---
base_model: Anwaarma/Improved-xlm-attempt2
metrics:
- accuracy
tags:
- generated_from_trainer
model-index:
- name: robust-xlm2
  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. -->

# robust-xlm2

This model is a fine-tuned version of [Anwaarma/Improved-xlm-attempt2](https://huggingface.co/Anwaarma/Improved-xlm-attempt2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2054
- Accuracy: 0.94

## 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: 10

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
|:-------------:|:------:|:----:|:---------------:|:--------:|
| No log        | 0.0546 | 50   | 0.2327          | 0.9      |
| No log        | 0.1092 | 100  | 0.2348          | 0.92     |
| No log        | 0.1638 | 150  | 0.3075          | 0.9      |
| No log        | 0.2183 | 200  | 0.2929          | 0.9      |
| No log        | 0.2729 | 250  | 0.3723          | 0.89     |
| No log        | 0.3275 | 300  | 0.2431          | 0.9      |
| No log        | 0.3821 | 350  | 0.2377          | 0.91     |
| No log        | 0.4367 | 400  | 0.2088          | 0.91     |
| No log        | 0.4913 | 450  | 0.3995          | 0.89     |
| 0.2747        | 0.5459 | 500  | 0.2175          | 0.91     |
| 0.2747        | 0.6004 | 550  | 0.2226          | 0.93     |
| 0.2747        | 0.6550 | 600  | 0.2073          | 0.9      |
| 0.2747        | 0.7096 | 650  | 0.2741          | 0.9      |
| 0.2747        | 0.7642 | 700  | 0.2444          | 0.9      |
| 0.2747        | 0.8188 | 750  | 0.3467          | 0.9      |
| 0.2747        | 0.8734 | 800  | 0.2255          | 0.92     |
| 0.2747        | 0.9279 | 850  | 0.2496          | 0.9      |
| 0.2747        | 0.9825 | 900  | 0.3061          | 0.91     |
| 0.2747        | 1.0371 | 950  | 0.2751          | 0.92     |
| 0.2371        | 1.0917 | 1000 | 0.2757          | 0.93     |
| 0.2371        | 1.1463 | 1050 | 0.2745          | 0.9      |
| 0.2371        | 1.2009 | 1100 | 0.2469          | 0.94     |
| 0.2371        | 1.2555 | 1150 | 0.2018          | 0.92     |
| 0.2371        | 1.3100 | 1200 | 0.2179          | 0.94     |
| 0.2371        | 1.3646 | 1250 | 0.3163          | 0.92     |
| 0.2371        | 1.4192 | 1300 | 0.2712          | 0.92     |
| 0.2371        | 1.4738 | 1350 | 0.1603          | 0.95     |
| 0.2371        | 1.5284 | 1400 | 0.2201          | 0.94     |
| 0.2371        | 1.5830 | 1450 | 0.1814          | 0.95     |
| 0.1934        | 1.6376 | 1500 | 0.3111          | 0.91     |
| 0.1934        | 1.6921 | 1550 | 0.2185          | 0.95     |
| 0.1934        | 1.7467 | 1600 | 0.3108          | 0.93     |
| 0.1934        | 1.8013 | 1650 | 0.1857          | 0.92     |
| 0.1934        | 1.8559 | 1700 | 0.1940          | 0.93     |
| 0.1934        | 1.9105 | 1750 | 0.2189          | 0.93     |
| 0.1934        | 1.9651 | 1800 | 0.2018          | 0.94     |
| 0.1934        | 2.0197 | 1850 | 0.1617          | 0.94     |
| 0.1934        | 2.0742 | 1900 | 0.2025          | 0.94     |
| 0.1934        | 2.1288 | 1950 | 0.2668          | 0.93     |
| 0.1773        | 2.1834 | 2000 | 0.2049          | 0.94     |
| 0.1773        | 2.2380 | 2050 | 0.2101          | 0.96     |
| 0.1773        | 2.2926 | 2100 | 0.2709          | 0.92     |
| 0.1773        | 2.3472 | 2150 | 0.2168          | 0.92     |
| 0.1773        | 2.4017 | 2200 | 0.3266          | 0.91     |
| 0.1773        | 2.4563 | 2250 | 0.3344          | 0.92     |
| 0.1773        | 2.5109 | 2300 | 0.2054          | 0.94     |


### Framework versions

- Transformers 4.42.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1