videomae-base-finetuned-IEMOCAP_3
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: 1.3701
- Accuracy: 0.3179
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: 4370
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.3648 | 0.1 | 438 | 1.3661 | 0.3746 |
1.3188 | 1.1 | 876 | 1.3436 | 0.3215 |
1.2826 | 2.1 | 1314 | 1.3651 | 0.3215 |
1.2141 | 3.1 | 1752 | 1.3170 | 0.3759 |
1.2555 | 4.1 | 2190 | 1.3018 | 0.4053 |
1.2422 | 5.1 | 2628 | 1.3036 | 0.3565 |
1.2776 | 6.1 | 3066 | 1.2650 | 0.3921 |
1.2074 | 7.1 | 3504 | 1.2655 | 0.3971 |
1.2354 | 8.1 | 3942 | 1.2542 | 0.3952 |
1.0865 | 9.1 | 4370 | 1.2498 | 0.4078 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.0
- Tokenizers 0.13.3
- Downloads last month
- 5
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.