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: abcd
results: []
abcd
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: 0.7002
- Accuracy: 0.7887
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: 4
- eval_batch_size: 4
- 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: 552
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.1325 | 0.1685 | 93 | 1.0676 | 0.5568 |
| 0.738 | 1.1685 | 186 | 1.2091 | 0.5499 |
| 0.6397 | 2.1685 | 279 | 1.2484 | 0.6116 |
| 0.4395 | 3.1685 | 372 | 1.0140 | 0.6427 |
| 0.3098 | 4.1685 | 465 | 0.9757 | 0.6830 |
| 0.1016 | 5.1576 | 552 | 0.7179 | 0.7589 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu118
- Datasets 3.3.2
- Tokenizers 0.21.1