---
license: mit
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: MiniLM-evidence-types
  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. -->

# MiniLM-evidence-types

This model is a fine-tuned version of [microsoft/MiniLM-L12-H384-uncased](https://huggingface.co/microsoft/MiniLM-L12-H384-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.0233
- Macro f1: 0.3675
- Weighted f1: 0.6815
- Accuracy: 0.6948
- Balanced accuracy: 0.3520

## 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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Macro f1 | Weighted f1 | Accuracy | Balanced accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------:|:--------:|:-----------------:|
| 1.3773        | 1.0   | 125  | 1.2259          | 0.1981   | 0.6131      | 0.6819   | 0.2171            |
| 1.156         | 2.0   | 250  | 1.1316          | 0.2898   | 0.6207      | 0.6636   | 0.3052            |
| 1.0304        | 3.0   | 375  | 1.1232          | 0.2515   | 0.6382      | 0.6461   | 0.2741            |
| 0.8953        | 4.0   | 500  | 1.0837          | 0.2739   | 0.6950      | 0.7131   | 0.2830            |
| 0.7685        | 5.0   | 625  | 1.1225          | 0.3440   | 0.6965      | 0.7207   | 0.3420            |
| 0.6505        | 6.0   | 750  | 1.1907          | 0.3380   | 0.6814      | 0.6963   | 0.3376            |
| 0.5534        | 7.0   | 875  | 1.2381          | 0.3348   | 0.6932      | 0.7139   | 0.3296            |
| 0.4729        | 8.0   | 1000 | 1.3227          | 0.3117   | 0.6929      | 0.7161   | 0.3013            |
| 0.4205        | 9.0   | 1125 | 1.4013          | 0.3374   | 0.6793      | 0.6925   | 0.3298            |
| 0.3618        | 10.0  | 1250 | 1.4847          | 0.3623   | 0.6963      | 0.7131   | 0.3385            |
| 0.3165        | 11.0  | 1375 | 1.5459          | 0.3507   | 0.6732      | 0.6842   | 0.3387            |
| 0.2759        | 12.0  | 1500 | 1.5969          | 0.3556   | 0.6861      | 0.7032   | 0.3406            |
| 0.2474        | 13.0  | 1625 | 1.7362          | 0.3559   | 0.6795      | 0.6880   | 0.3448            |
| 0.2187        | 14.0  | 1750 | 1.8644          | 0.3460   | 0.6786      | 0.6979   | 0.3262            |
| 0.2144        | 15.0  | 1875 | 1.8729          | 0.3478   | 0.6830      | 0.7032   | 0.3289            |
| 0.1911        | 16.0  | 2000 | 1.8958          | 0.3620   | 0.6765      | 0.6834   | 0.3609            |
| 0.1858        | 17.0  | 2125 | 1.9366          | 0.3662   | 0.6815      | 0.6933   | 0.3535            |
| 0.1579        | 18.0  | 2250 | 2.0065          | 0.3624   | 0.6820      | 0.6979   | 0.3442            |
| 0.1492        | 19.0  | 2375 | 2.0467          | 0.3577   | 0.6786      | 0.6963   | 0.3373            |
| 0.1527        | 20.0  | 2500 | 2.0233          | 0.3675   | 0.6815      | 0.6948   | 0.3520            |


### Framework versions

- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1