metadata
library_name: transformers
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
model-index:
- name: mvit_v2_s_Kinetics400_transf_b_rwf2000
results: []
mvit_v2_s_Kinetics400_transf_b_rwf2000
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3624
- Accuracy: 0.905
- F1: 0.9050
- Precision: 0.9054
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 1900
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision |
|---|---|---|---|---|---|---|
| 0.4714 | 0.1 | 190 | 0.4167 | 0.8562 | 0.8553 | 0.8659 |
| 0.4534 | 1.1 | 380 | 0.3293 | 0.8938 | 0.8928 | 0.9081 |
| 0.2061 | 2.1 | 570 | 0.2627 | 0.9187 | 0.9185 | 0.9241 |
| 0.142 | 3.1 | 760 | 0.2556 | 0.9375 | 0.9375 | 0.9375 |
| 0.4586 | 4.1 | 950 | 0.3117 | 0.9375 | 0.9373 | 0.9419 |
| 0.3396 | 5.1 | 1140 | 0.4245 | 0.9125 | 0.9120 | 0.9220 |
| 0.593 | 6.1 | 1330 | 0.2777 | 0.9375 | 0.9374 | 0.9400 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.0.1+cu118
- Datasets 2.21.0
- Tokenizers 0.19.1