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-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: 0.4448
- Accuracy: 0.8452
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: 16
- eval_batch_size: 16
- 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: 148
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.3498 | 0.1284 | 19 | 2.0894 | 0.2143 |
| 1.9304 | 1.1284 | 38 | 1.5131 | 0.4857 |
| 1.099 | 2.1284 | 57 | 0.8322 | 0.6857 |
| 0.4725 | 3.1284 | 76 | 0.5528 | 0.7714 |
| 0.3629 | 4.1284 | 95 | 0.3822 | 0.8571 |
| 0.196 | 5.1284 | 114 | 0.3011 | 0.9143 |
| 0.1357 | 6.1284 | 133 | 0.2539 | 0.9143 |
| 0.0847 | 7.1014 | 148 | 0.1923 | 0.9429 |
Framework versions
- Transformers 4.48.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0