metadata
library_name: transformers
base_model: uitnlp/visobert
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: visobert-human-finetune-seed-69
results: []
visobert-human-finetune-seed-69
This model is a fine-tuned version of uitnlp/visobert on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3651
- Accuracy: 0.8720
- Precision: 0.6884
- Recall: 0.7116
- F1: 0.6966
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: 0.0001
- train_batch_size: 64
- eval_batch_size: 64
- 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_steps: 500
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 346 | 0.3459 | 0.8656 | 0.6824 | 0.6750 | 0.6476 |
| 0.3399 | 2.0 | 692 | 0.3651 | 0.8720 | 0.6884 | 0.7116 | 0.6966 |
| 0.1883 | 3.0 | 1038 | 0.3686 | 0.8787 | 0.7074 | 0.6771 | 0.6913 |
| 0.1883 | 4.0 | 1384 | 0.5800 | 0.8720 | 0.7127 | 0.6519 | 0.6594 |
| 0.0913 | 5.0 | 1730 | 0.5507 | 0.8746 | 0.7029 | 0.6860 | 0.6934 |
| 0.0605 | 6.0 | 2076 | 0.6090 | 0.8757 | 0.7007 | 0.6792 | 0.6895 |
| 0.0605 | 7.0 | 2422 | 0.6178 | 0.8821 | 0.7406 | 0.6434 | 0.6830 |
Framework versions
- Transformers 4.51.1
- Pytorch 2.5.1+cu124
- Datasets 3.5.0
- Tokenizers 0.21.0