<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
videomae-base-finetuned-IEMOCAP_1x
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: 3.3207
- Accuracy: 0.3299
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: 4440
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.2967 | 0.1 | 445 | 1.4327 | 0.3311 |
1.0266 | 1.1 | 890 | 1.2180 | 0.4362 |
0.8349 | 2.1 | 1335 | 1.1512 | 0.4984 |
0.6229 | 3.1 | 1780 | 0.9030 | 0.6590 |
0.5852 | 4.1 | 2225 | 0.7925 | 0.7200 |
0.4507 | 5.1 | 2670 | 0.7894 | 0.7256 |
0.2965 | 6.1 | 3115 | 0.8228 | 0.7455 |
0.2977 | 7.1 | 3560 | 0.8956 | 0.7654 |
0.1292 | 8.1 | 4005 | 0.9879 | 0.7617 |
0.1829 | 9.1 | 4440 | 1.0109 | 0.7698 |
Framework versions
- Transformers 4.34.0
- Pytorch 1.12.0+cu116
- Datasets 2.14.5
- Tokenizers 0.14.1