metadata
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: videomae-base-finetuned-ElderReact-Sadness12
results: []
videomae-base-finetuned-ElderReact-Sadness12
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: 0.5360
- F1: 0.0133
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: 16
- eval_batch_size: 16
- 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: 380
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.5312 | 0.1 | 39 | 0.5029 | 0.0 |
| 0.4889 | 1.1 | 78 | 0.5069 | 0.0 |
| 0.4707 | 2.1 | 117 | 0.5262 | 0.0 |
| 0.4758 | 3.1 | 156 | 0.5055 | 0.0 |
| 0.5164 | 4.1 | 195 | 0.5525 | 0.0118 |
| 0.4793 | 5.1 | 234 | 0.5121 | 0.0 |
| 0.4872 | 6.1 | 273 | 0.5168 | 0.0 |
| 0.3846 | 7.1 | 312 | 0.5490 | 0.0 |
| 0.3796 | 8.1 | 351 | 0.5376 | 0.0 |
| 0.3853 | 9.08 | 380 | 0.5240 | 0.0 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2