---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: aift-model
  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. -->

# aift-model

This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 3.1256
- Accuracy Thresh: 0.9115

## 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: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: tpu
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy Thresh |
|:-------------:|:-----:|:----:|:---------------:|:---------------:|
| 2.2235        | 1.0   | 584  | 1.2682          | 0.7171          |
| 1.1638        | 2.0   | 1168 | 1.1630          | 0.8122          |
| 0.8698        | 3.0   | 1752 | 1.3732          | 0.8635          |
| 0.7107        | 4.0   | 2336 | 1.5609          | 0.8770          |
| 0.542         | 5.0   | 2920 | 1.9944          | 0.8927          |
| 0.3618        | 6.0   | 3504 | 2.2950          | 0.9012          |
| 0.2842        | 7.0   | 4088 | 2.5621          | 0.9018          |
| 0.2358        | 8.0   | 4672 | 2.8400          | 0.9079          |
| 0.2135        | 9.0   | 5256 | 3.1208          | 0.9111          |
| 0.1731        | 10.0  | 5840 | 3.1256          | 0.9115          |


### Framework versions

- Transformers 4.37.1
- Pytorch 2.0.0+cu118
- Datasets 2.16.1
- Tokenizers 0.15.0