---
library_name: transformers
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vivit-videomae-d2
  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. -->

# vivit-videomae-d2

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: 2.3393
- Accuracy: 0.3190

## 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: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 6650
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 2.5973        | 0.1   | 665  | 2.5600          | 0.0937   |
| 2.5359        | 1.1   | 1330 | 2.4382          | 0.1767   |
| 2.0681        | 2.1   | 1995 | 2.4175          | 0.2154   |
| 2.2863        | 3.1   | 2660 | 2.3472          | 0.2166   |
| 2.1409        | 4.1   | 3325 | 2.4337          | 0.2049   |
| 2.1223        | 5.1   | 3990 | 2.3414          | 0.2821   |
| 2.041         | 6.1   | 4655 | 2.2474          | 0.2054   |
| 1.4722        | 7.1   | 5320 | 2.3306          | 0.2925   |
| 1.9404        | 8.1   | 5985 | 2.4100          | 0.2897   |
| 1.5395        | 9.1   | 6650 | 2.3393          | 0.3190   |


### Framework versions

- Transformers 4.46.2
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3