generated_from_trainer

<!-- 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. -->

V3_20230929-2-xlm-roberta-base-new

This model is a fine-tuned version of xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:

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:

Training results

Training Loss Epoch Step Accuracy Validation Loss
4.4076 0.46 200 0.2641 nan
4.0232 0.91 400 0.3172 nan
3.9061 1.37 600 0.3025 nan
3.6669 1.82 800 0.3241 3.5105
3.5761 2.28 1000 0.3492 3.2617
3.4949 2.73 1200 0.3894 nan
3.3705 3.19 1400 0.4269 nan
3.3901 3.64 1600 0.4191 3.3508
3.1971 4.1 1800 0.3889 nan
3.1646 4.56 2000 0.4204 3.3370
2.9748 5.01 2200 0.4468 2.8025
3.0047 5.47 2400 0.4327 3.0098
2.9395 5.92 2600 0.4673 2.7967
2.8467 6.38 2800 0.4675 nan
2.7492 6.83 3000 0.4613 2.8956
2.802 7.29 3200 0.4766 2.5544
2.8111 7.74 3400 0.4925 nan
2.6549 8.2 3600 0.5013 nan
2.7367 8.66 3800 0.4842 2.7689
2.6375 9.11 4000 0.5303 nan
2.616 9.57 4200 0.5157 2.6867
2.711 10.02 4400 0.5357 2.2537
2.4239 10.48 4600 0.4976 nan
2.7012 10.93 4800 0.5105 2.4325
2.5152 11.39 5000 0.5372 nan
2.5798 11.85 5200 0.5320 nan
2.4845 12.3 5400 0.5553 nan
2.4842 12.76 5600 0.5206 nan
2.4412 13.21 5800 0.5398 2.3403
2.4967 13.67 6000 0.5285 2.2010
2.4451 14.12 6200 0.4803 2.5469
2.485 14.58 6400 0.5469 nan

Framework versions