metadata
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base-finetuned-kinetics
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-finetuned-kinetics-finetuned-conflab-traj-direction-rh-v10
results: []
videomae-base-finetuned-kinetics-finetuned-conflab-traj-direction-rh-v10
This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-kinetics on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4978
- Accuracy: 0.5756
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: 819
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.989 | 0.1441 | 118 | 1.8787 | 0.2670 |
| 1.3092 | 1.1441 | 236 | 1.6428 | 0.4272 |
| 1.0096 | 2.1441 | 354 | 1.4351 | 0.4757 |
| 0.604 | 3.1441 | 472 | 1.3919 | 0.5 |
| 0.2381 | 4.1441 | 590 | 1.3555 | 0.5437 |
| 0.2201 | 5.1441 | 708 | 1.3875 | 0.5777 |
| 0.1171 | 6.1355 | 819 | 1.3528 | 0.6019 |
Framework versions
- Transformers 4.41.0
- Pytorch 1.12.0+cu116
- Datasets 2.19.1
- Tokenizers 0.19.1