metadata
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-groub23-24-finetuned-SLT-subset
results: []
videomae-base-groub23-24-finetuned-SLT-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: 3.2558
- Accuracy: 0.1463
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: 4
- eval_batch_size: 4
- 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: 80
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 3.8674 | 0.14 | 11 | 3.6587 | 0.0488 |
| 3.7787 | 1.14 | 22 | 3.5948 | 0.1220 |
| 3.6605 | 2.14 | 33 | 3.5183 | 0.1220 |
| 3.6081 | 3.14 | 44 | 3.4284 | 0.1463 |
| 3.5543 | 4.14 | 55 | 3.3461 | 0.1463 |
| 3.4024 | 5.14 | 66 | 3.2865 | 0.1220 |
| 3.3301 | 6.14 | 77 | 3.2581 | 0.1463 |
| 3.3935 | 7.04 | 80 | 3.2558 | 0.1463 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0+cpu
- Datasets 2.1.0
- Tokenizers 0.13.3