mbti-career / README.md
theta's picture
update model card README.md
d3ba4b2
metadata
license: mit
tags:
  - generated_from_trainer
model-index:
  - name: mbti-career
    results: []

mbti-career

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

  • Loss: 0.3516

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: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 300
  • num_epochs: 15

Training results

Training Loss Epoch Step Validation Loss
0.6547 0.59 100 0.6169
0.5967 1.18 200 0.5943
0.5872 1.76 300 0.5696
0.554 2.35 400 0.5287
0.5041 2.94 500 0.4890
0.4773 3.53 600 0.4895
0.4691 4.12 700 0.4840
0.4253 4.71 800 0.4573
0.4002 5.29 900 0.4240
0.3813 5.88 1000 0.4031
0.3561 6.47 1100 0.3943
0.3359 7.06 1200 0.3864
0.3126 7.65 1300 0.3889
0.2948 8.24 1400 0.3869
0.2816 8.82 1500 0.3788
0.2522 9.41 1600 0.3891
0.2451 10.0 1700 0.3849
0.2148 10.59 1800 0.3784
0.2132 11.18 1900 0.3716
0.1882 11.76 2000 0.3659
0.1754 12.35 2100 0.3737
0.169 12.94 2200 0.3711
0.1559 13.53 2300 0.3672
0.1537 14.12 2400 0.3391
0.1427 14.71 2500 0.3516

Framework versions

  • Transformers 4.25.1
  • Pytorch 1.13.0+cu116
  • Datasets 2.8.0
  • Tokenizers 0.13.2