Hugging Face's logo

salbatarni
/
arabert_cross_relevance_task4_fold1

TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files Metrics Community
arabert_cross_relevance_task4_fold1 / README.md
salbatarni's picture
salbatarni
End of training
a1a358b verified
preview code
|
raw
history blame
3.63 kB
metadata
base_model: aubmindlab/bert-base-arabertv02
tags:
  - generated_from_trainer
model-index:
  - name: arabert_cross_relevance_task4_fold1
    results: []

arabert_cross_relevance_task4_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: 0.1659
  • Qwk: 0.0402
  • Mse: 0.1659

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 0.0308 2 2.0522 -0.0055 2.0522
No log 0.0615 4 0.6665 -0.0084 0.6665
No log 0.0923 6 0.2290 0.0207 0.2290
No log 0.1231 8 0.1690 0.0796 0.1690
No log 0.1538 10 0.2100 0.0199 0.2100
No log 0.1846 12 0.4380 0.0228 0.4380
No log 0.2154 14 0.4146 0.0114 0.4146
No log 0.2462 16 0.4672 0.0164 0.4672
No log 0.2769 18 0.4548 0.0082 0.4548
No log 0.3077 20 0.3092 0.0166 0.3092
No log 0.3385 22 0.1656 0.0373 0.1656
No log 0.3692 24 0.1443 0.0155 0.1443
No log 0.4 26 0.1375 0.0344 0.1375
No log 0.4308 28 0.1319 0.0250 0.1319
No log 0.4615 30 0.1415 0.0270 0.1415
No log 0.4923 32 0.1730 0.0185 0.1730
No log 0.5231 34 0.2033 0.0185 0.2033
No log 0.5538 36 0.2320 0.0166 0.2320
No log 0.5846 38 0.2349 0.0149 0.2349
No log 0.6154 40 0.2136 0.0165 0.2136
No log 0.6462 42 0.1798 0.0165 0.1798
No log 0.6769 44 0.1596 0.0175 0.1596
No log 0.7077 46 0.1554 0.0243 0.1554
No log 0.7385 48 0.1612 0.0316 0.1612
No log 0.7692 50 0.1628 0.0261 0.1628
No log 0.8 52 0.1699 0.0317 0.1699
No log 0.8308 54 0.1702 0.0284 0.1702
No log 0.8615 56 0.1679 0.0334 0.1679
No log 0.8923 58 0.1678 0.0334 0.1678
No log 0.9231 60 0.1646 0.0436 0.1646
No log 0.9538 62 0.1648 0.0402 0.1648
No log 0.9846 64 0.1659 0.0402 0.1659

Framework versions

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