 500 | 0.6872 | 0.7429 | 0.7571 | 0.7429 | 0.7418 | |
|
|
| 1.2792 | 3.0986 | 550 | 0.6073 | 0.7698 | 0.7783 | 0.7698 | 0.7700 | |
|
|
| 1.2792 | 3.3803 | 600 | 0.6297 | 0.7714 | 0.7840 | 0.7714 | 0.7718 | |
|
|
| 1.2792 | 3.6620 | 650 | 0.6160 | 0.7762 | 0.7764 | 0.7762 | 0.7731 | |
|
|
| 1.2792 | 3.9437 | 700 | 0.5895 | 0.8111 | 0.8147 | 0.8111 | 0.8110 | |
|
|
| 1.2792 | 4.2254 | 750 | 0.5717 | 0.8111 | 0.8087 | 0.8111 | 0.8089 | |
|
|
| 1.2792 | 4.5070 | 800 | 0.5767 | 0.8095 | 0.8126 | 0.8095 | 0.8083 | |
|
|
| 1.2792 | 4.7887 | 850 | 0.5898 | 0.8016 | 0.8029 | 0.8016 | 0.7995 | |
|
|
| 1.2792 | 5.0704 | 900 | 0.5908 | 0.8127 | 0.8143 | 0.8127 | 0.8115 | |
|
|
| 1.2792 | 5.3521 | 950 | 0.5972 | 0.8111 | 0.8136 | 0.8111 | 0.8102 | |
|
|
| 0.304 | 5.6338 | 1000 | 0.5945 | 0.8127 | 0.8116 | 0.8127 | 0.8110 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.46.3 |
|
|
- Pytorch 2.4.0 |
|
|
- Datasets 3.1.0 |
|
|
- Tokenizers 0.20.3 |
|
|
|
