metadata
library_name: transformers
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-finetuned-soccer
results: []
videomae-base-finetuned-soccer
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: 0.9822
- Accuracy: 0.5
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: 8
- eval_batch_size: 8
- 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: 24
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 3 | 1.0756 | 0.4167 |
| No log | 2.0 | 6 | 1.0862 | 0.4167 |
| No log | 3.0 | 9 | 1.0376 | 0.5 |
| 1.126 | 4.0 | 12 | 0.9851 | 0.6667 |
| 1.126 | 5.0 | 15 | 0.9839 | 0.5 |
| 1.126 | 6.0 | 18 | 0.9849 | 0.5 |
| 0.8186 | 7.0 | 21 | 0.9838 | 0.5833 |
| 0.8186 | 8.0 | 24 | 0.9822 | 0.5 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0