metadata
license: apache-2.0
base_model: google/vit-base-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: vit-base-patch16-224-RU4-40
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: 0.7833333333333333
vit-base-patch16-224-RU4-40
This model is a fine-tuned version of google/vit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 49869186446092573277078519432609792.0000
- Accuracy: 0.7833
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: 5.5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 40
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 62336480581735638025587599492513792.0000 | 0.99 | 19 | 49869186446092573277078519432609792.0000 | 0.4667 |
| 58440439651504818626990770153848832.0000 | 1.97 | 38 | 49869186446092573277078519432609792.0000 | 0.6 |
| 50648389482308178156834519410278400.0000 | 2.96 | 57 | 49869186446092573277078519432609792.0000 | 0.7333 |
| 56102820639337698928052607882625024.0000 | 4.0 | 77 | 49869186446092573277078519432609792.0000 | 0.75 |
| 62336476620327508623021905073405952.0000 | 4.99 | 96 | 49869186446092573277078519432609792.0000 | 0.7667 |
| 56882041501889867672610159036727296.0000 | 5.97 | 115 | 49869186446092573277078519432609792.0000 | 0.75 |
| 51817195026983603992051887699394560.0000 | 6.96 | 134 | 49869186446092573277078519432609792.0000 | 0.75 |
| 52986004533067168453206987262394368.0000 | 8.0 | 154 | 49869186446092573277078519432609792.0000 | 0.6667 |
| 55713231995806303211455059473727488.0000 | 8.99 | 173 | 49869186446092573277078519432609792.0000 | 0.6833 |
| 54934019056070393272028897157840896.0000 | 9.97 | 192 | 49869186446092573277078519432609792.0000 | 0.7833 |
| 51427598460635967917067024161832960.0000 | 10.96 | 211 | 49869186446092573277078519432609792.0000 | 0.7167 |
| 51817198988391733394617582118502400.0000 | 12.0 | 231 | 49869186446092573277078519432609792.0000 | 0.7 |
| 57661238595993278448517617385734144.0000 | 12.99 | 250 | 49869186446092573277078519432609792.0000 | 0.7333 |
| 58050851007973422910393221744951296.0000 | 13.97 | 269 | 49869186446092573277078519432609792.0000 | 0.75 |
| 56882045463297987851803816601059328.0000 | 14.96 | 288 | 49869186446092573277078519432609792.0000 | 0.7333 |
| 56102844407786447673330663832944640.0000 | 16.0 | 308 | 49869186446092573277078519432609792.0000 | 0.75 |
| 56492437012725972792493906660950016.0000 | 16.99 | 327 | 49869186446092573277078519432609792.0000 | 0.7833 |
| 51817195026983603992051887699394560.0000 | 17.97 | 346 | 49869186446092573277078519432609792.0000 | 0.7667 |
| 48310774431549178637090014703386624.0000 | 18.96 | 365 | 49869186446092573277078519432609792.0000 | 0.7667 |
| 58440451535729188387943779701620736.0000 | 20.0 | 385 | 49869186446092573277078519432609792.0000 | 0.7667 |
| 51037990010063943634385077366947840.0000 | 20.99 | 404 | 49869186446092573277078519432609792.0000 | 0.7667 |
| 52206811400371877856493186477719552.0000 | 21.97 | 423 | 49869186446092573277078519432609792.0000 | 0.7333 |
| 54934023017478513451222554722172928.0000 | 22.96 | 442 | 49869186446092573277078519432609792.0000 | 0.75 |
| 58830048102076833686300680093958144.0000 | 24.0 | 462 | 49869186446092573277078519432609792.0000 | 0.75 |
| 52986004533067168453206987262394368.0000 | 24.99 | 481 | 49869186446092573277078519432609792.0000 | 0.7667 |
| 54544418528314618571106302346395648.0000 | 25.97 | 500 | 49869186446092573277078519432609792.0000 | 0.7667 |
| 51644037916400559103047539831603200.0000 | 26.96 | 519 | 49869186446092573277078519432609792.0000 | 0.75 |
| 56102840446378327494137006268612608.0000 | 28.0 | 539 | 49869186446092573277078519432609792.0000 | 0.7667 |
| 59998853646752268744890085237850112.0000 | 28.99 | 558 | 49869186446092573277078519432609792.0000 | 0.7833 |
| 51427598460635967917067024161832960.0000 | 29.97 | 577 | 49869186446092573277078519432609792.0000 | 0.7833 |
| 53375620906455442317648286040719360.0000 | 30.96 | 596 | 49869186446092573277078519432609792.0000 | 0.7667 |
| 58830044140668713507107022529626112.0000 | 32.0 | 616 | 49869186446092573277078519432609792.0000 | 0.75 |
| 52596404005311393752284392450949120.0000 | 32.99 | 635 | 49869186446092573277078519432609792.0000 | 0.7333 |
| 57661234634585149045951922966626304.0000 | 33.97 | 654 | 49869186446092573277078519432609792.0000 | 0.7833 |
| 50648393443716298336028176974610432.0000 | 34.96 | 673 | 49869186446092573277078519432609792.0000 | 0.7667 |
| 56882045463297987851803816601059328.0000 | 36.0 | 693 | 49869186446092573277078519432609792.0000 | 0.7667 |
| 55713231995806303211455059473727488.0000 | 36.99 | 712 | 49869186446092573277078519432609792.0000 | 0.7833 |
| 51427594499227838514501329742725120.0000 | 37.97 | 731 | 49869186446092573277078519432609792.0000 | 0.7833 |
| 52596407966719523154850086870056960.0000 | 38.96 | 750 | 49869186446092573277078519432609792.0000 | 0.7833 |
| 53505475864816321566964104575320064.0000 | 39.48 | 760 | 49869186446092573277078519432609792.0000 | 0.7833 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu118
- Datasets 2.16.1
- Tokenizers 0.15.0