metadata
license: cc-by-nc-4.0
base_model: minhah/videomae-base-finetuned-crema-d8
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-finetuned-crema-d8-finetuned-elder-creama-d-pretuned
results: []
videomae-base-finetuned-crema-d8-finetuned-elder-creama-d-pretuned
This model is a fine-tuned version of minhah/videomae-base-finetuned-crema-d8 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6702
- Accuracy: 0.3389
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: 8
- eval_batch_size: 8
- 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: 1440
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.6909 | 0.1 | 145 | 1.6484 | 0.3352 |
| 1.5944 | 1.1 | 290 | 1.6735 | 0.2798 |
| 1.5776 | 2.1 | 435 | 1.6654 | 0.3212 |
| 1.6768 | 3.1 | 580 | 1.7330 | 0.1858 |
| 1.6108 | 4.1 | 725 | 1.6919 | 0.2504 |
| 1.5103 | 5.1 | 870 | 1.6524 | 0.2805 |
| 1.5447 | 6.1 | 1015 | 1.6767 | 0.3086 |
| 1.5237 | 7.1 | 1160 | 1.7329 | 0.2553 |
| 1.4397 | 8.1 | 1305 | 1.7293 | 0.2475 |
| 1.4544 | 9.09 | 1440 | 1.7368 | 0.2518 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2