Hugging Face's logo

salbatarni
/
arabert_cross_relevance_task2_fold2

TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files Metrics Community
arabert_cross_relevance_task2_fold2 / README.md
salbatarni's picture
salbatarni
Training in progress, step 65
8dc17dc verified
preview code
|
raw
history blame
3.55 kB
metadata
base_model: aubmindlab/bert-base-arabertv02
tags:
  - generated_from_trainer
model-index:
  - name: arabert_cross_relevance_task2_fold1
    results: []

arabert_cross_relevance_task2_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: 0.3095
  • Qwk: 0.0122
  • Mse: 0.3095

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 0.0317 2 0.4149 -0.0147 0.4158
No log 0.0635 4 0.5335 0.1106 0.5335
No log 0.0952 6 0.5725 0.1645 0.5725
No log 0.1270 8 0.3171 -0.0585 0.3169
No log 0.1587 10 0.2926 0.0 0.2912
No log 0.1905 12 0.2846 0.0 0.2833
No log 0.2222 14 0.3130 0.0 0.3124
No log 0.2540 16 0.4146 -0.0932 0.4145
No log 0.2857 18 0.5126 -0.0604 0.5126
No log 0.3175 20 0.5293 0.0071 0.5293
No log 0.3492 22 0.5096 -0.0065 0.5096
No log 0.3810 24 0.4663 -0.0607 0.4663
No log 0.4127 26 0.3891 0.0072 0.3890
No log 0.4444 28 0.3106 0.0 0.3105
No log 0.4762 30 0.2879 0.0 0.2877
No log 0.5079 32 0.2833 0.0 0.2833
No log 0.5397 34 0.2867 0.0 0.2867
No log 0.5714 36 0.2981 0.0 0.2981
No log 0.6032 38 0.3163 0.0122 0.3163
No log 0.6349 40 0.3375 -0.0208 0.3375
No log 0.6667 42 0.3404 -0.0128 0.3404
No log 0.6984 44 0.3376 -0.0128 0.3376
No log 0.7302 46 0.3381 -0.0128 0.3381
No log 0.7619 48 0.3257 -0.0042 0.3257
No log 0.7937 50 0.3134 0.0122 0.3134
No log 0.8254 52 0.3075 0.0 0.3075
No log 0.8571 54 0.3042 0.0 0.3042
No log 0.8889 56 0.3043 0.0 0.3043
No log 0.9206 58 0.3064 0.0 0.3064
No log 0.9524 60 0.3082 0.0122 0.3082
No log 0.9841 62 0.3095 0.0122 0.3095

Framework versions

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