---
license: mit
tags:
- generated_from_trainer
model-index:
- name: roberta-base-mnli_IndE
  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. -->

# roberta-base-mnli_IndE

This model is a fine-tuned version of [WillHeld/roberta-base-mnli](https://huggingface.co/WillHeld/roberta-base-mnli) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7633
- Acc: 0.8517

## 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: 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: 5

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Acc    |
|:-------------:|:-----:|:-----:|:---------------:|:------:|
| 0.3903        | 0.17  | 2000  | 0.4502          | 0.8359 |
| 0.3776        | 0.33  | 4000  | 0.4488          | 0.8378 |
| 0.3694        | 0.5   | 6000  | 0.4400          | 0.8408 |
| 0.3679        | 0.67  | 8000  | 0.4412          | 0.8395 |
| 0.3584        | 0.83  | 10000 | 0.4079          | 0.8514 |
| 0.3618        | 1.0   | 12000 | 0.4326          | 0.8433 |
| 0.2582        | 1.17  | 14000 | 0.4738          | 0.8459 |
| 0.2603        | 1.33  | 16000 | 0.4921          | 0.8468 |
| 0.2608        | 1.5   | 18000 | 0.4542          | 0.8498 |
| 0.2591        | 1.67  | 20000 | 0.4709          | 0.8483 |
| 0.263         | 1.83  | 22000 | 0.4955          | 0.8466 |
| 0.2611        | 2.0   | 24000 | 0.4829          | 0.8513 |
| 0.1802        | 2.17  | 26000 | 0.5470          | 0.8493 |
| 0.1819        | 2.33  | 28000 | 0.5523          | 0.8503 |
| 0.1847        | 2.5   | 30000 | 0.5160          | 0.8519 |
| 0.1886        | 2.67  | 32000 | 0.5229          | 0.8521 |
| 0.1877        | 2.83  | 34000 | 0.5024          | 0.8528 |
| 0.1839        | 3.0   | 36000 | 0.5456          | 0.8536 |
| 0.1322        | 3.17  | 38000 | 0.6997          | 0.8492 |
| 0.1385        | 3.33  | 40000 | 0.6212          | 0.8534 |
| 0.1326        | 3.5   | 42000 | 0.6629          | 0.8529 |
| 0.1355        | 3.67  | 44000 | 0.6448          | 0.8516 |
| 0.1332        | 3.83  | 46000 | 0.6411          | 0.8544 |
| 0.1372        | 4.0   | 48000 | 0.6574          | 0.8526 |
| 0.1056        | 4.17  | 50000 | 0.7427          | 0.8529 |
| 0.1053        | 4.33  | 52000 | 0.7466          | 0.8518 |
| 0.1062        | 4.5   | 54000 | 0.7734          | 0.8536 |
| 0.1056        | 4.67  | 56000 | 0.7623          | 0.8518 |
| 0.1072        | 4.83  | 58000 | 0.7633          | 0.8517 |


### Framework versions

- Transformers 4.24.0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1
- Tokenizers 0.12.1