VideoMAE-URFall_MultipleCameraFall_UnrealFallDataset
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: 0.1020
- Accuracy: 0.9717
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 12000
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.9074 | 0.1 | 1201 | 2.1151 | 0.5007 |
| 0.8521 | 1.1 | 2402 | 0.8536 | 0.7784 |
| 0.3171 | 2.1 | 3603 | 0.6226 | 0.8360 |
| 0.1523 | 3.1 | 4804 | 0.3766 | 0.8986 |
| 0.1122 | 4.1 | 6005 | 0.2525 | 0.9274 |
| 0.0261 | 5.1 | 7206 | 0.2098 | 0.9429 |
| 0.0707 | 6.1 | 8407 | 0.1900 | 0.9495 |
| 0.0038 | 7.1 | 9608 | 0.1314 | 0.9657 |
| 0.0009 | 8.1 | 10809 | 0.1177 | 0.9677 |
| 0.0011 | 9.1 | 12000 | 0.1020 | 0.9717 |
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1
- Downloads last month
- 1
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 darkviid/VideoMAE-URFall_MultipleCameraFall_UnrealFallDataset
Base model
MCG-NJU/videomae-base