metadata
library_name: transformers
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: cricketshot-predictor
results: []
cricketshot-predictor
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: 1.5308
- Accuracy: 0.6605
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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 6250
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.6249 | 0.1 | 625 | 1.7054 | 0.3542 |
| 1.3162 | 1.1 | 1250 | 1.6491 | 0.4539 |
| 1.575 | 2.1 | 1875 | 1.4801 | 0.4834 |
| 1.4376 | 3.1 | 2500 | 1.4187 | 0.5351 |
| 0.935 | 4.1 | 3125 | 1.5090 | 0.5129 |
| 0.8346 | 5.1 | 3750 | 1.2971 | 0.6089 |
| 0.8204 | 6.1 | 4375 | 1.7406 | 0.5609 |
| 0.2341 | 7.1 | 5000 | 1.5780 | 0.6236 |
| 0.8821 | 8.1 | 5625 | 1.6022 | 0.6310 |
| 0.2366 | 9.1 | 6250 | 1.5308 | 0.6605 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.5.1
- Datasets 3.3.2
- Tokenizers 0.21.0