Prot10/vit-base-patch16-224-for-pre_evaluation

1---2license: apache-2.03base_model: google/vit-base-patch16-2244tags:5- generated_from_trainer6metrics:7- accuracy8model-index:9- name: vit-base-patch16-224-for-pre_evaluation10  results: []11---12 13<!-- This model card has been generated automatically according to the information the Trainer had access to. You14should probably proofread and complete it, then remove this comment. -->15 16# vit-base-patch16-224-for-pre_evaluation17 18This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the None dataset.19It achieves the following results on the evaluation set:20- Loss: 1.604821- Accuracy: 0.392922 23## Model description24 25More information needed26 27## Intended uses & limitations28 29More information needed30 31## Training and evaluation data32 33More information needed34 35## Training procedure36 37### Training hyperparameters38 39The following hyperparameters were used during training:40- learning_rate: 5e-0541- train_batch_size: 3242- eval_batch_size: 3243- seed: 4244- gradient_accumulation_steps: 445- total_train_batch_size: 12846- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0847- lr_scheduler_type: linear48- lr_scheduler_warmup_ratio: 0.149- num_epochs: 3050 51### Training results52 53| Training Loss | Epoch | Step | Validation Loss | Accuracy |54|:-------------:|:-----:|:----:|:---------------:|:--------:|55| 1.5774        | 0.98  | 16   | 1.5109          | 0.3022   |56| 1.4794        | 1.97  | 32   | 1.4942          | 0.3242   |57| 1.4536        | 2.95  | 48   | 1.4943          | 0.3187   |58| 1.421         | 4.0   | 65   | 1.4247          | 0.3407   |59| 1.3882        | 4.98  | 81   | 1.4944          | 0.3462   |60| 1.3579        | 5.97  | 97   | 1.4180          | 0.3571   |61| 1.2838        | 6.95  | 113  | 1.4693          | 0.3681   |62| 1.2695        | 8.0   | 130  | 1.4359          | 0.3434   |63| 1.2016        | 8.98  | 146  | 1.4656          | 0.3599   |64| 1.2087        | 9.97  | 162  | 1.4550          | 0.3379   |65| 1.206         | 10.95 | 178  | 1.5056          | 0.3516   |66| 1.1236        | 12.0  | 195  | 1.5003          | 0.3434   |67| 1.0534        | 12.98 | 211  | 1.5193          | 0.3269   |68| 1.0024        | 13.97 | 227  | 1.4890          | 0.3681   |69| 0.9767        | 14.95 | 243  | 1.5628          | 0.3434   |70| 0.9201        | 16.0  | 260  | 1.6306          | 0.3516   |71| 0.9136        | 16.98 | 276  | 1.5715          | 0.3626   |72| 0.8566        | 17.97 | 292  | 1.5966          | 0.3654   |73| 0.8273        | 18.95 | 308  | 1.6048          | 0.3929   |74| 0.7825        | 20.0  | 325  | 1.6175          | 0.3846   |75| 0.736         | 20.98 | 341  | 1.6526          | 0.3929   |76| 0.7008        | 21.97 | 357  | 1.6563          | 0.3736   |77| 0.6714        | 22.95 | 373  | 1.7319          | 0.3901   |78| 0.7039        | 24.0  | 390  | 1.6866          | 0.3929   |79| 0.628         | 24.98 | 406  | 1.7023          | 0.3791   |80| 0.6182        | 25.97 | 422  | 1.7301          | 0.3901   |81| 0.5957        | 26.95 | 438  | 1.7157          | 0.3846   |82| 0.5973        | 28.0  | 455  | 1.7478          | 0.3709   |83| 0.5655        | 28.98 | 471  | 1.7377          | 0.3736   |84| 0.5631        | 29.54 | 480  | 1.7374          | 0.3736   |85 86 87### Framework versions88 89- Transformers 4.33.190- Pytorch 2.0.1+cu11891- Datasets 2.14.592- Tokenizers 0.13.393