metadata
base_model: hf-tiny-model-private/tiny-random-VideoMAEModel
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: VideoMAE-tiny-finetuned-ucf101-subset
results: []
VideoMAE-tiny-finetuned-ucf101-subset
This model is a fine-tuned version of hf-tiny-model-private/tiny-random-VideoMAEModel on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.2723
- Accuracy: 0.1455
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: 148
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.3099 | 0.26 | 38 | 2.2978 | 0.0893 |
| 2.3305 | 1.26 | 76 | 2.2971 | 0.0893 |
| 2.2972 | 2.26 | 114 | 2.2965 | 0.0893 |
| 2.3006 | 3.23 | 148 | 2.2967 | 0.0893 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2