|
|
--- |
|
|
license: apache-2.0 |
|
|
base_model: google-bert/bert-large-uncased |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- precision |
|
|
- recall |
|
|
- f1 |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: cfd_model2 |
|
|
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. --> |
|
|
|
|
|
# cfd_model2 |
|
|
|
|
|
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: 0.0066 |
|
|
- Precision: 0.9978 |
|
|
- Recall: 0.9987 |
|
|
- F1: 0.9982 |
|
|
- Accuracy: 0.9986 |
|
|
|
|
|
## 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: 3e-05 |
|
|
- train_batch_size: 4 |
|
|
- eval_batch_size: 4 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 4 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
|
| 0.0493 | 0.19 | 100 | 0.0352 | 0.9890 | 0.9930 | 0.9910 | 0.9937 | |
|
|
| 0.0103 | 0.39 | 200 | 0.0273 | 0.9886 | 0.9956 | 0.9921 | 0.9946 | |
|
|
| 0.0011 | 0.58 | 300 | 0.0190 | 0.9921 | 0.9978 | 0.9950 | 0.9960 | |
|
|
| 0.0247 | 0.77 | 400 | 0.0167 | 0.9978 | 0.9943 | 0.9960 | 0.9968 | |
|
|
| 0.0003 | 0.97 | 500 | 0.0269 | 0.9926 | 0.9978 | 0.9952 | 0.9961 | |
|
|
| 0.0036 | 1.16 | 600 | 0.0133 | 0.9960 | 0.9960 | 0.9960 | 0.9968 | |
|
|
| 0.0008 | 1.35 | 700 | 0.0222 | 0.9926 | 0.9987 | 0.9956 | 0.9965 | |
|
|
| 0.0003 | 1.55 | 800 | 0.0287 | 0.9895 | 0.9974 | 0.9934 | 0.9953 | |
|
|
| 0.0005 | 1.74 | 900 | 0.0132 | 0.9934 | 0.9982 | 0.9958 | 0.9970 | |
|
|
| 0.0024 | 1.93 | 1000 | 0.0123 | 0.9952 | 0.9982 | 0.9967 | 0.9977 | |
|
|
| 0.0007 | 2.13 | 1100 | 0.0099 | 0.9969 | 0.9943 | 0.9956 | 0.9965 | |
|
|
| 0.0005 | 2.32 | 1200 | 0.0087 | 0.9978 | 0.9965 | 0.9971 | 0.9977 | |
|
|
| 0.001 | 2.51 | 1300 | 0.0055 | 0.9974 | 0.9991 | 0.9982 | 0.9986 | |
|
|
| 0.0002 | 2.71 | 1400 | 0.0049 | 0.9974 | 0.9982 | 0.9978 | 0.9986 | |
|
|
| 0.0004 | 2.9 | 1500 | 0.0065 | 0.9969 | 0.9982 | 0.9976 | 0.9984 | |
|
|
| 0.0002 | 3.09 | 1600 | 0.0071 | 0.9969 | 0.9978 | 0.9974 | 0.9982 | |
|
|
| 0.0001 | 3.29 | 1700 | 0.0077 | 0.9974 | 0.9978 | 0.9976 | 0.9984 | |
|
|
| 0.0002 | 3.48 | 1800 | 0.0072 | 0.9974 | 0.9978 | 0.9976 | 0.9984 | |
|
|
| 0.0005 | 3.68 | 1900 | 0.0072 | 0.9974 | 0.9978 | 0.9976 | 0.9984 | |
|
|
| 0.0207 | 3.87 | 2000 | 0.0066 | 0.9978 | 0.9987 | 0.9982 | 0.9986 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.36.2 |
|
|
- Pytorch 2.1.2+cu121 |
|
|
- Datasets 2.14.6 |
|
|
- Tokenizers 0.15.0 |
|
|
|
