metadata
library_name: transformers
license: cc-by-nc-4.0
base_model: facebook/timesformer-base-finetuned-k400
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vivit-videomae-d1
results: []
vivit-videomae-d1
This model is a fine-tuned version of facebook/timesformer-base-finetuned-k400 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.7181
- Accuracy: 0.7829
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: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 12010
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4829 | 0.1 | 1201 | 2.2415 | 0.6216 |
| 0.2241 | 1.1 | 2402 | 1.7867 | 0.7155 |
| 0.4836 | 2.1 | 3603 | 1.7255 | 0.7142 |
| 0.0001 | 3.1 | 4804 | 1.7792 | 0.7604 |
| 0.001 | 4.1 | 6005 | 1.8104 | 0.7163 |
| 0.0001 | 5.1 | 7206 | 1.5018 | 0.7600 |
| 0.0008 | 6.1 | 8407 | 1.8564 | 0.7788 |
| 0.6079 | 7.1 | 9608 | 1.5529 | 0.7644 |
| 0.9314 | 8.1 | 10809 | 1.7200 | 0.7820 |
| 0.392 | 9.1 | 12010 | 1.7181 | 0.7829 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3