metadata
license: cc-by-nc-4.0
base_model: facebook/timesformer-base-finetuned-k400
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: videomae-surf-analytics-runpod
results: []
videomae-surf-analytics-runpod
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: 0.4794
- Accuracy: 0.8340
- F1: 0.8347
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: 10
- eval_batch_size: 10
- 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: 370
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.6213 | 0.2027 | 75 | 0.7774 | 0.6971 | 0.6902 |
| 0.3269 | 1.2027 | 150 | 0.6851 | 0.7593 | 0.7562 |
| 0.2339 | 2.2027 | 225 | 0.5252 | 0.8008 | 0.7993 |
| 0.1931 | 3.2027 | 300 | 0.4942 | 0.8340 | 0.8342 |
| 0.1037 | 4.1892 | 370 | 0.4794 | 0.8340 | 0.8347 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.1+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1