metadata
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: []
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: 0.0480
- Accuracy: 0.9857
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: 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: 600
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.2995 | 0.06 | 38 | 2.1143 | 0.3 |
| 1.6428 | 1.06 | 76 | 1.5030 | 0.3429 |
| 0.6261 | 2.06 | 114 | 0.8121 | 0.6286 |
| 0.4044 | 3.06 | 152 | 0.4910 | 0.7714 |
| 0.3236 | 4.06 | 190 | 0.4558 | 0.8714 |
| 0.1865 | 5.06 | 228 | 0.6773 | 0.8 |
| 0.1479 | 6.06 | 266 | 0.1813 | 0.9571 |
| 0.0418 | 7.06 | 304 | 0.1312 | 0.9714 |
| 0.0718 | 8.06 | 342 | 0.2473 | 0.9286 |
| 0.0596 | 9.06 | 380 | 0.1378 | 0.9714 |
| 0.0079 | 10.06 | 418 | 0.0308 | 0.9857 |
| 0.0134 | 11.06 | 456 | 0.0329 | 1.0 |
| 0.0083 | 12.06 | 494 | 0.0310 | 1.0 |
| 0.0394 | 13.06 | 532 | 0.0543 | 0.9714 |
| 0.004 | 14.06 | 570 | 0.0492 | 0.9857 |
| 0.0043 | 15.05 | 600 | 0.0480 | 0.9857 |
Framework versions
- Transformers 4.31.0
- Pytorch 1.10.0+cu113
- Datasets 2.14.4
- Tokenizers 0.13.3