---
license: mit
tags:
- generated_from_trainer
model-index:
- name: refinement-finetuned-mnli-1
  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. -->

# refinement-finetuned-mnli-1

This model is a fine-tuned version of [mfreihaut/refinement-finetuned-mnli-1](https://huggingface.co/mfreihaut/refinement-finetuned-mnli-1) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 6.9744

## 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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log        | 1.0   | 50   | 3.6639          |
| No log        | 2.0   | 100  | 3.1760          |
| No log        | 3.0   | 150  | 3.5147          |
| No log        | 4.0   | 200  | 7.2978          |
| No log        | 5.0   | 250  | 6.9823          |
| No log        | 6.0   | 300  | 6.1548          |
| No log        | 7.0   | 350  | 1.8893          |
| No log        | 8.0   | 400  | 3.4601          |
| No log        | 9.0   | 450  | 5.1852          |
| 0.9791        | 10.0  | 500  | 5.1913          |
| 0.9791        | 11.0  | 550  | 2.7786          |
| 0.9791        | 12.0  | 600  | 6.8241          |
| 0.9791        | 13.0  | 650  | 5.2724          |
| 0.9791        | 14.0  | 700  | 4.7973          |
| 0.9791        | 15.0  | 750  | 6.1139          |
| 0.9791        | 16.0  | 800  | 6.5590          |
| 0.9791        | 17.0  | 850  | 5.6065          |
| 0.9791        | 18.0  | 900  | 6.4056          |
| 0.9791        | 19.0  | 950  | 5.7737          |
| 0.3292        | 20.0  | 1000 | 5.6033          |
| 0.3292        | 21.0  | 1050 | 6.8969          |
| 0.3292        | 22.0  | 1100 | 6.3766          |
| 0.3292        | 23.0  | 1150 | 6.1115          |
| 0.3292        | 24.0  | 1200 | 6.3750          |
| 0.3292        | 25.0  | 1250 | 6.3604          |
| 0.3292        | 26.0  | 1300 | 6.4051          |
| 0.3292        | 27.0  | 1350 | 6.7069          |
| 0.3292        | 28.0  | 1400 | 6.3017          |
| 0.3292        | 29.0  | 1450 | 6.9539          |
| 0.2482        | 30.0  | 1500 | 6.9133          |
| 0.2482        | 31.0  | 1550 | 6.5188          |
| 0.2482        | 32.0  | 1600 | 6.7478          |
| 0.2482        | 33.0  | 1650 | 6.5621          |
| 0.2482        | 34.0  | 1700 | 6.9490          |
| 0.2482        | 35.0  | 1750 | 6.6875          |
| 0.2482        | 36.0  | 1800 | 6.7723          |
| 0.2482        | 37.0  | 1850 | 6.5755          |
| 0.2482        | 38.0  | 1900 | 6.8727          |
| 0.2482        | 39.0  | 1950 | 6.8581          |
| 0.2245        | 40.0  | 2000 | 6.9993          |
| 0.2245        | 41.0  | 2050 | 7.1120          |
| 0.2245        | 42.0  | 2100 | 7.2491          |
| 0.2245        | 43.0  | 2150 | 7.0870          |
| 0.2245        | 44.0  | 2200 | 7.3960          |
| 0.2245        | 45.0  | 2250 | 7.0658          |
| 0.2245        | 46.0  | 2300 | 7.0175          |
| 0.2245        | 47.0  | 2350 | 7.0082          |
| 0.2245        | 48.0  | 2400 | 6.9570          |
| 0.2245        | 49.0  | 2450 | 6.9720          |
| 0.2124        | 50.0  | 2500 | 6.9744          |


### Framework versions

- Transformers 4.22.2
- Pytorch 1.10.0
- Datasets 2.5.1
- Tokenizers 0.12.1