metadata
license: cc-by-nc-4.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-finetuned-ucf101-subset-SBDtoy
results: []
videomae-base-finetuned-ucf101-subset-SBDtoy
This model is a fine-tuned version of MCG-NJU/videomae-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4955
- Accuracy: 1.0
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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.1 | 2 | 0.6590 | 0.5 |
| No log | 1.1 | 4 | 0.5487 | 0.5 |
| No log | 2.1 | 6 | 0.4955 | 1.0 |
| No log | 3.1 | 8 | 0.5463 | 0.5 |
| 0.4651 | 4.1 | 10 | 0.5728 | 0.5 |
| 0.4651 | 5.1 | 12 | 0.5635 | 0.5 |
| 0.4651 | 6.1 | 14 | 0.6040 | 0.5 |
| 0.4651 | 7.1 | 16 | 0.6417 | 0.5 |
| 0.4651 | 8.1 | 18 | 0.6531 | 0.5 |
| 0.122 | 9.1 | 20 | 0.6686 | 0.5 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.0+cu117
- Datasets 2.18.0
- Tokenizers 0.13.3