Hugging Face's logo

salbatarni
/
arabert_cross_organization_task6_fold4

Safetensors
bert
Generated from Trainer
Model card Files Community
arabert_cross_organization_task6_fold4 / README.md
salbatarni's picture
salbatarni
End of training
33123d1 verified
preview code
|
raw
history blame contribute delete
No virus
6.88 kB
metadata
base_model: aubmindlab/bert-base-arabertv02
tags:
  - generated_from_trainer
model-index:
  - name: arabert_cross_organization_task6_fold4
    results: []

arabert_cross_organization_task6_fold4

This model is a fine-tuned version of aubmindlab/bert-base-arabertv02 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5513
  • Qwk: 0.8014
  • Mse: 0.5513

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: 2e-05
  • train_batch_size: 64
  • eval_batch_size: 64
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Qwk Mse
No log 0.125 2 1.7949 0.0785 1.7949
No log 0.25 4 1.3176 0.3355 1.3176
No log 0.375 6 1.0133 0.4987 1.0133
No log 0.5 8 0.8195 0.6242 0.8195
No log 0.625 10 0.6810 0.6733 0.6810
No log 0.75 12 0.6997 0.7476 0.6997
No log 0.875 14 0.8146 0.7416 0.8146
No log 1.0 16 0.7351 0.6641 0.7351
No log 1.125 18 0.6322 0.6459 0.6322
No log 1.25 20 0.6009 0.7063 0.6009
No log 1.375 22 0.6280 0.7695 0.6280
No log 1.5 24 0.6339 0.7783 0.6339
No log 1.625 26 0.6448 0.7702 0.6448
No log 1.75 28 0.5640 0.7779 0.5640
No log 1.875 30 0.5431 0.7439 0.5431
No log 2.0 32 0.5812 0.7734 0.5812
No log 2.125 34 0.6724 0.7815 0.6724
No log 2.25 36 0.7187 0.7729 0.7187
No log 2.375 38 0.5409 0.7541 0.5409
No log 2.5 40 0.5281 0.7293 0.5281
No log 2.625 42 0.6063 0.7901 0.6063
No log 2.75 44 0.6529 0.7684 0.6529
No log 2.875 46 0.5454 0.7558 0.5454
No log 3.0 48 0.5428 0.7521 0.5428
No log 3.125 50 0.6258 0.7773 0.6258
No log 3.25 52 0.6788 0.7753 0.6788
No log 3.375 54 0.5643 0.7870 0.5643
No log 3.5 56 0.5302 0.7485 0.5302
No log 3.625 58 0.5557 0.7880 0.5557
No log 3.75 60 0.6261 0.7858 0.6261
No log 3.875 62 0.5642 0.7914 0.5642
No log 4.0 64 0.5355 0.7849 0.5355
No log 4.125 66 0.5320 0.7895 0.5320
No log 4.25 68 0.5634 0.7939 0.5634
No log 4.375 70 0.5815 0.7876 0.5815
No log 4.5 72 0.5643 0.7947 0.5643
No log 4.625 74 0.5290 0.7923 0.5290
No log 4.75 76 0.5541 0.7948 0.5541
No log 4.875 78 0.6162 0.7857 0.6162
No log 5.0 80 0.5720 0.7885 0.5720
No log 5.125 82 0.5198 0.7815 0.5198
No log 5.25 84 0.5301 0.7775 0.5301
No log 5.375 86 0.5941 0.7837 0.5941
No log 5.5 88 0.5713 0.7985 0.5713
No log 5.625 90 0.5275 0.7835 0.5275
No log 5.75 92 0.5396 0.7877 0.5396
No log 5.875 94 0.5560 0.7929 0.5560
No log 6.0 96 0.5601 0.7822 0.5601
No log 6.125 98 0.5313 0.7829 0.5313
No log 6.25 100 0.5126 0.7686 0.5126
No log 6.375 102 0.5279 0.7834 0.5279
No log 6.5 104 0.5844 0.8096 0.5844
No log 6.625 106 0.5860 0.8086 0.5860
No log 6.75 108 0.5568 0.7963 0.5568
No log 6.875 110 0.5406 0.7844 0.5406
No log 7.0 112 0.5425 0.7887 0.5425
No log 7.125 114 0.5630 0.8032 0.5630
No log 7.25 116 0.5942 0.8088 0.5942
No log 7.375 118 0.6014 0.8083 0.6014
No log 7.5 120 0.5778 0.8081 0.5778
No log 7.625 122 0.5335 0.7946 0.5335
No log 7.75 124 0.5308 0.7931 0.5308
No log 7.875 126 0.5490 0.7917 0.5490
No log 8.0 128 0.5644 0.8045 0.5644
No log 8.125 130 0.5800 0.8050 0.5800
No log 8.25 132 0.5999 0.8207 0.5999
No log 8.375 134 0.5872 0.8085 0.5872
No log 8.5 136 0.5666 0.8035 0.5666
No log 8.625 138 0.5568 0.8039 0.5568
No log 8.75 140 0.5546 0.8000 0.5546
No log 8.875 142 0.5612 0.8043 0.5612
No log 9.0 144 0.5764 0.8146 0.5764
No log 9.125 146 0.5943 0.8208 0.5943
No log 9.25 148 0.6016 0.8226 0.6016
No log 9.375 150 0.5924 0.8205 0.5924
No log 9.5 152 0.5765 0.8109 0.5765
No log 9.625 154 0.5638 0.8056 0.5638
No log 9.75 156 0.5558 0.8031 0.5558
No log 9.875 158 0.5516 0.7992 0.5516
No log 10.0 160 0.5513 0.8014 0.5513

Framework versions

  • Transformers 4.44.0
  • Pytorch 2.4.0
  • Datasets 2.21.0
  • Tokenizers 0.19.1