metadata
library_name: transformers
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-diving48-finetuned
results: []
videomae-diving48-finetuned
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.3810
- Accuracy: 0.0788
- Top5 Accuracy: 0.3677
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: 0.0003
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 15965
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Top5 Accuracy |
|---|---|---|---|---|---|
| 3.7503 | 0.2 | 3193 | 3.6511 | 0.0471 | 0.2444 |
| 3.5645 | 1.2 | 6386 | 3.5746 | 0.0672 | 0.2826 |
| 3.7438 | 2.2 | 9579 | 3.5204 | 0.0834 | 0.3457 |
| 3.4429 | 3.2 | 12772 | 3.4543 | 0.0797 | 0.3387 |
| 3.5896 | 4.2 | 15965 | 3.3810 | 0.0788 | 0.3677 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.1.0+cu118
- Datasets 3.6.0
- Tokenizers 0.21.1