Hugging Face's logo

Temo27Anas
/
vivit-b-16x2-kinetics400-ft-48192

Video Classification
Transformers
Safetensors
vivit
Generated from Trainer
Inference Endpoints
Model card Files Community
vivit-b-16x2-kinetics400-ft-48192 / README.md
Temo27Anas's picture
Temo27Anas
Model save
95781bc verified
preview code
|
raw
history blame
4.72 kB
metadata
license: mit
base_model: google/vivit-b-16x2-kinetics400
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: vivit-b-16x2-kinetics400-ft-48192
    results: []

vivit-b-16x2-kinetics400-ft-48192

This model is a fine-tuned version of google/vivit-b-16x2-kinetics400 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7001
  • Accuracy: 0.7302

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: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • training_steps: 5500

Training results

Training Loss Epoch Step Validation Loss Accuracy
1.0936 0.0202 111 1.1342 0.3280
1.0023 1.0202 222 0.9602 0.5291
1.1132 2.0202 333 1.0361 0.4603
0.9459 3.0202 444 1.0181 0.4603
0.9839 4.0202 555 0.9418 0.5767
1.0077 5.0202 666 0.9735 0.5344
1.046 6.0202 777 0.8630 0.6032
1.2237 7.0202 888 0.8513 0.6455
0.8309 8.0202 999 1.0534 0.5344
0.9748 9.0202 1110 0.8717 0.6402
0.9053 10.0202 1221 0.9555 0.5291
0.8577 11.0202 1332 0.9219 0.5820
0.9806 12.0202 1443 0.9808 0.5397
0.7957 13.0202 1554 0.9395 0.5820
0.787 14.0202 1665 0.8645 0.5979
0.8045 15.0202 1776 0.9837 0.5450
0.7793 16.0202 1887 0.9503 0.5767
0.68 17.0202 1998 0.8213 0.6667
0.8641 18.0202 2109 0.8046 0.6772
0.6624 19.0202 2220 0.7309 0.6984
0.6083 20.0202 2331 0.8542 0.6508
0.6252 21.0202 2442 0.7641 0.6878
0.6654 22.0202 2553 0.8472 0.6931
0.5135 23.0202 2664 0.7514 0.6614
0.6607 24.0202 2775 0.9482 0.5979
0.6489 25.0202 2886 1.7302 0.4497
0.5558 26.0202 2997 1.1263 0.5661
0.7327 27.0202 3108 0.7243 0.6878
0.5886 28.0202 3219 0.6610 0.7143
0.7143 29.0202 3330 0.7716 0.6667
0.5154 30.0202 3441 0.9681 0.6138
0.5505 31.0202 3552 0.9641 0.6349
0.6 32.0202 3663 0.7182 0.6984
0.6814 33.0202 3774 0.7108 0.7090
0.7797 34.0202 3885 0.7822 0.6984
0.5997 35.0202 3996 0.7895 0.6984
0.6454 36.0202 4107 0.8025 0.7090
0.5421 37.0202 4218 0.7742 0.6825
0.5026 38.0202 4329 0.6991 0.7302
0.5058 39.0202 4440 0.7855 0.6667
0.5395 40.0202 4551 0.7164 0.7196
0.5196 41.0202 4662 0.8336 0.6931
0.3783 42.0202 4773 0.7769 0.7143
0.5183 43.0202 4884 0.8074 0.6984
0.4013 44.0202 4995 0.7954 0.7196
0.5218 45.0202 5106 0.7939 0.7090
0.52 46.0202 5217 0.7603 0.7143
0.409 47.0202 5328 0.8217 0.7143
0.4437 48.0202 5439 0.8168 0.7143
0.415 49.0111 5500 0.8344 0.7196

Framework versions

  • Transformers 4.41.2
  • Pytorch 1.13.0+cu117
  • Datasets 2.20.0
  • Tokenizers 0.19.1