videomae-base-finetuned-kinetics-finetuned-round2-v4
This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-kinetics on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3267
- Accuracy: 0.9093
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: 9e-05
- train_batch_size: 4
- eval_batch_size: 4
- 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: 2057
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.6144 | 0.09 | 188 | 0.7972 | 0.7909 |
0.2191 | 1.09 | 376 | 0.3035 | 0.8816 |
0.0656 | 2.09 | 564 | 0.4555 | 0.8665 |
0.2142 | 3.09 | 752 | 0.4683 | 0.8715 |
0.004 | 4.09 | 940 | 0.6044 | 0.8690 |
0.0013 | 5.09 | 1128 | 0.4463 | 0.8917 |
0.0007 | 6.09 | 1316 | 0.3773 | 0.9043 |
0.0007 | 7.09 | 1504 | 0.4021 | 0.9018 |
0.0006 | 8.09 | 1692 | 0.3116 | 0.9144 |
0.0006 | 9.09 | 1880 | 0.3104 | 0.9093 |
0.0005 | 10.09 | 2057 | 0.3267 | 0.9093 |
Framework versions
- Transformers 4.39.1
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 62
Model state unknown