metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-finetuned-ucf101-subset-finetuned
results: []
videomae-base-finetuned-ucf101-subset-finetuned
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9147
- Accuracy: 0.7701
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: 29760
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.537 | 0.2 | 5952 | 1.8361 | 0.4807 |
| 0.8794 | 1.2 | 11904 | 1.6076 | 0.5795 |
| 0.3028 | 2.2 | 17856 | 1.5198 | 0.6318 |
| 0.2322 | 3.2 | 23808 | 0.9564 | 0.7515 |
| 0.4151 | 4.2 | 29760 | 0.9741 | 0.7595 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3