videomae-base-finetuned-pupilscreen-subset-v2
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: 0.4616
- Accuracy: 0.8182
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 OptimizerNames.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: 76
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6581 | 0.2632 | 20 | 0.7273 | 0.4603 |
| 0.7527 | 1.2632 | 40 | 0.5567 | 0.7778 |
| 0.3166 | 2.2632 | 60 | 0.4519 | 0.8095 |
| 0.2841 | 3.2105 | 76 | 0.5590 | 0.7143 |
Framework versions
- Transformers 4.48.2
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 8
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for ajm1099/videomae-base-finetuned-pupilscreen-subset-v2
Base model
MCG-NJU/videomae-base