metadata
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-groub29-30-finetuned-SLT-subset
results: []
videomae-base-groub29-30-finetuned-SLT-subset
This model is a fine-tuned version of MCG-NJU/videomae-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.8812
- Accuracy: 0.1111
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: 4
- eval_batch_size: 4
- 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: 48
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.15 | 7 | 3.2525 | 0.0741 |
| 3.4041 | 1.15 | 14 | 3.1928 | 0.0741 |
| 3.3195 | 2.15 | 21 | 3.0810 | 0.1111 |
| 3.3195 | 3.15 | 28 | 3.0070 | 0.1111 |
| 3.1425 | 4.15 | 35 | 2.9406 | 0.1481 |
| 2.9592 | 5.15 | 42 | 2.8942 | 0.1481 |
| 2.9592 | 6.12 | 48 | 2.8812 | 0.1111 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0+cpu
- Datasets 2.1.0
- Tokenizers 0.13.3