| --- |
| base_model: Fsoft-AIC/videberta-base |
| tags: |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| model-index: |
| - name: videberta-base_1024 |
| results: [] |
| --- |
| |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| should probably proofread and complete it, then remove this comment. --> |
|
|
| # videberta-base_1024 |
| |
| This model is a fine-tuned version of [Fsoft-AIC/videberta-base](https://huggingface.co/Fsoft-AIC/videberta-base) on the None dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.5931 |
| - Accuracy: 0.75 |
| |
| ## 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: 0.0003 |
| - train_batch_size: 2 |
| - eval_batch_size: 2 |
| - seed: 42 |
| - gradient_accumulation_steps: 8 |
| - total_train_batch_size: 16 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: linear |
| - lr_scheduler_warmup_ratio: 0.18 |
| - training_steps: 1000 |
| - mixed_precision_training: Native AMP |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | |
| |:-------------:|:-----:|:----:|:---------------:|:--------:| |
| | 0.5982 | 0.1 | 50 | 0.6297 | 0.75 | |
| | 0.5505 | 0.21 | 100 | 0.5696 | 0.75 | |
| | 0.5838 | 0.31 | 150 | 0.5629 | 0.75 | |
| | 0.5925 | 0.41 | 200 | 0.5931 | 0.75 | |
| | 0.7003 | 0.52 | 250 | 0.5931 | 0.75 | |
| | 0.606 | 0.62 | 300 | 0.5931 | 0.75 | |
| | 0.6744 | 0.72 | 350 | 0.5931 | 0.75 | |
| | 0.6448 | 0.83 | 400 | 0.5931 | 0.75 | |
| | 0.7365 | 0.93 | 450 | 0.5931 | 0.75 | |
| | 0.6083 | 1.03 | 500 | 0.5931 | 0.75 | |
| | 0.6217 | 1.14 | 550 | 0.5931 | 0.75 | |
| | 0.642 | 1.24 | 600 | 0.5931 | 0.75 | |
| | 0.6433 | 1.34 | 650 | 0.5931 | 0.75 | |
| | 0.7497 | 1.45 | 700 | 0.5931 | 0.75 | |
| | 0.6385 | 1.55 | 750 | 0.5931 | 0.75 | |
| | 0.6581 | 1.65 | 800 | 0.5931 | 0.75 | |
| | 0.6201 | 1.76 | 850 | 0.5931 | 0.75 | |
| | 0.6424 | 1.86 | 900 | 0.5931 | 0.75 | |
| | 0.619 | 1.96 | 950 | 0.5931 | 0.75 | |
| | 0.6807 | 2.07 | 1000 | 0.5931 | 0.75 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 4.35.0.dev0 |
| - Pytorch 2.0.0 |
| - Datasets 2.1.0 |
| - Tokenizers 0.14.1 |
| |
