metadata
library_name: transformers
base_model: MCG-NJU/videomae-base
tags:
- generated_from_trainer
model-index:
- name: videomae-base-readminds-assignment
results: []
videomae-base-readminds-assignment
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: 1.5827
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 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: 100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.5236 | 0.12 | 12 | 1.4575 |
| 1.1957 | 1.12 | 24 | 1.4403 |
| 0.7669 | 2.12 | 36 | 1.4573 |
| 0.4632 | 3.12 | 48 | 1.5034 |
| 0.299 | 4.12 | 60 | 1.5987 |
| 0.1672 | 5.12 | 72 | 1.5975 |
| 0.0682 | 6.12 | 84 | 1.5670 |
| 0.0324 | 7.12 | 96 | 1.5827 |
| 0.0155 | 8.04 | 100 | 1.5827 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.0