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-timesformer-d1
results: []
vivit-timesformer-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: 1.4413
- Accuracy: 0.7876
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 |
|---|---|---|---|---|
| 1.4177 | 0.1 | 1201 | 1.6974 | 0.6286 |
| 1.3055 | 1.1 | 2402 | 1.7565 | 0.6570 |
| 0.8467 | 2.1 | 3603 | 1.7238 | 0.6763 |
| 0.0019 | 3.1 | 4804 | 1.6070 | 0.6877 |
| 1.0625 | 4.1 | 6005 | 1.6971 | 0.6939 |
| 0.0012 | 5.1 | 7206 | 1.8048 | 0.7005 |
| 0.8867 | 6.1 | 8407 | 1.6243 | 0.7337 |
| 1.7533 | 7.1 | 9608 | 1.3174 | 0.7661 |
| 0.8878 | 8.1 | 10809 | 1.5021 | 0.7828 |
| 0.0005 | 9.1 | 12010 | 1.4413 | 0.7876 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3