metadata
library_name: transformers
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base
tags:
- generated_from_trainer
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: 0.8688
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- 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: 370
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.3516 | 0.1027 | 38 | 2.2951 |
| 2.1851 | 1.1027 | 76 | 2.1559 |
| 1.9452 | 2.1027 | 114 | 1.9531 |
| 1.6471 | 3.1027 | 152 | 1.6395 |
| 1.255 | 4.1027 | 190 | 1.3609 |
| 1.0922 | 5.1027 | 228 | 1.1511 |
| 0.7825 | 6.1027 | 266 | 1.0092 |
| 0.7033 | 7.1027 | 304 | 0.9361 |
| 0.5924 | 8.1027 | 342 | 0.8911 |
| 0.616 | 9.0757 | 370 | 0.8688 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.1.0+cu121
- Tokenizers 0.19.1