|
--- |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- imagefolder |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: msi-nat-mini |
|
results: |
|
- task: |
|
name: Image Classification |
|
type: image-classification |
|
dataset: |
|
name: imagefolder |
|
type: imagefolder |
|
config: default |
|
split: validation |
|
args: default |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.8460220784164446 |
|
- name: F1 |
|
type: f1 |
|
value: 0.8017318846499469 |
|
- name: Precision |
|
type: precision |
|
value: 0.8296559303406882 |
|
- name: Recall |
|
type: recall |
|
value: 0.7756263336758081 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# msi-nat-mini |
|
|
|
This model was trained from scratch on the imagefolder dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3451 |
|
- Accuracy: 0.8460 |
|
- F1: 0.8017 |
|
- Precision: 0.8297 |
|
- Recall: 0.7756 |
|
|
|
## 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: 1e-06 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| 0.5705 | 1.0 | 1970 | 0.5230 | 0.7410 | 0.6588 | 0.6988 | 0.6232 | |
|
| 0.4805 | 2.0 | 3941 | 0.4447 | 0.7924 | 0.7298 | 0.7640 | 0.6986 | |
|
| 0.4521 | 3.0 | 5911 | 0.4090 | 0.8107 | 0.7518 | 0.7936 | 0.7141 | |
|
| 0.4343 | 4.0 | 7882 | 0.3878 | 0.8239 | 0.7768 | 0.7907 | 0.7634 | |
|
| 0.4003 | 5.0 | 9852 | 0.3720 | 0.8328 | 0.7850 | 0.8113 | 0.7604 | |
|
| 0.3887 | 6.0 | 11823 | 0.3620 | 0.8376 | 0.7875 | 0.8295 | 0.7496 | |
|
| 0.3709 | 7.0 | 13793 | 0.3506 | 0.8435 | 0.7977 | 0.8286 | 0.7690 | |
|
| 0.3686 | 8.0 | 15764 | 0.3473 | 0.8461 | 0.8025 | 0.8271 | 0.7793 | |
|
| 0.3819 | 9.0 | 17734 | 0.3422 | 0.8476 | 0.8052 | 0.8270 | 0.7845 | |
|
| 0.3838 | 10.0 | 19700 | 0.3451 | 0.8460 | 0.8017 | 0.8297 | 0.7756 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
