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
results: []
videomae-base-finetuned-lift-data
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: 1.2411
- Accuracy: 0.6067
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 |
|---|---|---|---|---|
| 1.6135 | 0.1282 | 20 | 1.6537 | 0.2297 |
| 1.3333 | 1.1282 | 40 | 1.5572 | 0.2872 |
| 1.4219 | 2.1282 | 60 | 1.4465 | 0.3034 |
| 1.1874 | 3.1282 | 80 | 1.4073 | 0.3063 |
| 1.1121 | 4.1282 | 100 | 1.3247 | 0.2901 |
| 0.938 | 5.1282 | 120 | 1.2015 | 0.3255 |
| 1.1317 | 6.1282 | 140 | 1.2459 | 0.5361 |
| 1.0411 | 7.1026 | 156 | 1.1583 | 0.4683 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.0.1+cu118
- Datasets 3.0.1
- Tokenizers 0.20.1