metadata
license: cc-by-nc-4.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-finetuned
results: []
videomae-base-finetuned
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: 1.6497
- Accuracy: 0.4464
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: 2
- eval_batch_size: 2
- 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: 1110
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
2.6811 | 0.1 | 112 | 2.6770 | 0.0536 |
2.5749 | 1.1 | 224 | 2.5443 | 0.1607 |
2.5502 | 2.1 | 336 | 2.3254 | 0.1786 |
2.2348 | 3.1 | 448 | 2.1844 | 0.3214 |
1.8674 | 4.1 | 560 | 2.0689 | 0.375 |
1.9905 | 5.1 | 672 | 2.2431 | 0.2679 |
1.3901 | 6.1 | 784 | 1.7099 | 0.3929 |
1.6569 | 7.1 | 896 | 1.6179 | 0.4821 |
1.3572 | 8.1 | 1008 | 1.7215 | 0.4286 |
0.8182 | 9.09 | 1110 | 1.6497 | 0.4464 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1
- Datasets 2.9.0
- Tokenizers 0.13.2