|
--- |
|
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-caer-final-4-epochs |
|
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-caer-final-4-epochs |
|
|
|
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: 1.2269 |
|
- Accuracy: 0.5443 |
|
|
|
## 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: 6 |
|
- eval_batch_size: 6 |
|
- 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: 584 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 1.3388 | 0.14 | 82 | 1.4802 | 0.3924 | |
|
| 1.1881 | 1.14 | 164 | 1.3926 | 0.3671 | |
|
| 0.9722 | 2.14 | 246 | 1.2269 | 0.5443 | |
|
| 0.6545 | 3.14 | 328 | 1.2294 | 0.4937 | |
|
| 0.5289 | 4.14 | 410 | 1.3318 | 0.4810 | |
|
| 0.2826 | 5.14 | 492 | 1.2542 | 0.4810 | |
|
| 0.2948 | 6.14 | 574 | 1.2193 | 0.5443 | |
|
| 0.1954 | 7.02 | 584 | 1.2166 | 0.5316 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.0 |
|
- Pytorch 2.1.0 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
