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_new
results: []
videomae-base-finetuned-ucf101-subset_new
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: 0.2017
- Accuracy: 0.9419
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: 4e-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: 0.2
- training_steps: 296
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.3017 | 0.1284 | 38 | 2.2057 | 0.1143 |
| 1.7529 | 1.1284 | 76 | 1.5770 | 0.4571 |
| 0.738 | 2.1284 | 114 | 0.7969 | 0.7571 |
| 0.4054 | 3.1284 | 152 | 0.4407 | 0.8143 |
| 0.1165 | 4.1284 | 190 | 0.3495 | 0.8429 |
| 0.1328 | 5.1284 | 228 | 0.1444 | 0.9571 |
| 0.0875 | 6.1284 | 266 | 0.0864 | 0.9857 |
| 0.0347 | 7.1014 | 296 | 0.0651 | 0.9857 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1