finetuned-Accident-MultipleLabels-Video-subset-v2-new1
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: 1.7707
- Accuracy: 0.2222
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
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 20
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
No log | 0.1 | 2 | 1.8807 | 0.2031 |
No log | 1.1 | 4 | 1.8070 | 0.2812 |
No log | 2.1 | 6 | 1.8501 | 0.25 |
No log | 3.1 | 8 | 1.9253 | 0.2812 |
1.6852 | 4.1 | 10 | 1.9988 | 0.2656 |
1.6852 | 5.1 | 12 | 2.0073 | 0.2812 |
1.6852 | 6.1 | 14 | 1.9848 | 0.2812 |
1.6852 | 7.1 | 16 | 1.9575 | 0.2812 |
1.6852 | 8.1 | 18 | 1.9472 | 0.2969 |
1.4101 | 9.1 | 20 | 1.9442 | 0.2969 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.2.0.dev20231202+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 56
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for pavitemple/finetuned-Accident-MultipleLabels-Video-subset-v2-new1
Base model
MCG-NJU/videomae-base