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: Timesformer_BdSLW60
results: []
Timesformer_BdSLW60
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: 0.9056
- Accuracy: 0.7750
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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 2190
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3419 | 0.4005 | 877 | 1.5632 | 0.5540 |
| 0.1291 | 1.4005 | 1754 | 1.2778 | 0.6516 |
| 0.183 | 2.1991 | 2190 | 1.3431 | 0.6296 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1