|
--- |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- preprocessed1024_config |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: convnext-mlo-512-breat_composition |
|
results: |
|
- task: |
|
name: Image Classification |
|
type: image-classification |
|
dataset: |
|
name: preprocessed1024_config |
|
type: preprocessed1024_config |
|
args: default |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: |
|
accuracy: 0.5665829145728644 |
|
- name: F1 |
|
type: f1 |
|
value: |
|
f1: 0.5549950963329491 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# convnext-mlo-512-breat_composition |
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on the preprocessed1024_config dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.1801 |
|
- Accuracy: {'accuracy': 0.5665829145728644} |
|
- F1: {'f1': 0.5549950963329491} |
|
|
|
## 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 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------------------------------:|:---------------------------:| |
|
| 1.3412 | 1.0 | 796 | 1.1931 | {'accuracy': 0.4547738693467337} | {'f1': 0.31154642522501674} | |
|
| 1.1149 | 2.0 | 1592 | 1.0845 | {'accuracy': 0.4886934673366834} | {'f1': 0.40829339044510005} | |
|
| 1.0531 | 3.0 | 2388 | 1.1650 | {'accuracy': 0.48304020100502515} | {'f1': 0.38992060973001436} | |
|
| 0.917 | 4.0 | 3184 | 0.9950 | {'accuracy': 0.5452261306532663} | {'f1': 0.50281030200465} | |
|
| 0.8633 | 5.0 | 3980 | 1.0152 | {'accuracy': 0.5552763819095478} | {'f1': 0.511332789082197} | |
|
| 0.7747 | 6.0 | 4776 | 1.0201 | {'accuracy': 0.5703517587939698} | {'f1': 0.523154780871296} | |
|
| 0.7133 | 7.0 | 5572 | 1.0345 | {'accuracy': 0.5640703517587939} | {'f1': 0.5198008328503952} | |
|
| 0.659 | 8.0 | 6368 | 1.0702 | {'accuracy': 0.5785175879396985} | {'f1': 0.5460580312777853} | |
|
| 0.5943 | 9.0 | 7164 | 1.1634 | {'accuracy': 0.5734924623115578} | {'f1': 0.5501266468657362} | |
|
| 0.5699 | 10.0 | 7960 | 1.1801 | {'accuracy': 0.5665829145728644} | {'f1': 0.5549950963329491} | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.20.1 |
|
- Pytorch 1.12.0 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.12.1 |
|
|
