Hugging Face's logo

salbatarni
/
arabert_cross_relevance_task1_fold4

TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files Metrics Community
arabert_cross_relevance_task1_fold4 / README.md
salbatarni's picture
salbatarni
End of training
5fd2c1f verified
preview code
|
raw
history blame
3.48 kB
metadata
base_model: aubmindlab/bert-base-arabertv02
tags:
  - generated_from_trainer
model-index:
  - name: arabert_cross_relevance_task1_fold4
    results: []

arabert_cross_relevance_task1_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: 0.2814
  • Qwk: 0.1577
  • Mse: 0.2814

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

Training results

Training Loss Epoch Step Validation Loss Qwk Mse
No log 0.0328 2 0.5567 -0.0320 0.5567
No log 0.0656 4 0.5564 -0.0102 0.5564
No log 0.0984 6 0.5081 0.0304 0.5081
No log 0.1311 8 0.4677 0.0304 0.4677
No log 0.1639 10 0.4282 0.0400 0.4282
No log 0.1967 12 0.4239 0.0496 0.4239
No log 0.2295 14 0.4171 0.0384 0.4171
No log 0.2623 16 0.3868 0.0496 0.3868
No log 0.2951 18 0.3678 0.0690 0.3678
No log 0.3279 20 0.3448 0.0596 0.3448
No log 0.3607 22 0.3295 0.0877 0.3295
No log 0.3934 24 0.3190 0.0877 0.3190
No log 0.4262 26 0.3166 0.0969 0.3166
No log 0.4590 28 0.3135 0.0969 0.3135
No log 0.4918 30 0.3075 0.0969 0.3075
No log 0.5246 32 0.3014 0.1139 0.3014
No log 0.5574 34 0.2971 0.1139 0.2971
No log 0.5902 36 0.2957 0.1048 0.2957
No log 0.6230 38 0.2937 0.1048 0.2937
No log 0.6557 40 0.2888 0.1139 0.2888
No log 0.6885 42 0.2867 0.1139 0.2867
No log 0.7213 44 0.2857 0.1139 0.2857
No log 0.7541 46 0.2847 0.1321 0.2847
No log 0.7869 48 0.2833 0.1577 0.2833
No log 0.8197 50 0.2826 0.1577 0.2826
No log 0.8525 52 0.2822 0.1577 0.2822
No log 0.8852 54 0.2805 0.1577 0.2805
No log 0.9180 56 0.2810 0.1667 0.2810
No log 0.9508 58 0.2816 0.1667 0.2816
No log 0.9836 60 0.2814 0.1577 0.2814

Framework versions

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