|
--- |
|
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-lh-v1 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# videomae-base-finetuned-kinetics-finetuned-conflab-traj-direction-lh-v1 |
|
|
|
This model is a fine-tuned version of [MCG-NJU/videomae-base-finetuned-kinetics](https://huggingface.co/MCG-NJU/videomae-base-finetuned-kinetics) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.3609 |
|
- Accuracy: 0.6096 |
|
|
|
## 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: 728 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:------:|:----:|:---------------:|:--------:| |
|
| 1.6395 | 0.1442 | 105 | 1.6255 | 0.3723 | |
|
| 1.4009 | 1.1442 | 210 | 1.4288 | 0.5053 | |
|
| 1.0856 | 2.1442 | 315 | 1.2735 | 0.5745 | |
|
| 0.6975 | 3.1442 | 420 | 1.2629 | 0.6064 | |
|
| 0.3574 | 4.1442 | 525 | 1.2030 | 0.6170 | |
|
| 0.1654 | 5.1442 | 630 | 1.2649 | 0.6436 | |
|
| 0.1179 | 6.1346 | 728 | 1.2939 | 0.6330 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.0 |
|
- Pytorch 1.12.0+cu116 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
