metadata
library_name: transformers
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-finetuned-lift-data-resize
results: []
videomae-base-finetuned-lift-data-resize
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: 0.8146
- Accuracy: 0.7681
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: 156
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.5758 | 0.1282 | 20 | 1.6619 | 0.2901 |
| 1.3067 | 1.1282 | 40 | 1.6048 | 0.2990 |
| 1.3787 | 2.1282 | 60 | 1.4723 | 0.3181 |
| 1.1642 | 3.1282 | 80 | 1.4191 | 0.3004 |
| 1.1172 | 4.1282 | 100 | 1.2374 | 0.3196 |
| 0.8982 | 5.1282 | 120 | 1.0099 | 0.5655 |
| 0.915 | 6.1282 | 140 | 0.9540 | 0.5891 |
| 0.7809 | 7.1026 | 156 | 0.9189 | 0.5714 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.0.1+cu118
- Datasets 3.0.1
- Tokenizers 0.20.1