metadata
license: cc-by-nc-4.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-finetuned-ucf101-subset
results: []
videomae-base-finetuned-ucf101-subset
This model is a fine-tuned version of MCG-NJU/videomae-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8124
- Accuracy: 0.8324
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 3990
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.1012 | 0.1 | 398 | 1.9809 | 0.38 |
| 1.0416 | 1.1 | 796 | 1.6140 | 0.56 |
| 0.2096 | 2.1 | 1194 | 1.5776 | 0.66 |
| 0.7101 | 3.1 | 1592 | 1.2004 | 0.74 |
| 1.2344 | 4.1 | 1990 | 1.9621 | 0.58 |
| 0.1809 | 5.1 | 2388 | 1.6322 | 0.71 |
| 0.0011 | 6.1 | 2786 | 1.8266 | 0.71 |
| 0.0951 | 7.1 | 3184 | 1.5910 | 0.78 |
| 0.4047 | 8.1 | 3582 | 1.9999 | 0.7 |
| 0.0011 | 9.1 | 3980 | 1.5903 | 0.78 |
| 0.001 | 10.0 | 3990 | 1.5903 | 0.78 |
Framework versions
- Transformers 4.27.4
- Pytorch 1.13.1+cu116
- Datasets 2.11.0
- Tokenizers 0.13.2