salbatarni's picture
Training in progress, step 170
b2fb6a9 verified
|
raw
history blame
6.88 kB
metadata
base_model: aubmindlab/bert-base-arabertv02
tags:
  - generated_from_trainer
model-index:
  - name: arabert_cross_organization_task6_fold1
    results: []

arabert_cross_organization_task6_fold1

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: 0.8118
  • Qwk: 0.4006
  • Mse: 0.8118

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 3.3727 0.0150 3.3727
No log 0.25 4 1.5579 0.0418 1.5579
No log 0.375 6 0.8889 0.1524 0.8889
No log 0.5 8 0.7988 0.2568 0.7988
No log 0.625 10 0.9045 0.2445 0.9045
No log 0.75 12 1.3396 0.2180 1.3396
No log 0.875 14 0.8588 0.3519 0.8588
No log 1.0 16 0.5574 0.5527 0.5574
No log 1.125 18 0.5553 0.5503 0.5553
No log 1.25 20 0.8079 0.3672 0.8079
No log 1.375 22 1.3052 0.2456 1.3052
No log 1.5 24 0.9198 0.3104 0.9198
No log 1.625 26 0.5541 0.5285 0.5541
No log 1.75 28 0.5512 0.5290 0.5512
No log 1.875 30 0.6121 0.4768 0.6121
No log 2.0 32 0.8609 0.3129 0.8609
No log 2.125 34 0.9886 0.2731 0.9886
No log 2.25 36 0.8076 0.3795 0.8076
No log 2.375 38 0.6513 0.4757 0.6513
No log 2.5 40 0.6322 0.4656 0.6322
No log 2.625 42 0.8239 0.3721 0.8239
No log 2.75 44 0.8173 0.3657 0.8173
No log 2.875 46 0.5953 0.4602 0.5953
No log 3.0 48 0.4998 0.5491 0.4998
No log 3.125 50 0.4994 0.5388 0.4994
No log 3.25 52 0.5985 0.4558 0.5985
No log 3.375 54 0.8360 0.3362 0.8360
No log 3.5 56 0.7638 0.3694 0.7638
No log 3.625 58 0.5758 0.4882 0.5758
No log 3.75 60 0.5627 0.5091 0.5627
No log 3.875 62 0.6464 0.4616 0.6464
No log 4.0 64 0.7995 0.3939 0.7995
No log 4.125 66 0.8090 0.4038 0.8090
No log 4.25 68 0.7637 0.4270 0.7637
No log 4.375 70 0.6773 0.4614 0.6773
No log 4.5 72 0.6071 0.4596 0.6071
No log 4.625 74 0.6404 0.4305 0.6404
No log 4.75 76 0.7606 0.3850 0.7606
No log 4.875 78 0.7167 0.4134 0.7167
No log 5.0 80 0.6509 0.4134 0.6509
No log 5.125 82 0.6798 0.4551 0.6798
No log 5.25 84 0.7948 0.3986 0.7948
No log 5.375 86 0.8620 0.3562 0.8620
No log 5.5 88 0.8876 0.3559 0.8876
No log 5.625 90 0.7515 0.4248 0.7515
No log 5.75 92 0.7108 0.4577 0.7108
No log 5.875 94 0.7862 0.4061 0.7862
No log 6.0 96 0.8416 0.3952 0.8416
No log 6.125 98 0.7997 0.4122 0.7997
No log 6.25 100 0.8258 0.3932 0.8258
No log 6.375 102 0.7838 0.4124 0.7838
No log 6.5 104 0.7944 0.4076 0.7944
No log 6.625 106 0.8231 0.3830 0.8231
No log 6.75 108 0.7694 0.4134 0.7694
No log 6.875 110 0.7985 0.3792 0.7985
No log 7.0 112 0.8356 0.3632 0.8356
No log 7.125 114 0.8848 0.3450 0.8848
No log 7.25 116 0.8497 0.3620 0.8497
No log 7.375 118 0.7434 0.4183 0.7434
No log 7.5 120 0.7023 0.4781 0.7023
No log 7.625 122 0.7498 0.4429 0.7498
No log 7.75 124 0.9144 0.3785 0.9144
No log 7.875 126 1.0497 0.3405 1.0497
No log 8.0 128 1.0554 0.3506 1.0554
No log 8.125 130 0.9425 0.3693 0.9425
No log 8.25 132 0.8329 0.4324 0.8329
No log 8.375 134 0.7552 0.4623 0.7552
No log 8.5 136 0.7557 0.4559 0.7557
No log 8.625 138 0.7684 0.4526 0.7684
No log 8.75 140 0.8092 0.4060 0.8092
No log 8.875 142 0.8508 0.3842 0.8508
No log 9.0 144 0.8605 0.3817 0.8605
No log 9.125 146 0.8641 0.3822 0.8641
No log 9.25 148 0.8326 0.3939 0.8326
No log 9.375 150 0.8206 0.3946 0.8206
No log 9.5 152 0.7988 0.4013 0.7988
No log 9.625 154 0.7932 0.4040 0.7932
No log 9.75 156 0.7973 0.4040 0.7973
No log 9.875 158 0.8061 0.4006 0.8061
No log 10.0 160 0.8118 0.4006 0.8118

Framework versions

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