vivit-b-16x2-kinetics400-0511-training-original_mediapipe
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: 0.8679
- Accuracy: 0.87
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: 1
- eval_batch_size: 1
- 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: 3000
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.9371 | 0.1 | 300 | 1.3835 | 0.55 |
0.3638 | 1.1 | 600 | 0.7150 | 0.82 |
0.0015 | 2.1 | 900 | 0.6783 | 0.86 |
0.0033 | 3.1 | 1200 | 0.7366 | 0.83 |
0.0003 | 4.1 | 1500 | 0.8180 | 0.84 |
0.0004 | 5.1 | 1800 | 0.8207 | 0.84 |
0.0003 | 6.1 | 2100 | 0.8953 | 0.86 |
0.003 | 7.1 | 2400 | 0.9083 | 0.84 |
0.0025 | 8.1 | 2700 | 0.9555 | 0.82 |
0.0003 | 9.1 | 3000 | 0.8679 | 0.87 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 37
Model state unknown