Hugging Face's logo

haryoaw
/
scenario-NON-KD-SCR-COPY-CDF-CL-D2_data-cl-cardiff_cl_only_alpha

Text Classification
Transformers
PyTorch
xlm-roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
scenario-NON-KD-SCR-COPY-CDF-CL-D2_data-cl-cardiff_cl_only_alpha / README.md
haryoaw's picture
haryoaw
Initial Commit
e1a00a3 verified
preview code
|
raw
history blame
3.33 kB
metadata
license: mit
base_model: xlm-roberta-base
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
model-index:
  - name: scenario-NON-KD-SCR-COPY-CDF-CL-D2_data-cl-cardiff_cl_only_alpha
    results: []

scenario-NON-KD-SCR-COPY-CDF-CL-D2_data-cl-cardiff_cl_only_alpha

This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 6.4834
  • Accuracy: 0.3758
  • F1: 0.3692

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: 1123
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 30

Training results

Training Loss Epoch Step Validation Loss Accuracy F1
No log 1.09 250 1.1269 0.3302 0.2264
1.0552 2.17 500 1.4862 0.3673 0.3240
1.0552 3.26 750 2.0425 0.3580 0.3105
0.4849 4.35 1000 2.7827 0.3673 0.3562
0.4849 5.43 1250 2.3787 0.3804 0.3790
0.1731 6.52 1500 3.5404 0.3873 0.3523
0.1731 7.61 1750 4.1335 0.3765 0.3561
0.0878 8.7 2000 4.4114 0.375 0.3748
0.0878 9.78 2250 4.9951 0.3650 0.3587
0.036 10.87 2500 5.1386 0.3642 0.3569
0.036 11.96 2750 5.4524 0.3711 0.3499
0.0297 13.04 3000 5.4964 0.3681 0.3565
0.0297 14.13 3250 5.3291 0.3765 0.3709
0.0225 15.22 3500 5.6184 0.3719 0.3346
0.0225 16.3 3750 5.4079 0.3719 0.3466
0.0144 17.39 4000 5.6999 0.3634 0.3538
0.0144 18.48 4250 5.7290 0.3681 0.3575
0.007 19.57 4500 5.9349 0.3673 0.3272
0.007 20.65 4750 5.7265 0.3789 0.3760
0.0064 21.74 5000 6.1464 0.3611 0.3370
0.0064 22.83 5250 6.1483 0.3765 0.3678
0.0026 23.91 5500 6.3733 0.3742 0.3688
0.0026 25.0 5750 6.3795 0.3704 0.3498
0.002 26.09 6000 6.4692 0.3735 0.3582
0.002 27.17 6250 6.5994 0.3727 0.3448
0.0006 28.26 6500 6.4658 0.3758 0.3693
0.0006 29.35 6750 6.4834 0.3758 0.3692

Framework versions

  • Transformers 4.33.3
  • Pytorch 2.1.1+cu121
  • Datasets 2.14.5
  • Tokenizers 0.13.3