metadata
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base-finetuned-kinetics
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-finetuned-kinetics-finetuned-right-hand-conflab-v7
results: []
videomae-base-finetuned-kinetics-finetuned-right-hand-conflab-v7
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: 1.6074
- Accuracy: 0.6195
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-06
- 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: 1755
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3647 | 0.0672 | 118 | 1.5877 | 0.5971 |
| 0.2213 | 1.0672 | 236 | 1.6058 | 0.6117 |
| 0.19 | 2.0672 | 354 | 1.6941 | 0.5728 |
| 0.061 | 3.0672 | 472 | 1.7403 | 0.5922 |
| 0.0512 | 4.0672 | 590 | 1.7683 | 0.5971 |
| 0.0393 | 5.0672 | 708 | 1.7420 | 0.6262 |
| 0.0219 | 6.0672 | 826 | 1.7741 | 0.6019 |
| 0.0363 | 7.0672 | 944 | 1.7825 | 0.6117 |
| 0.0457 | 8.0672 | 1062 | 1.8103 | 0.6019 |
| 0.0201 | 9.0672 | 1180 | 1.8303 | 0.6019 |
| 0.0325 | 10.0672 | 1298 | 1.8135 | 0.6165 |
| 0.049 | 11.0672 | 1416 | 1.8364 | 0.6214 |
| 0.0077 | 12.0672 | 1534 | 1.8431 | 0.6165 |
| 0.0088 | 13.0672 | 1652 | 1.8508 | 0.6165 |
| 0.0818 | 14.0587 | 1755 | 1.8490 | 0.6117 |
Framework versions
- Transformers 4.41.0
- Pytorch 1.12.0+cu116
- Datasets 2.19.1
- Tokenizers 0.19.1