<!-- 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. -->
hftest-mae-finetuned-k400-subset
This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-kinetics on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4572
- Accuracy: 1.0
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: 1e-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: 250
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.287 | 1.0 | 32 | 0.9858 | 1.0 |
0.483 | 2.0 | 64 | 1.1285 | 1.0 |
0.3014 | 3.0 | 96 | 1.2834 | 1.0 |
0.1469 | 4.0 | 128 | 1.4076 | 1.0 |
0.1355 | 5.0 | 160 | 1.4415 | 1.0 |
0.1282 | 6.0 | 192 | 1.4215 | 1.0 |
0.0728 | 7.0 | 224 | 1.5009 | 1.0 |
0.0691 | 7.81 | 250 | 1.4572 | 1.0 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.1.0.dev20230627
- Datasets 2.13.1
- Tokenizers 0.13.3