|
--- |
|
license: apache-2.0 |
|
tags: |
|
- image-classification |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: exper7_mesum5 |
|
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. --> |
|
|
|
# exper7_mesum5 |
|
|
|
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the sudo-s/herbier_mesuem5 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5889 |
|
- Accuracy: 0.8538 |
|
|
|
## 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: 0.0001 |
|
- train_batch_size: 16 |
|
- 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 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 4.2072 | 0.23 | 100 | 4.1532 | 0.1923 | |
|
| 3.5433 | 0.47 | 200 | 3.5680 | 0.2888 | |
|
| 3.1388 | 0.7 | 300 | 3.1202 | 0.3911 | |
|
| 2.7924 | 0.93 | 400 | 2.7434 | 0.4787 | |
|
| 2.1269 | 1.16 | 500 | 2.3262 | 0.5781 | |
|
| 1.8589 | 1.4 | 600 | 1.9754 | 0.6272 | |
|
| 1.7155 | 1.63 | 700 | 1.7627 | 0.6840 | |
|
| 1.4689 | 1.86 | 800 | 1.5937 | 0.6994 | |
|
| 1.0149 | 2.09 | 900 | 1.3168 | 0.7497 | |
|
| 0.8148 | 2.33 | 1000 | 1.1630 | 0.7615 | |
|
| 0.7159 | 2.56 | 1100 | 1.0869 | 0.7675 | |
|
| 0.7257 | 2.79 | 1200 | 0.9607 | 0.7893 | |
|
| 0.4171 | 3.02 | 1300 | 0.8835 | 0.7935 | |
|
| 0.2969 | 3.26 | 1400 | 0.8259 | 0.8130 | |
|
| 0.2405 | 3.49 | 1500 | 0.7711 | 0.8142 | |
|
| 0.2948 | 3.72 | 1600 | 0.7629 | 0.8112 | |
|
| 0.1765 | 3.95 | 1700 | 0.7117 | 0.8124 | |
|
| 0.1603 | 4.19 | 1800 | 0.6946 | 0.8237 | |
|
| 0.0955 | 4.42 | 1900 | 0.6597 | 0.8349 | |
|
| 0.0769 | 4.65 | 2000 | 0.6531 | 0.8266 | |
|
| 0.0816 | 4.88 | 2100 | 0.6335 | 0.8337 | |
|
| 0.0315 | 5.12 | 2200 | 0.6087 | 0.8402 | |
|
| 0.0368 | 5.35 | 2300 | 0.6026 | 0.8444 | |
|
| 0.0377 | 5.58 | 2400 | 0.6450 | 0.8278 | |
|
| 0.0603 | 5.81 | 2500 | 0.6564 | 0.8343 | |
|
| 0.0205 | 6.05 | 2600 | 0.6119 | 0.8467 | |
|
| 0.019 | 6.28 | 2700 | 0.6070 | 0.8479 | |
|
| 0.0249 | 6.51 | 2800 | 0.6002 | 0.8538 | |
|
| 0.0145 | 6.74 | 2900 | 0.6012 | 0.8497 | |
|
| 0.0134 | 6.98 | 3000 | 0.5991 | 0.8521 | |
|
| 0.0271 | 7.21 | 3100 | 0.5972 | 0.8503 | |
|
| 0.0128 | 7.44 | 3200 | 0.5911 | 0.8521 | |
|
| 0.0123 | 7.67 | 3300 | 0.5889 | 0.8538 | |
|
| 0.0278 | 7.91 | 3400 | 0.6135 | 0.8491 | |
|
| 0.0106 | 8.14 | 3500 | 0.5934 | 0.8533 | |
|
| 0.0109 | 8.37 | 3600 | 0.5929 | 0.8533 | |
|
| 0.0095 | 8.6 | 3700 | 0.5953 | 0.8550 | |
|
| 0.009 | 8.84 | 3800 | 0.5933 | 0.8574 | |
|
| 0.009 | 9.07 | 3900 | 0.5948 | 0.8550 | |
|
| 0.0089 | 9.3 | 4000 | 0.5953 | 0.8556 | |
|
| 0.0086 | 9.53 | 4100 | 0.5956 | 0.8544 | |
|
| 0.0085 | 9.77 | 4200 | 0.5955 | 0.8556 | |
|
| 0.0087 | 10.0 | 4300 | 0.5954 | 0.8538 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.20.1 |
|
- Pytorch 1.12.0+cu113 |
|
- Datasets 2.3.2 |
|
- Tokenizers 0.12.1 |
|
|
