Hugging Face's logo

rshrott
/
ryan_model2

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
ryan_model2 / README.md
rshrott's picture
rshrott
🍻 cheers
1c35710 verified
preview code
|
raw
history blame contribute delete
No virus
6.73 kB
metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - image-classification
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: ryan_model2
    results: []

ryan_model2

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the beans dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7611
  • Accuracy: 0.6954

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: 0.0002
  • 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: 4
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy
1.1685 0.05 100 1.1497 0.5270
0.93 0.09 200 1.0087 0.5966
0.8567 0.14 300 1.1028 0.5607
0.9407 0.19 400 0.9464 0.6150
0.9323 0.23 500 0.9542 0.6165
0.8375 0.28 600 0.8750 0.6431
1.0136 0.32 700 0.9315 0.6077
1.0557 0.37 800 0.9124 0.6268
0.7398 0.42 900 0.8843 0.6384
0.7579 0.46 1000 0.8965 0.6338
0.8872 0.51 1100 0.8624 0.6444
0.889 0.56 1200 0.9395 0.6213
0.8863 0.6 1300 0.8294 0.6645
0.6924 0.65 1400 0.8748 0.6431
0.7978 0.7 1500 0.8624 0.6497
0.764 0.74 1600 0.8861 0.6389
0.7159 0.79 1700 0.8413 0.6504
0.7912 0.84 1800 0.8729 0.6376
0.8232 0.88 1900 0.7743 0.6776
0.7108 0.93 2000 0.8804 0.6361
0.7324 0.97 2100 0.7950 0.6743
0.5353 1.02 2200 0.9441 0.6285
0.5808 1.07 2300 0.8193 0.6670
0.5451 1.11 2400 0.9586 0.6258
0.5201 1.16 2500 0.8172 0.6745
0.5294 1.21 2600 0.8386 0.6713
0.5595 1.25 2700 0.8296 0.6622
0.488 1.3 2800 0.8134 0.6758
0.5577 1.35 2900 0.8476 0.6763
0.4918 1.39 3000 0.8701 0.6640
0.5549 1.44 3100 0.9492 0.6371
0.6421 1.48 3200 0.8248 0.6763
0.5423 1.53 3300 0.7948 0.6838
0.5654 1.58 3400 0.7697 0.6836
0.5051 1.62 3500 0.8189 0.6818
0.4797 1.67 3600 0.7995 0.6833
0.5645 1.72 3700 0.8068 0.6796
0.4865 1.76 3800 0.8162 0.6808
0.502 1.81 3900 0.7947 0.6859
0.5164 1.86 4000 0.8085 0.6801
0.4822 1.9 4100 0.7611 0.6954
0.4777 1.95 4200 0.8203 0.6823
0.5423 2.0 4300 0.7761 0.6896
0.2653 2.04 4400 0.8337 0.7004
0.2646 2.09 4500 0.9206 0.6911
0.2782 2.13 4600 0.9539 0.6924
0.2032 2.18 4700 0.8932 0.6999
0.2837 2.23 4800 0.9431 0.6914
0.3152 2.27 4900 0.9220 0.7022
0.4516 2.32 5000 0.9568 0.6904
0.2151 2.37 5100 0.9406 0.7075
0.2932 2.41 5200 0.9687 0.6904
0.3352 2.46 5300 0.9500 0.7024
0.2447 2.51 5400 0.9382 0.6982
0.371 2.55 5500 0.9664 0.6916
0.1435 2.6 5600 1.0167 0.6853
0.2489 2.65 5700 0.9714 0.6941
0.2744 2.69 5800 1.0301 0.6899
0.2139 2.74 5900 1.0056 0.6861
0.2953 2.78 6000 0.9620 0.7014
0.2672 2.83 6100 0.9992 0.6919
0.2384 2.88 6200 1.0486 0.6987
0.2759 2.92 6300 1.0390 0.6896
0.2098 2.97 6400 1.0927 0.6818
0.0427 3.02 6500 1.0394 0.6957
0.0582 3.06 6600 1.0990 0.7057
0.0494 3.11 6700 1.1617 0.6999
0.1249 3.16 6800 1.2645 0.6929
0.0786 3.2 6900 1.2227 0.7002
0.0728 3.25 7000 1.2736 0.6977
0.1319 3.29 7100 1.3114 0.6969
0.041 3.34 7200 1.3003 0.7022
0.0174 3.39 7300 1.3064 0.6997
0.0911 3.43 7400 1.3231 0.7009
0.0187 3.48 7500 1.3725 0.6979
0.1097 3.53 7600 1.3446 0.7034
0.1588 3.57 7700 1.3276 0.7060
0.0598 3.62 7800 1.3460 0.7029
0.0418 3.67 7900 1.3614 0.7027
0.0522 3.71 8000 1.3581 0.7062
0.0932 3.76 8100 1.3598 0.7072
0.092 3.81 8200 1.3826 0.7039
0.0199 3.85 8300 1.3744 0.7057
0.0251 3.9 8400 1.3652 0.7065
0.1199 3.94 8500 1.3612 0.7102
0.0629 3.99 8600 1.3649 0.7100

Framework versions

  • Transformers 4.39.1
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2