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: 2.9364
- Accuracy: 0.1423
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: 4
- eval_batch_size: 4
- 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: 11919
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 3.1544 | 0.3324 | 3962 | 3.1157 | 0.1087 |
| 3.1054 | 1.3324 | 7924 | 2.9993 | 0.1346 |
| 2.9247 | 2.3324 | 11886 | 2.9364 | 0.1433 |
| 2.8548 | 3.0028 | 11919 | 2.9364 | 0.1423 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 2
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model's library.
Model tree for martinnz/videomae-base-finetuned-ucf101-subset
Base model
MCG-NJU/videomae-base