metadata
library_name: transformers
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: videomae-base-videoMAE
results: []
videomae-base-videoMAE
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: 0.0563
- Accuracy: 1.0
- Precision: 1.0
- Recall: 1.0
- F1: 1.0
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: 1275
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.5203 | 1.0 | 256 | 0.4891 | 0.4667 | 0.2178 | 0.4667 | 0.2970 |
| 0.2595 | 2.0 | 512 | 0.0563 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.0315 | 3.0 | 768 | 1.3579 | 0.6667 | 0.8056 | 0.6667 | 0.6348 |
| 0.0004 | 4.0 | 1024 | 2.7397 | 0.5333 | 0.7667 | 0.5333 | 0.4296 |
| 0.0002 | 4.9805 | 1275 | 2.8840 | 0.5333 | 0.7667 | 0.5333 | 0.4296 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1