---
license: apache-2.0
base_model: microsoft/swinv2-small-patch4-window16-256
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: swinv2-small-patch4-window16-256-mineral
  results:
  - task:
      name: Image Classification
      type: image-classification
    dataset:
      name: imagefolder
      type: imagefolder
      config: default
      split: train
      args: default
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.24
---

<!-- 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. -->

# swinv2-small-patch4-window16-256-mineral

This model is a fine-tuned version of [microsoft/swinv2-small-patch4-window16-256](https://huggingface.co/microsoft/swinv2-small-patch4-window16-256) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 4.9130
- Accuracy: 0.24

## 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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 500

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
|:-------------:|:------:|:----:|:---------------:|:--------:|
| 5.6941        | 0.96   | 18   | 5.6921          | 0.005    |
| 5.6886        | 1.97   | 37   | 5.6825          | 0.005    |
| 5.6735        | 2.99   | 56   | 5.6691          | 0.005    |
| 5.6521        | 4.0    | 75   | 5.6549          | 0.0033   |
| 5.6394        | 4.96   | 93   | 5.6416          | 0.0033   |
| 5.6078        | 5.97   | 112  | 5.6278          | 0.0033   |
| 5.5743        | 6.99   | 131  | 5.6128          | 0.0017   |
| 5.5509        | 8.0    | 150  | 5.5918          | 0.0017   |
| 5.5115        | 8.96   | 168  | 5.5696          | 0.0067   |
| 5.4411        | 9.97   | 187  | 5.5440          | 0.01     |
| 5.3335        | 10.99  | 206  | 5.5135          | 0.0167   |
| 5.2413        | 12.0   | 225  | 5.4640          | 0.0217   |
| 5.1738        | 12.96  | 243  | 5.4084          | 0.0333   |
| 5.0222        | 13.97  | 262  | 5.3321          | 0.045    |
| 4.8594        | 14.99  | 281  | 5.2485          | 0.0533   |
| 4.7441        | 16.0   | 300  | 5.1509          | 0.065    |
| 4.5946        | 16.96  | 318  | 5.0701          | 0.0717   |
| 4.3382        | 17.97  | 337  | 4.9767          | 0.0867   |
| 4.2008        | 18.99  | 356  | 4.8622          | 0.105    |
| 4.0563        | 20.0   | 375  | 4.7726          | 0.1033   |
| 3.8064        | 20.96  | 393  | 4.6898          | 0.115    |
| 3.5584        | 21.97  | 412  | 4.5997          | 0.125    |
| 3.3377        | 22.99  | 431  | 4.4848          | 0.1367   |
| 3.1119        | 24.0   | 450  | 4.4052          | 0.1533   |
| 2.8686        | 24.96  | 468  | 4.3705          | 0.15     |
| 2.7649        | 25.97  | 487  | 4.2980          | 0.165    |
| 2.5698        | 26.99  | 506  | 4.2363          | 0.1767   |
| 2.4344        | 28.0   | 525  | 4.1733          | 0.1767   |
| 2.2186        | 28.96  | 543  | 4.1783          | 0.1733   |
| 2.0227        | 29.97  | 562  | 4.1306          | 0.18     |
| 1.9153        | 30.99  | 581  | 4.0948          | 0.175    |
| 1.7363        | 32.0   | 600  | 4.0612          | 0.1783   |
| 1.6171        | 32.96  | 618  | 4.0209          | 0.185    |
| 1.4865        | 33.97  | 637  | 4.0194          | 0.185    |
| 1.3194        | 34.99  | 656  | 3.9881          | 0.205    |
| 1.2811        | 36.0   | 675  | 3.9862          | 0.215    |
| 1.1703        | 36.96  | 693  | 3.9905          | 0.2033   |
| 1.114         | 37.97  | 712  | 3.9514          | 0.2133   |
| 0.9645        | 38.99  | 731  | 3.9678          | 0.2067   |
| 0.8976        | 40.0   | 750  | 3.9874          | 0.2167   |
| 0.8147        | 40.96  | 768  | 3.9257          | 0.2083   |
| 0.7239        | 41.97  | 787  | 3.9394          | 0.2217   |
| 0.7732        | 42.99  | 806  | 3.9473          | 0.215    |
| 0.7009        | 44.0   | 825  | 3.9461          | 0.215    |
| 0.5945        | 44.96  | 843  | 4.0207          | 0.2133   |
| 0.555         | 45.97  | 862  | 4.0353          | 0.2083   |
| 0.5241        | 46.99  | 881  | 4.0232          | 0.2167   |
| 0.4789        | 48.0   | 900  | 4.0026          | 0.22     |
| 0.4284        | 48.96  | 918  | 4.0031          | 0.22     |
| 0.4701        | 49.97  | 937  | 4.0572          | 0.215    |
| 0.4501        | 50.99  | 956  | 4.0877          | 0.215    |
| 0.3966        | 52.0   | 975  | 4.0207          | 0.2167   |
| 0.3564        | 52.96  | 993  | 4.0827          | 0.215    |
| 0.3472        | 53.97  | 1012 | 4.0902          | 0.235    |
| 0.3731        | 54.99  | 1031 | 4.0953          | 0.2417   |
| 0.3161        | 56.0   | 1050 | 4.1660          | 0.2033   |
| 0.3352        | 56.96  | 1068 | 4.1153          | 0.2217   |
| 0.3317        | 57.97  | 1087 | 4.1096          | 0.2167   |
| 0.294         | 58.99  | 1106 | 4.1856          | 0.215    |
| 0.3299        | 60.0   | 1125 | 4.1476          | 0.2233   |
| 0.2847        | 60.96  | 1143 | 4.2046          | 0.225    |
| 0.2924        | 61.97  | 1162 | 4.1568          | 0.2183   |
| 0.2818        | 62.99  | 1181 | 4.1519          | 0.2333   |
| 0.2698        | 64.0   | 1200 | 4.2275          | 0.215    |
| 0.2579        | 64.96  | 1218 | 4.1626          | 0.235    |
| 0.2597        | 65.97  | 1237 | 4.2277          | 0.2217   |
| 0.2443        | 66.99  | 1256 | 4.1929          | 0.2367   |
| 0.2532        | 68.0   | 1275 | 4.2779          | 0.2233   |
| 0.2305        | 68.96  | 1293 | 4.2441          | 0.2367   |
| 0.2423        | 69.97  | 1312 | 4.2583          | 0.2217   |
| 0.222         | 70.99  | 1331 | 4.2935          | 0.23     |
| 0.2096        | 72.0   | 1350 | 4.2714          | 0.23     |
| 0.1776        | 72.96  | 1368 | 4.2348          | 0.225    |
| 0.2009        | 73.97  | 1387 | 4.2930          | 0.2283   |
| 0.2087        | 74.99  | 1406 | 4.3071          | 0.235    |
| 0.1818        | 76.0   | 1425 | 4.2960          | 0.235    |
| 0.2236        | 76.96  | 1443 | 4.2910          | 0.24     |
| 0.1802        | 77.97  | 1462 | 4.2896          | 0.25     |
| 0.2037        | 78.99  | 1481 | 4.3314          | 0.245    |
| 0.1912        | 80.0   | 1500 | 4.2612          | 0.2333   |
| 0.2305        | 80.96  | 1518 | 4.2790          | 0.2367   |
| 0.2188        | 81.97  | 1537 | 4.3069          | 0.2217   |
| 0.1639        | 82.99  | 1556 | 4.3539          | 0.2183   |
| 0.1741        | 84.0   | 1575 | 4.3211          | 0.225    |
| 0.1937        | 84.96  | 1593 | 4.3576          | 0.2117   |
| 0.1712        | 85.97  | 1612 | 4.3434          | 0.2233   |
| 0.1665        | 86.99  | 1631 | 4.3349          | 0.2117   |
| 0.1846        | 88.0   | 1650 | 4.4170          | 0.235    |
| 0.1827        | 88.96  | 1668 | 4.3350          | 0.23     |
| 0.1591        | 89.97  | 1687 | 4.3397          | 0.215    |
| 0.1508        | 90.99  | 1706 | 4.3273          | 0.2317   |
| 0.1808        | 92.0   | 1725 | 4.3315          | 0.2317   |
| 0.17          | 92.96  | 1743 | 4.2760          | 0.24     |
| 0.14          | 93.97  | 1762 | 4.3144          | 0.2333   |
| 0.1734        | 94.99  | 1781 | 4.3667          | 0.2283   |
| 0.1593        | 96.0   | 1800 | 4.3903          | 0.225    |
| 0.1523        | 96.96  | 1818 | 4.3314          | 0.24     |
| 0.1599        | 97.97  | 1837 | 4.4115          | 0.23     |
| 0.1352        | 98.99  | 1856 | 4.3626          | 0.2467   |
| 0.1406        | 100.0  | 1875 | 4.3555          | 0.2383   |
| 0.1486        | 100.96 | 1893 | 4.3116          | 0.2383   |
| 0.149         | 101.97 | 1912 | 4.3894          | 0.23     |
| 0.115         | 102.99 | 1931 | 4.3755          | 0.2233   |
| 0.1301        | 104.0  | 1950 | 4.3765          | 0.2317   |
| 0.1429        | 104.96 | 1968 | 4.4027          | 0.235    |
| 0.1209        | 105.97 | 1987 | 4.3803          | 0.2317   |
| 0.1287        | 106.99 | 2006 | 4.3235          | 0.2467   |
| 0.1318        | 108.0  | 2025 | 4.3484          | 0.24     |
| 0.1136        | 108.96 | 2043 | 4.3977          | 0.225    |
| 0.1326        | 109.97 | 2062 | 4.3978          | 0.2267   |
| 0.1415        | 110.99 | 2081 | 4.3214          | 0.2383   |
| 0.1229        | 112.0  | 2100 | 4.3699          | 0.2467   |
| 0.1004        | 112.96 | 2118 | 4.3828          | 0.2583   |
| 0.0961        | 113.97 | 2137 | 4.3564          | 0.2517   |
| 0.1132        | 114.99 | 2156 | 4.3384          | 0.2533   |
| 0.1166        | 116.0  | 2175 | 4.4152          | 0.2417   |
| 0.1193        | 116.96 | 2193 | 4.3634          | 0.2417   |
| 0.096         | 117.97 | 2212 | 4.3826          | 0.235    |
| 0.1158        | 118.99 | 2231 | 4.4524          | 0.235    |
| 0.099         | 120.0  | 2250 | 4.4978          | 0.2233   |
| 0.1065        | 120.96 | 2268 | 4.4124          | 0.24     |
| 0.129         | 121.97 | 2287 | 4.3814          | 0.235    |
| 0.1047        | 122.99 | 2306 | 4.3663          | 0.2467   |
| 0.101         | 124.0  | 2325 | 4.5113          | 0.23     |
| 0.1076        | 124.96 | 2343 | 4.4553          | 0.2367   |
| 0.1135        | 125.97 | 2362 | 4.4351          | 0.23     |
| 0.1066        | 126.99 | 2381 | 4.4874          | 0.235    |
| 0.1256        | 128.0  | 2400 | 4.4635          | 0.2333   |
| 0.0932        | 128.96 | 2418 | 4.4576          | 0.2383   |
| 0.1189        | 129.97 | 2437 | 4.5770          | 0.2267   |
| 0.1096        | 130.99 | 2456 | 4.4921          | 0.2317   |
| 0.0791        | 132.0  | 2475 | 4.5090          | 0.2267   |
| 0.1152        | 132.96 | 2493 | 4.4572          | 0.2417   |
| 0.1264        | 133.97 | 2512 | 4.5109          | 0.25     |
| 0.1009        | 134.99 | 2531 | 4.5236          | 0.2283   |
| 0.0956        | 136.0  | 2550 | 4.4783          | 0.245    |
| 0.0919        | 136.96 | 2568 | 4.5484          | 0.2467   |
| 0.1042        | 137.97 | 2587 | 4.5423          | 0.2433   |
| 0.1039        | 138.99 | 2606 | 4.4918          | 0.245    |
| 0.094         | 140.0  | 2625 | 4.5456          | 0.2467   |
| 0.1056        | 140.96 | 2643 | 4.5219          | 0.245    |
| 0.0918        | 141.97 | 2662 | 4.5255          | 0.245    |
| 0.0877        | 142.99 | 2681 | 4.4923          | 0.2383   |
| 0.105         | 144.0  | 2700 | 4.5352          | 0.235    |
| 0.0892        | 144.96 | 2718 | 4.4715          | 0.245    |
| 0.0963        | 145.97 | 2737 | 4.5060          | 0.245    |
| 0.095         | 146.99 | 2756 | 4.5593          | 0.2433   |
| 0.0997        | 148.0  | 2775 | 4.5804          | 0.24     |
| 0.0839        | 148.96 | 2793 | 4.5917          | 0.23     |
| 0.0924        | 149.97 | 2812 | 4.5931          | 0.2267   |
| 0.0781        | 150.99 | 2831 | 4.5784          | 0.2317   |
| 0.0986        | 152.0  | 2850 | 4.6546          | 0.2283   |
| 0.0823        | 152.96 | 2868 | 4.5985          | 0.2367   |
| 0.0887        | 153.97 | 2887 | 4.6148          | 0.23     |
| 0.0671        | 154.99 | 2906 | 4.6397          | 0.2333   |
| 0.0897        | 156.0  | 2925 | 4.5834          | 0.235    |
| 0.093         | 156.96 | 2943 | 4.5397          | 0.2433   |
| 0.0973        | 157.97 | 2962 | 4.5532          | 0.2333   |
| 0.1001        | 158.99 | 2981 | 4.5827          | 0.24     |
| 0.0884        | 160.0  | 3000 | 4.5728          | 0.235    |
| 0.084         | 160.96 | 3018 | 4.6542          | 0.235    |
| 0.0902        | 161.97 | 3037 | 4.6366          | 0.2417   |
| 0.0944        | 162.99 | 3056 | 4.5957          | 0.2383   |
| 0.0828        | 164.0  | 3075 | 4.6521          | 0.23     |
| 0.0812        | 164.96 | 3093 | 4.6761          | 0.2367   |
| 0.0817        | 165.97 | 3112 | 4.6272          | 0.225    |
| 0.07          | 166.99 | 3131 | 4.6536          | 0.2433   |
| 0.0746        | 168.0  | 3150 | 4.5671          | 0.245    |
| 0.0782        | 168.96 | 3168 | 4.5915          | 0.24     |
| 0.0677        | 169.97 | 3187 | 4.6373          | 0.2433   |
| 0.0626        | 170.99 | 3206 | 4.6723          | 0.2583   |
| 0.0697        | 172.0  | 3225 | 4.6817          | 0.245    |
| 0.077         | 172.96 | 3243 | 4.6793          | 0.23     |
| 0.068         | 173.97 | 3262 | 4.7110          | 0.2417   |
| 0.0875        | 174.99 | 3281 | 4.7012          | 0.2433   |
| 0.0787        | 176.0  | 3300 | 4.7113          | 0.2367   |
| 0.0779        | 176.96 | 3318 | 4.6998          | 0.24     |
| 0.0823        | 177.97 | 3337 | 4.7092          | 0.24     |
| 0.0685        | 178.99 | 3356 | 4.6763          | 0.245    |
| 0.0698        | 180.0  | 3375 | 4.7181          | 0.2567   |
| 0.0924        | 180.96 | 3393 | 4.7151          | 0.2483   |
| 0.084         | 181.97 | 3412 | 4.7231          | 0.2417   |
| 0.0508        | 182.99 | 3431 | 4.6856          | 0.2317   |
| 0.0637        | 184.0  | 3450 | 4.7041          | 0.2417   |
| 0.06          | 184.96 | 3468 | 4.7205          | 0.24     |
| 0.0659        | 185.97 | 3487 | 4.7251          | 0.2433   |
| 0.0842        | 186.99 | 3506 | 4.7215          | 0.23     |
| 0.0733        | 188.0  | 3525 | 4.7068          | 0.24     |
| 0.0647        | 188.96 | 3543 | 4.7594          | 0.2367   |
| 0.0569        | 189.97 | 3562 | 4.7831          | 0.2233   |
| 0.0883        | 190.99 | 3581 | 4.7212          | 0.235    |
| 0.0622        | 192.0  | 3600 | 4.6878          | 0.2417   |
| 0.057         | 192.96 | 3618 | 4.6654          | 0.2467   |
| 0.0654        | 193.97 | 3637 | 4.6358          | 0.2517   |
| 0.0868        | 194.99 | 3656 | 4.6621          | 0.2333   |
| 0.0789        | 196.0  | 3675 | 4.6985          | 0.2333   |
| 0.0657        | 196.96 | 3693 | 4.6636          | 0.2567   |
| 0.0648        | 197.97 | 3712 | 4.7698          | 0.2467   |
| 0.0635        | 198.99 | 3731 | 4.7226          | 0.2417   |
| 0.0637        | 200.0  | 3750 | 4.7481          | 0.245    |
| 0.0665        | 200.96 | 3768 | 4.7789          | 0.2483   |
| 0.0799        | 201.97 | 3787 | 4.7014          | 0.235    |
| 0.064         | 202.99 | 3806 | 4.7528          | 0.2417   |
| 0.0772        | 204.0  | 3825 | 4.7401          | 0.2383   |
| 0.0438        | 204.96 | 3843 | 4.7678          | 0.2417   |
| 0.0766        | 205.97 | 3862 | 4.7180          | 0.2367   |
| 0.0687        | 206.99 | 3881 | 4.7058          | 0.2433   |
| 0.0801        | 208.0  | 3900 | 4.7584          | 0.235    |
| 0.0772        | 208.96 | 3918 | 4.7304          | 0.2433   |
| 0.0663        | 209.97 | 3937 | 4.6940          | 0.2367   |
| 0.0529        | 210.99 | 3956 | 4.6940          | 0.235    |
| 0.0568        | 212.0  | 3975 | 4.7333          | 0.235    |
| 0.0697        | 212.96 | 3993 | 4.6673          | 0.2367   |
| 0.0394        | 213.97 | 4012 | 4.6733          | 0.245    |
| 0.0625        | 214.99 | 4031 | 4.7383          | 0.225    |
| 0.0588        | 216.0  | 4050 | 4.7674          | 0.24     |
| 0.0594        | 216.96 | 4068 | 4.6873          | 0.2417   |
| 0.0451        | 217.97 | 4087 | 4.6718          | 0.2433   |
| 0.047         | 218.99 | 4106 | 4.7146          | 0.2283   |
| 0.0445        | 220.0  | 4125 | 4.7174          | 0.2283   |
| 0.0746        | 220.96 | 4143 | 4.6702          | 0.2367   |
| 0.0697        | 221.97 | 4162 | 4.6462          | 0.2367   |
| 0.0562        | 222.99 | 4181 | 4.6956          | 0.2333   |
| 0.047         | 224.0  | 4200 | 4.7278          | 0.2383   |
| 0.0612        | 224.96 | 4218 | 4.7307          | 0.235    |
| 0.0625        | 225.97 | 4237 | 4.6670          | 0.2567   |
| 0.0739        | 226.99 | 4256 | 4.7110          | 0.2317   |
| 0.0637        | 228.0  | 4275 | 4.7039          | 0.22     |
| 0.0461        | 228.96 | 4293 | 4.7119          | 0.2267   |
| 0.0506        | 229.97 | 4312 | 4.7099          | 0.23     |
| 0.0412        | 230.99 | 4331 | 4.6714          | 0.2317   |
| 0.057         | 232.0  | 4350 | 4.6921          | 0.2367   |
| 0.0402        | 232.96 | 4368 | 4.7545          | 0.2317   |
| 0.058         | 233.97 | 4387 | 4.7573          | 0.225    |
| 0.0661        | 234.99 | 4406 | 4.6800          | 0.2283   |
| 0.0613        | 236.0  | 4425 | 4.6533          | 0.2433   |
| 0.0462        | 236.96 | 4443 | 4.6748          | 0.2283   |
| 0.0494        | 237.97 | 4462 | 4.6874          | 0.23     |
| 0.0643        | 238.99 | 4481 | 4.7291          | 0.2333   |
| 0.0422        | 240.0  | 4500 | 4.7088          | 0.23     |
| 0.0376        | 240.96 | 4518 | 4.7422          | 0.225    |
| 0.0696        | 241.97 | 4537 | 4.8011          | 0.2283   |
| 0.0609        | 242.99 | 4556 | 4.8013          | 0.2217   |
| 0.0637        | 244.0  | 4575 | 4.7603          | 0.225    |
| 0.0529        | 244.96 | 4593 | 4.7895          | 0.2233   |
| 0.0603        | 245.97 | 4612 | 4.7639          | 0.235    |
| 0.0365        | 246.99 | 4631 | 4.7285          | 0.2433   |
| 0.0732        | 248.0  | 4650 | 4.7252          | 0.2283   |
| 0.0709        | 248.96 | 4668 | 4.7620          | 0.23     |
| 0.0485        | 249.97 | 4687 | 4.7529          | 0.2367   |
| 0.0449        | 250.99 | 4706 | 4.8006          | 0.2417   |
| 0.0506        | 252.0  | 4725 | 4.8028          | 0.2333   |
| 0.0455        | 252.96 | 4743 | 4.7778          | 0.2367   |
| 0.0594        | 253.97 | 4762 | 4.7439          | 0.2383   |
| 0.0551        | 254.99 | 4781 | 4.8069          | 0.2367   |
| 0.0435        | 256.0  | 4800 | 4.8171          | 0.2383   |
| 0.042         | 256.96 | 4818 | 4.7961          | 0.2383   |
| 0.0403        | 257.97 | 4837 | 4.8172          | 0.2383   |
| 0.0524        | 258.99 | 4856 | 4.8537          | 0.23     |
| 0.0461        | 260.0  | 4875 | 4.7698          | 0.2283   |
| 0.05          | 260.96 | 4893 | 4.8058          | 0.2483   |
| 0.0545        | 261.97 | 4912 | 4.8398          | 0.2333   |
| 0.0405        | 262.99 | 4931 | 4.8228          | 0.2367   |
| 0.0615        | 264.0  | 4950 | 4.8395          | 0.2367   |
| 0.0381        | 264.96 | 4968 | 4.8231          | 0.2233   |
| 0.0464        | 265.97 | 4987 | 4.8180          | 0.2367   |
| 0.058         | 266.99 | 5006 | 4.8744          | 0.235    |
| 0.0553        | 268.0  | 5025 | 4.8866          | 0.2367   |
| 0.0505        | 268.96 | 5043 | 4.8534          | 0.24     |
| 0.049         | 269.97 | 5062 | 4.8702          | 0.2333   |
| 0.0444        | 270.99 | 5081 | 4.8715          | 0.2267   |
| 0.0457        | 272.0  | 5100 | 4.8274          | 0.225    |
| 0.0546        | 272.96 | 5118 | 4.8441          | 0.225    |
| 0.0378        | 273.97 | 5137 | 4.8229          | 0.225    |
| 0.0374        | 274.99 | 5156 | 4.8053          | 0.2217   |
| 0.047         | 276.0  | 5175 | 4.8619          | 0.2333   |
| 0.0526        | 276.96 | 5193 | 4.8793          | 0.2417   |
| 0.0503        | 277.97 | 5212 | 4.9060          | 0.2283   |
| 0.0414        | 278.99 | 5231 | 4.8687          | 0.24     |
| 0.0361        | 280.0  | 5250 | 4.8537          | 0.24     |
| 0.0449        | 280.96 | 5268 | 4.8204          | 0.2383   |
| 0.0596        | 281.97 | 5287 | 4.8030          | 0.2367   |
| 0.0494        | 282.99 | 5306 | 4.8060          | 0.2483   |
| 0.0483        | 284.0  | 5325 | 4.7878          | 0.235    |
| 0.0338        | 284.96 | 5343 | 4.8254          | 0.2383   |
| 0.0319        | 285.97 | 5362 | 4.8264          | 0.2383   |
| 0.0454        | 286.99 | 5381 | 4.8426          | 0.2367   |
| 0.0409        | 288.0  | 5400 | 4.8198          | 0.2483   |
| 0.0435        | 288.96 | 5418 | 4.8339          | 0.2367   |
| 0.0498        | 289.97 | 5437 | 4.8387          | 0.225    |
| 0.0447        | 290.99 | 5456 | 4.8342          | 0.23     |
| 0.0402        | 292.0  | 5475 | 4.8496          | 0.2333   |
| 0.0366        | 292.96 | 5493 | 4.8671          | 0.2317   |
| 0.0369        | 293.97 | 5512 | 4.8366          | 0.2467   |
| 0.0361        | 294.99 | 5531 | 4.7992          | 0.2433   |
| 0.0448        | 296.0  | 5550 | 4.8486          | 0.2267   |
| 0.055         | 296.96 | 5568 | 4.8979          | 0.2267   |
| 0.0585        | 297.97 | 5587 | 4.8660          | 0.2367   |
| 0.0477        | 298.99 | 5606 | 4.8717          | 0.2433   |
| 0.0247        | 300.0  | 5625 | 4.8838          | 0.2283   |
| 0.047         | 300.96 | 5643 | 4.8248          | 0.2383   |
| 0.0608        | 301.97 | 5662 | 4.8330          | 0.2367   |
| 0.0417        | 302.99 | 5681 | 4.8236          | 0.2317   |
| 0.0494        | 304.0  | 5700 | 4.8070          | 0.2383   |
| 0.0316        | 304.96 | 5718 | 4.8213          | 0.2267   |
| 0.0421        | 305.97 | 5737 | 4.8634          | 0.2317   |
| 0.0411        | 306.99 | 5756 | 4.8770          | 0.24     |
| 0.0404        | 308.0  | 5775 | 4.9030          | 0.2383   |
| 0.0397        | 308.96 | 5793 | 4.9433          | 0.2383   |
| 0.053         | 309.97 | 5812 | 4.9301          | 0.2333   |
| 0.0303        | 310.99 | 5831 | 4.8961          | 0.2283   |
| 0.0369        | 312.0  | 5850 | 4.8560          | 0.2433   |
| 0.0423        | 312.96 | 5868 | 4.9177          | 0.225    |
| 0.0343        | 313.97 | 5887 | 4.8928          | 0.2233   |
| 0.0216        | 314.99 | 5906 | 4.8958          | 0.23     |
| 0.0287        | 316.0  | 5925 | 4.8803          | 0.235    |
| 0.0286        | 316.96 | 5943 | 4.8615          | 0.23     |
| 0.0304        | 317.97 | 5962 | 4.8736          | 0.2317   |
| 0.0486        | 318.99 | 5981 | 4.8825          | 0.2233   |
| 0.0404        | 320.0  | 6000 | 4.8618          | 0.2283   |
| 0.0439        | 320.96 | 6018 | 4.8848          | 0.23     |
| 0.0428        | 321.97 | 6037 | 4.8975          | 0.2267   |
| 0.0498        | 322.99 | 6056 | 4.8614          | 0.2383   |
| 0.0314        | 324.0  | 6075 | 4.8718          | 0.235    |
| 0.0334        | 324.96 | 6093 | 4.9021          | 0.2383   |
| 0.0431        | 325.97 | 6112 | 4.8973          | 0.2283   |
| 0.0473        | 326.99 | 6131 | 4.8671          | 0.24     |
| 0.0348        | 328.0  | 6150 | 4.9050          | 0.2333   |
| 0.0718        | 328.96 | 6168 | 4.8869          | 0.2417   |
| 0.0387        | 329.97 | 6187 | 4.8552          | 0.245    |
| 0.0335        | 330.99 | 6206 | 4.8932          | 0.2367   |
| 0.0355        | 332.0  | 6225 | 4.9195          | 0.245    |
| 0.0407        | 332.96 | 6243 | 4.9163          | 0.2333   |
| 0.0471        | 333.97 | 6262 | 4.8860          | 0.225    |
| 0.0334        | 334.99 | 6281 | 4.8943          | 0.235    |
| 0.0301        | 336.0  | 6300 | 4.9223          | 0.2367   |
| 0.0281        | 336.96 | 6318 | 4.9101          | 0.2433   |
| 0.0305        | 337.97 | 6337 | 4.8897          | 0.24     |
| 0.0505        | 338.99 | 6356 | 4.9290          | 0.2417   |
| 0.024         | 340.0  | 6375 | 4.9442          | 0.2333   |
| 0.0504        | 340.96 | 6393 | 4.9183          | 0.2367   |
| 0.0259        | 341.97 | 6412 | 4.8832          | 0.235    |
| 0.0313        | 342.99 | 6431 | 4.8958          | 0.2317   |
| 0.0293        | 344.0  | 6450 | 4.8979          | 0.2433   |
| 0.0427        | 344.96 | 6468 | 4.9055          | 0.2417   |
| 0.0399        | 345.97 | 6487 | 4.8957          | 0.2433   |
| 0.0273        | 346.99 | 6506 | 4.8989          | 0.24     |
| 0.0388        | 348.0  | 6525 | 4.9087          | 0.2367   |
| 0.0306        | 348.96 | 6543 | 4.9264          | 0.2283   |
| 0.0411        | 349.97 | 6562 | 4.9219          | 0.2367   |
| 0.0394        | 350.99 | 6581 | 4.8998          | 0.24     |
| 0.0507        | 352.0  | 6600 | 4.9304          | 0.2317   |
| 0.0263        | 352.96 | 6618 | 4.9232          | 0.23     |
| 0.0395        | 353.97 | 6637 | 4.9241          | 0.2367   |
| 0.0394        | 354.99 | 6656 | 4.9263          | 0.2433   |
| 0.0391        | 356.0  | 6675 | 4.9273          | 0.26     |
| 0.0647        | 356.96 | 6693 | 4.9034          | 0.2633   |
| 0.038         | 357.97 | 6712 | 4.8910          | 0.2467   |
| 0.0368        | 358.99 | 6731 | 4.8830          | 0.245    |
| 0.0308        | 360.0  | 6750 | 4.8867          | 0.2367   |
| 0.0346        | 360.96 | 6768 | 4.8657          | 0.2433   |
| 0.0279        | 361.97 | 6787 | 4.8678          | 0.24     |
| 0.0443        | 362.99 | 6806 | 4.8723          | 0.2433   |
| 0.027         | 364.0  | 6825 | 4.8756          | 0.2433   |
| 0.0447        | 364.96 | 6843 | 4.8742          | 0.235    |
| 0.028         | 365.97 | 6862 | 4.9042          | 0.235    |
| 0.0483        | 366.99 | 6881 | 4.9086          | 0.2367   |
| 0.034         | 368.0  | 6900 | 4.8886          | 0.24     |
| 0.0363        | 368.96 | 6918 | 4.8778          | 0.2467   |
| 0.0417        | 369.97 | 6937 | 4.9051          | 0.2417   |
| 0.0326        | 370.99 | 6956 | 4.9112          | 0.2367   |
| 0.028         | 372.0  | 6975 | 4.9116          | 0.2333   |
| 0.0343        | 372.96 | 6993 | 4.9104          | 0.245    |
| 0.0229        | 373.97 | 7012 | 4.9401          | 0.2367   |
| 0.0337        | 374.99 | 7031 | 4.9341          | 0.245    |
| 0.0356        | 376.0  | 7050 | 4.9336          | 0.2317   |
| 0.029         | 376.96 | 7068 | 4.9132          | 0.2333   |
| 0.0272        | 377.97 | 7087 | 4.9102          | 0.2367   |
| 0.0256        | 378.99 | 7106 | 4.9255          | 0.2317   |
| 0.0276        | 380.0  | 7125 | 4.9282          | 0.2267   |
| 0.026         | 380.96 | 7143 | 4.9527          | 0.22     |
| 0.0385        | 381.97 | 7162 | 4.9411          | 0.2217   |
| 0.026         | 382.99 | 7181 | 4.9530          | 0.2367   |
| 0.0444        | 384.0  | 7200 | 4.9387          | 0.2383   |
| 0.0369        | 384.96 | 7218 | 4.9042          | 0.2333   |
| 0.0203        | 385.97 | 7237 | 4.8860          | 0.23     |
| 0.0238        | 386.99 | 7256 | 4.8775          | 0.2333   |
| 0.0315        | 388.0  | 7275 | 4.8641          | 0.2333   |
| 0.0349        | 388.96 | 7293 | 4.8677          | 0.2467   |
| 0.038         | 389.97 | 7312 | 4.8688          | 0.24     |
| 0.0301        | 390.99 | 7331 | 4.8932          | 0.245    |
| 0.0363        | 392.0  | 7350 | 4.9023          | 0.2417   |
| 0.0329        | 392.96 | 7368 | 4.8825          | 0.24     |
| 0.0174        | 393.97 | 7387 | 4.8711          | 0.24     |
| 0.0284        | 394.99 | 7406 | 4.8762          | 0.2433   |
| 0.0178        | 396.0  | 7425 | 4.8684          | 0.2417   |
| 0.0359        | 396.96 | 7443 | 4.8660          | 0.245    |
| 0.029         | 397.97 | 7462 | 4.8799          | 0.2433   |
| 0.0227        | 398.99 | 7481 | 4.8845          | 0.25     |
| 0.0135        | 400.0  | 7500 | 4.8898          | 0.2383   |
| 0.0297        | 400.96 | 7518 | 4.8967          | 0.2383   |
| 0.0263        | 401.97 | 7537 | 4.8884          | 0.2333   |
| 0.0386        | 402.99 | 7556 | 4.8719          | 0.24     |
| 0.0298        | 404.0  | 7575 | 4.8609          | 0.2433   |
| 0.0232        | 404.96 | 7593 | 4.8602          | 0.2483   |
| 0.0232        | 405.97 | 7612 | 4.8667          | 0.2467   |
| 0.032         | 406.99 | 7631 | 4.8684          | 0.2483   |
| 0.0306        | 408.0  | 7650 | 4.8755          | 0.2433   |
| 0.0299        | 408.96 | 7668 | 4.8687          | 0.245    |
| 0.0307        | 409.97 | 7687 | 4.8724          | 0.24     |
| 0.0304        | 410.99 | 7706 | 4.8798          | 0.25     |
| 0.0293        | 412.0  | 7725 | 4.8901          | 0.2483   |
| 0.0273        | 412.96 | 7743 | 4.9025          | 0.24     |
| 0.0184        | 413.97 | 7762 | 4.8870          | 0.24     |
| 0.0377        | 414.99 | 7781 | 4.8901          | 0.2417   |
| 0.0278        | 416.0  | 7800 | 4.8895          | 0.2417   |
| 0.0345        | 416.96 | 7818 | 4.9046          | 0.2533   |
| 0.0301        | 417.97 | 7837 | 4.9002          | 0.2483   |
| 0.0159        | 418.99 | 7856 | 4.8982          | 0.245    |
| 0.0203        | 420.0  | 7875 | 4.9008          | 0.2483   |
| 0.0182        | 420.96 | 7893 | 4.9113          | 0.2467   |
| 0.0258        | 421.97 | 7912 | 4.9180          | 0.25     |
| 0.0266        | 422.99 | 7931 | 4.9134          | 0.2433   |
| 0.0304        | 424.0  | 7950 | 4.9005          | 0.2417   |
| 0.0247        | 424.96 | 7968 | 4.8937          | 0.2417   |
| 0.0493        | 425.97 | 7987 | 4.8835          | 0.245    |
| 0.0286        | 426.99 | 8006 | 4.8968          | 0.24     |
| 0.0228        | 428.0  | 8025 | 4.9066          | 0.2383   |
| 0.0362        | 428.96 | 8043 | 4.9031          | 0.245    |
| 0.0244        | 429.97 | 8062 | 4.8997          | 0.2467   |
| 0.0204        | 430.99 | 8081 | 4.9059          | 0.2433   |
| 0.0344        | 432.0  | 8100 | 4.9052          | 0.2433   |
| 0.0252        | 432.96 | 8118 | 4.8975          | 0.2433   |
| 0.0242        | 433.97 | 8137 | 4.8961          | 0.2467   |
| 0.0135        | 434.99 | 8156 | 4.9086          | 0.2467   |
| 0.0296        | 436.0  | 8175 | 4.9135          | 0.2417   |
| 0.0432        | 436.96 | 8193 | 4.9079          | 0.2433   |
| 0.0242        | 437.97 | 8212 | 4.8981          | 0.24     |
| 0.0227        | 438.99 | 8231 | 4.8857          | 0.24     |
| 0.021         | 440.0  | 8250 | 4.8874          | 0.2383   |
| 0.0244        | 440.96 | 8268 | 4.8847          | 0.24     |
| 0.0234        | 441.97 | 8287 | 4.8964          | 0.2367   |
| 0.0278        | 442.99 | 8306 | 4.9161          | 0.2383   |
| 0.0322        | 444.0  | 8325 | 4.9212          | 0.2367   |
| 0.038         | 444.96 | 8343 | 4.9251          | 0.24     |
| 0.0327        | 445.97 | 8362 | 4.9340          | 0.24     |
| 0.0256        | 446.99 | 8381 | 4.9246          | 0.2417   |
| 0.0327        | 448.0  | 8400 | 4.9294          | 0.2367   |
| 0.0246        | 448.96 | 8418 | 4.9311          | 0.2417   |
| 0.0239        | 449.97 | 8437 | 4.9220          | 0.2383   |
| 0.0219        | 450.99 | 8456 | 4.9205          | 0.24     |
| 0.0287        | 452.0  | 8475 | 4.9249          | 0.2367   |
| 0.0244        | 452.96 | 8493 | 4.9275          | 0.24     |
| 0.0222        | 453.97 | 8512 | 4.9322          | 0.2417   |
| 0.0277        | 454.99 | 8531 | 4.9318          | 0.2383   |
| 0.0315        | 456.0  | 8550 | 4.9291          | 0.2383   |
| 0.021         | 456.96 | 8568 | 4.9293          | 0.2367   |
| 0.0288        | 457.97 | 8587 | 4.9233          | 0.2333   |
| 0.0229        | 458.99 | 8606 | 4.9236          | 0.2383   |
| 0.0257        | 460.0  | 8625 | 4.9225          | 0.2367   |
| 0.0291        | 460.96 | 8643 | 4.9222          | 0.2383   |
| 0.0325        | 461.97 | 8662 | 4.9216          | 0.2367   |
| 0.0268        | 462.99 | 8681 | 4.9202          | 0.2367   |
| 0.0156        | 464.0  | 8700 | 4.9175          | 0.2367   |
| 0.0196        | 464.96 | 8718 | 4.9147          | 0.2333   |
| 0.0448        | 465.97 | 8737 | 4.9100          | 0.2333   |
| 0.0232        | 466.99 | 8756 | 4.9088          | 0.2333   |
| 0.0274        | 468.0  | 8775 | 4.9096          | 0.2367   |
| 0.029         | 468.96 | 8793 | 4.9105          | 0.2367   |
| 0.0337        | 469.97 | 8812 | 4.9125          | 0.235    |
| 0.0178        | 470.99 | 8831 | 4.9120          | 0.235    |
| 0.0286        | 472.0  | 8850 | 4.9125          | 0.2367   |
| 0.0159        | 472.96 | 8868 | 4.9102          | 0.2367   |
| 0.0318        | 473.97 | 8887 | 4.9116          | 0.2383   |
| 0.0302        | 474.99 | 8906 | 4.9113          | 0.24     |
| 0.0184        | 476.0  | 8925 | 4.9120          | 0.24     |
| 0.025         | 476.96 | 8943 | 4.9128          | 0.24     |
| 0.027         | 477.97 | 8962 | 4.9126          | 0.24     |
| 0.0298        | 478.99 | 8981 | 4.9130          | 0.24     |
| 0.0349        | 480.0  | 9000 | 4.9130          | 0.24     |


### Framework versions

- Transformers 4.31.0
- Pytorch 1.13.1
- Datasets 2.14.0
- Tokenizers 0.13.3