---
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-finetuned-ucf101-subset
  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

This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2622
- Accuracy: 0.9226

## 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: 4
- eval_batch_size: 4
- 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: 750

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 2.1525        | 0.1   | 75   | 1.7229          | 0.5429   |
| 1.028         | 1.1   | 150  | 0.7190          | 0.7571   |
| 0.3541        | 2.1   | 225  | 0.3072          | 0.8714   |
| 0.6501        | 3.1   | 300  | 0.5646          | 0.7857   |
| 0.0448        | 4.1   | 375  | 0.4440          | 0.8571   |
| 0.0785        | 5.1   | 450  | 0.3218          | 0.9      |
| 0.0214        | 6.1   | 525  | 0.1372          | 0.9571   |
| 0.0039        | 7.1   | 600  | 0.1034          | 0.9571   |
| 0.0048        | 8.1   | 675  | 0.1595          | 0.9143   |
| 0.0052        | 9.1   | 750  | 0.1007          | 0.9571   |


### Framework versions

- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1