metadata
license: apache-2.0
base_model: Liberty-L/Multiple_Choice
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Multiple_Choice
results: []
Multiple_Choice
This model is a fine-tuned version of Liberty-L/Multiple_Choice on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.5071
- Accuracy: 0.5279
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-08
- train_batch_size: 6
- eval_batch_size: 6
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 24
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3178 | 1.0 | 1059 | 1.4420 | 0.5265 |
| 0.2244 | 2.0 | 2118 | 1.5162 | 0.5265 |
| 0.5162 | 3.0 | 3177 | 1.5164 | 0.5272 |
| 0.6076 | 4.0 | 4237 | 1.5090 | 0.5279 |
| 0.6052 | 5.0 | 5295 | 1.5071 | 0.5279 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0