Hugging Face's logo

ydmeira
/
beit-finetuned-pokemon

Transformers
PyTorch
TensorBoard
beit
generated_from_trainer
Inference Endpoints
Model card Files Metrics Community
beit-finetuned-pokemon / README.md
ydmeira's picture
ydmeira
update model card README.md
de54407
preview code
|
raw history blame
4.36 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
model-index:
  - name: beit-finetuned-pokemon
    results: []

beit-finetuned-pokemon

This model is a fine-tuned version of ydmeira/beit-finetuned-pokemon on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0222
  • Mean Iou: 0.4964
  • Mean Accuracy: 0.9927
  • Overall Accuracy: 0.9927
  • Per Category Iou: [0.0, 0.9927382211696605]
  • Per Category Accuracy: [nan, 0.9927382211696605]

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: 6e-05
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 2

Training results

Training Loss Epoch Step Validation Loss Mean Iou Mean Accuracy Overall Accuracy Per Category Iou Per Category Accuracy
0.044 0.11 500 0.0430 0.4929 0.9857 0.9857 [0.0, 0.9857017551704262] [nan, 0.9857017551704262]
0.0495 0.21 1000 0.0345 0.4960 0.9920 0.9920 [0.0, 0.9920118130744071] [nan, 0.9920118130744071]
0.0382 0.32 1500 0.0399 0.4947 0.9894 0.9894 [0.0, 0.9893992290428889] [nan, 0.9893992290428889]
0.0361 0.43 2000 0.0311 0.4963 0.9926 0.9926 [0.0, 0.9925511589842341] [nan, 0.9925511589842341]
0.04 0.53 2500 0.0722 0.4920 0.9840 0.9840 [0.0, 0.9839730680037156] [nan, 0.9839730680037156]
0.0308 0.64 3000 0.0319 0.4977 0.9954 0.9954 [0.0, 0.9954462252146663] [nan, 0.9954462252146663]
0.0391 0.75 3500 0.1028 0.4837 0.9674 0.9674 [0.0, 0.9673708120597321] [nan, 0.9673708120597321]
0.0425 0.85 4000 0.0330 0.4973 0.9946 0.9946 [0.0, 0.9946091381677958] [nan, 0.9946091381677958]
0.0321 0.96 4500 0.0259 0.4963 0.9925 0.9925 [0.0, 0.9925195785900393] [nan, 0.9925195785900393]
0.031 1.07 5000 0.0270 0.4965 0.9930 0.9930 [0.0, 0.9930111407071547] [nan, 0.9930111407071547]
0.0281 1.17 5500 0.0367 0.4933 0.9866 0.9866 [0.0, 0.9865881607581373] [nan, 0.9865881607581373]
0.0325 1.28 6000 0.0327 0.4940 0.9880 0.9880 [0.0, 0.9879893562856097] [nan, 0.9879893562856097]
0.0253 1.39 6500 0.0237 0.4968 0.9937 0.9937 [0.0, 0.9936538460005984] [nan, 0.9936538460005984]
0.0258 1.49 7000 0.0241 0.4964 0.9928 0.9928 [0.0, 0.9927783017073394] [nan, 0.9927783017073394]
0.0266 1.6 7500 0.0234 0.4962 0.9924 0.9924 [0.0, 0.9923954115635184] [nan, 0.9923954115635184]
0.0223 1.71 8000 0.0264 0.4964 0.9928 0.9928 [0.0, 0.9928421413266322] [nan, 0.9928421413266322]
0.0212 1.81 8500 0.0235 0.4960 0.9920 0.9920 [0.0, 0.9920402354291824] [nan, 0.9920402354291824]
0.0196 1.92 9000 0.0222 0.4964 0.9927 0.9927 [0.0, 0.9927382211696605] [nan, 0.9927382211696605]

Framework versions

  • Transformers 4.21.2
  • Pytorch 1.12.1+cu113
  • Datasets 2.4.0
  • Tokenizers 0.12.1