metadata
license: cc-by-nc-4.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-finetuned-ucf101-subset-nimeshbuddhika
results: []
videomae-base-finetuned-ucf101-subset-nimeshbuddhika
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: 0.1097
- Accuracy: 0.9731
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: 2
- eval_batch_size: 2
- 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: 1500
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.4285 | 0.1 | 150 | 2.1186 | 0.2032 |
| 0.9154 | 1.1 | 300 | 1.1913 | 0.6043 |
| 0.4498 | 2.1 | 450 | 0.3770 | 0.8824 |
| 0.3012 | 3.1 | 600 | 0.3904 | 0.8663 |
| 0.1458 | 4.1 | 750 | 0.8938 | 0.7968 |
| 0.0464 | 5.1 | 900 | 0.6181 | 0.8556 |
| 0.0274 | 6.1 | 1050 | 0.7182 | 0.8075 |
| 0.0022 | 7.1 | 1200 | 0.4525 | 0.8717 |
| 0.0302 | 8.1 | 1350 | 0.3172 | 0.9091 |
| 0.0166 | 9.1 | 1500 | 0.2898 | 0.8984 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3