hf_images_model1 / README.md
moreover18's picture
End of training
ee409d0
|
raw
history blame
6.02 kB
metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - generated_from_trainer
datasets:
  - image_folder
metrics:
  - accuracy
model-index:
  - name: hf_images_model1
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: image_folder
          type: image_folder
          config: default
          split: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9178265524625268

hf_images_model1

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

  • Loss: 0.2058
  • Accuracy: 0.9178

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: 5e-05
  • 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: 3

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.7057 0.04 10 0.7027 0.4644
0.6808 0.09 20 0.6615 0.6590
0.6278 0.13 30 0.5969 0.7441
0.5674 0.17 40 0.5134 0.8183
0.4761 0.21 50 0.4146 0.875
0.3777 0.26 60 0.3362 0.8796
0.303 0.3 70 0.2906 0.8854
0.2385 0.34 80 0.2694 0.8937
0.2452 0.39 90 0.2515 0.9012
0.2771 0.43 100 0.2441 0.9050
0.2332 0.47 110 0.2510 0.8975
0.2495 0.51 120 0.2398 0.9052
0.2611 0.56 130 0.2384 0.9063
0.2292 0.6 140 0.2931 0.8865
0.2518 0.64 150 0.2537 0.8994
0.211 0.69 160 0.2619 0.8953
0.2514 0.73 170 0.2236 0.9090
0.2272 0.77 180 0.2254 0.9085
0.2263 0.81 190 0.2141 0.9181
0.2524 0.86 200 0.2038 0.9194
0.2024 0.9 210 0.2038 0.9165
0.2355 0.94 220 0.2215 0.9103
0.2431 0.99 230 0.2116 0.9178
0.1921 1.03 240 0.2105 0.9111
0.1845 1.07 250 0.2107 0.9117
0.1838 1.11 260 0.2070 0.9119
0.1824 1.16 270 0.2110 0.9130
0.1706 1.2 280 0.2177 0.9154
0.1826 1.24 290 0.2058 0.9160
0.1816 1.28 300 0.2081 0.9176
0.1901 1.33 310 0.2187 0.9149
0.2112 1.37 320 0.2107 0.9181
0.22 1.41 330 0.2065 0.9173
0.2105 1.46 340 0.2090 0.9170
0.2016 1.5 350 0.2044 0.9141
0.2055 1.54 360 0.2029 0.9173
0.1507 1.58 370 0.2103 0.9192
0.1705 1.63 380 0.1960 0.9184
0.1605 1.67 390 0.2070 0.9154
0.2011 1.71 400 0.2096 0.9160
0.1832 1.76 410 0.2023 0.9176
0.1756 1.8 420 0.2005 0.9189
0.1874 1.84 430 0.2050 0.9135
0.1497 1.88 440 0.1936 0.9240
0.1891 1.93 450 0.1991 0.9208
0.1595 1.97 460 0.2014 0.9194
0.2028 2.01 470 0.1994 0.9184
0.1794 2.06 480 0.2068 0.9146
0.1404 2.1 490 0.2046 0.9181
0.1615 2.14 500 0.1955 0.9243
0.1555 2.18 510 0.2027 0.9202
0.151 2.23 520 0.1893 0.9261
0.1676 2.27 530 0.2046 0.9192
0.1744 2.31 540 0.1967 0.9218
0.1644 2.36 550 0.1970 0.9226
0.2048 2.4 560 0.1930 0.9243
0.1649 2.44 570 0.1986 0.9218
0.1435 2.48 580 0.1956 0.9213
0.1598 2.53 590 0.1986 0.9197
0.1513 2.57 600 0.2020 0.9173
0.1769 2.61 610 0.2005 0.9170
0.1488 2.66 620 0.2033 0.9197
0.1636 2.7 630 0.1964 0.9216
0.1583 2.74 640 0.1985 0.9189
0.1294 2.78 650 0.2109 0.9151
0.1585 2.83 660 0.2000 0.9186
0.1531 2.87 670 0.2078 0.9178
0.1294 2.91 680 0.1891 0.9272
0.1612 2.96 690 0.2058 0.9178

Framework versions

  • Transformers 4.33.0
  • Pytorch 2.0.0
  • Datasets 2.1.0
  • Tokenizers 0.13.3