<!-- 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-ssv2-finetuned-mixed-v2-label-smoothing-focalloss0.7_5-less-strict
This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-ssv2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0029
- Accuracy: 0.8743
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: 7e-05
- train_batch_size: 12
- eval_batch_size: 12
- 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: 18140
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.0008 | 0.05 | 908 | 0.0010 | 0.8276 |
0.0007 | 1.05 | 1816 | 0.0011 | 0.8223 |
0.0005 | 2.05 | 2724 | 0.0010 | 0.8725 |
0.0007 | 3.05 | 3632 | 0.0017 | 0.7469 |
0.0005 | 4.05 | 4540 | 0.0010 | 0.8366 |
0.0008 | 5.05 | 5448 | 0.0009 | 0.8492 |
0.0003 | 6.05 | 6356 | 0.0010 | 0.8654 |
0.0004 | 7.05 | 7264 | 0.0014 | 0.8600 |
0.0007 | 8.05 | 8172 | 0.0014 | 0.8438 |
0.0003 | 9.05 | 9080 | 0.0014 | 0.8671 |
0.0004 | 10.05 | 9988 | 0.0028 | 0.8321 |
0.0002 | 11.05 | 10896 | 0.0018 | 0.8752 |
0.0002 | 12.05 | 11804 | 0.0019 | 0.8645 |
0.0003 | 13.05 | 12712 | 0.0014 | 0.8752 |
0.0001 | 14.05 | 13620 | 0.0021 | 0.8609 |
0.0003 | 15.05 | 14528 | 0.0021 | 0.8627 |
0.0002 | 16.05 | 15436 | 0.0021 | 0.8779 |
0.0001 | 17.05 | 16344 | 0.0027 | 0.8797 |
0.0001 | 18.05 | 17252 | 0.0029 | 0.8725 |
0.0001 | 19.05 | 18140 | 0.0029 | 0.8743 |
Framework versions
- Transformers 4.29.1
- Pytorch 2.0.1
- Datasets 2.14.4
- Tokenizers 0.13.3