---
library_name: transformers
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: outputs
  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. -->

# outputs

This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Accuracy: 0.8503
- Loss: 0.6328

## 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: 128
- eval_batch_size: 128
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 512
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 50

### Training results

| Training Loss | Epoch   | Step | Accuracy | Validation Loss |
|:-------------:|:-------:|:----:|:--------:|:---------------:|
| 2.9726        | 0.9953  | 53   | 0.1321   | 2.9325          |
| 2.5775        | 1.9906  | 106  | 0.2765   | 2.4443          |
| 2.0438        | 2.9859  | 159  | 0.4247   | 1.9166          |
| 1.5681        | 4.0     | 213  | 0.5003   | 1.5682          |
| 1.3107        | 4.9953  | 266  | 0.5581   | 1.3651          |
| 1.1594        | 5.9906  | 319  | 0.6131   | 1.1995          |
| 1.0232        | 6.9859  | 372  | 0.6575   | 1.0813          |
| 0.934         | 8.0     | 426  | 0.7081   | 0.9652          |
| 0.8727        | 8.9953  | 479  | 0.7333   | 0.8802          |
| 0.7644        | 9.9906  | 532  | 0.7378   | 0.8551          |
| 0.7007        | 10.9859 | 585  | 0.7663   | 0.7584          |
| 0.6585        | 12.0    | 639  | 0.7673   | 0.7550          |
| 0.59          | 12.9953 | 692  | 0.7847   | 0.7072          |
| 0.5775        | 13.9906 | 745  | 0.7860   | 0.7042          |
| 0.5487        | 14.9859 | 798  | 0.7981   | 0.6649          |
| 0.5296        | 16.0    | 852  | 0.7958   | 0.6387          |
| 0.4866        | 16.9953 | 905  | 0.8125   | 0.6029          |
| 0.4779        | 17.9906 | 958  | 0.7935   | 0.6498          |
| 0.4418        | 18.9859 | 1011 | 0.8128   | 0.6004          |
| 0.4334        | 20.0    | 1065 | 0.8165   | 0.5995          |
| 0.4097        | 20.9953 | 1118 | 0.8326   | 0.5508          |
| 0.3947        | 21.9906 | 1171 | 0.8315   | 0.5585          |
| 0.3521        | 22.9859 | 1224 | 0.8328   | 0.5513          |
| 0.3298        | 24.0    | 1278 | 0.8319   | 0.5810          |
| 0.3216        | 24.9953 | 1331 | 0.8358   | 0.5499          |
| 0.3086        | 25.9906 | 1384 | 0.8394   | 0.5383          |
| 0.2912        | 26.9859 | 1437 | 0.8349   | 0.5845          |
| 0.2801        | 28.0    | 1491 | 0.8423   | 0.5717          |
| 0.2677        | 28.9953 | 1544 | 0.8434   | 0.5563          |
| 0.263         | 29.9906 | 1597 | 0.8434   | 0.5684          |
| 0.244         | 30.9859 | 1650 | 0.8408   | 0.5900          |
| 0.2449        | 32.0    | 1704 | 0.8330   | 0.6121          |
| 0.2276        | 32.9953 | 1757 | 0.8428   | 0.5891          |
| 0.2407        | 33.9906 | 1810 | 0.8374   | 0.6033          |
| 0.1997        | 34.9859 | 1863 | 0.8459   | 0.5969          |
| 0.2081        | 36.0    | 1917 | 0.8451   | 0.5824          |
| 0.1936        | 36.9953 | 1970 | 0.8470   | 0.5834          |
| 0.1975        | 37.9906 | 2023 | 0.8446   | 0.6106          |
| 0.1938        | 38.9859 | 2076 | 0.8433   | 0.6166          |
| 0.1874        | 40.0    | 2130 | 0.8538   | 0.5823          |
| 0.184         | 40.9953 | 2183 | 0.8434   | 0.6395          |
| 0.1584        | 41.9906 | 2236 | 0.8542   | 0.6060          |
| 0.1608        | 42.9859 | 2289 | 0.8479   | 0.6289          |
| 0.1604        | 44.0    | 2343 | 0.8523   | 0.6105          |
| 0.1398        | 44.9953 | 2396 | 0.8502   | 0.6340          |
| 0.1487        | 45.9906 | 2449 | 0.8489   | 0.6414          |
| 0.137         | 46.9859 | 2502 | 0.8484   | 0.6285          |
| 0.1223        | 48.0    | 2556 | 0.8507   | 0.6331          |
| 0.1339        | 48.9953 | 2609 | 0.8492   | 0.6295          |
| 0.1368        | 49.7653 | 2650 | 0.8503   | 0.6328          |


### Framework versions

- Transformers 4.46.0.dev0
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.20.1