|
--- |
|
license: cc-by-nc-4.0 |
|
base_model: abduldattijo/videomae-base-finetuned-ucf101-subset |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: videomae-base-finetuned-ucf101-subset-V4KILLER |
|
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-ucf101-subset-V4KILLER |
|
|
|
This model is a fine-tuned version of [abduldattijo/videomae-base-finetuned-ucf101-subset](https://huggingface.co./abduldattijo/videomae-base-finetuned-ucf101-subset) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2156 |
|
- Accuracy: 0.9390 |
|
|
|
## 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: 10 |
|
- eval_batch_size: 10 |
|
- 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: 1010 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.5038 | 0.1 | 102 | 0.3170 | 0.8885 | |
|
| 0.4437 | 1.1 | 204 | 0.2099 | 0.9207 | |
|
| 0.4716 | 2.1 | 306 | 0.1865 | 0.9316 | |
|
| 0.4066 | 3.1 | 408 | 0.2122 | 0.9171 | |
|
| 0.193 | 4.1 | 510 | 0.3358 | 0.8943 | |
|
| 0.1657 | 5.1 | 612 | 0.2676 | 0.9232 | |
|
| 0.1507 | 6.1 | 714 | 0.2100 | 0.9282 | |
|
| 0.3165 | 7.1 | 816 | 0.1699 | 0.9535 | |
|
| 0.0733 | 8.1 | 918 | 0.3537 | 0.9280 | |
|
| 0.0851 | 9.09 | 1010 | 0.3110 | 0.9349 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.1+cu118 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
