metadata
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-finetuned-ucf101-subset
results: []
videomae-base-finetuned-ucf101-subset
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: 0.7813
- Accuracy: 0.8549
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: 1620
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.128 | 0.17 | 270 | 0.7532 | 0.7295 |
| 0.004 | 1.17 | 540 | 0.9392 | 0.7971 |
| 0.964 | 2.17 | 810 | 0.8220 | 0.8357 |
| 0.0024 | 3.17 | 1080 | 0.8664 | 0.8357 |
| 0.0051 | 4.17 | 1350 | 0.9912 | 0.7826 |
| 0.3863 | 5.17 | 1620 | 0.6859 | 0.8647 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0