metadata
license: mit
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: multiqa_model
results: []
multiqa_model
This model is a fine-tuned version of nc33/multiqa_model on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1150
- Precision: 0.0855
- Recall: 0.0485
- F1: 0.0619
- Accuracy: 0.9626
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 327 | 0.1121 | 0.0708 | 0.0280 | 0.0402 | 0.9631 |
| 0.0786 | 2.0 | 654 | 0.1098 | 0.0531 | 0.0254 | 0.0343 | 0.9599 |
| 0.0786 | 3.0 | 981 | 0.1085 | 0.0657 | 0.0243 | 0.0354 | 0.9634 |
| 0.0681 | 4.0 | 1308 | 0.1133 | 0.0765 | 0.0453 | 0.0569 | 0.9618 |
| 0.0641 | 5.0 | 1635 | 0.1150 | 0.0855 | 0.0485 | 0.0619 | 0.9626 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2