Hugging Face's logo

salbatarni
/
arabert_cross_relevance_task2_fold0

TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files Metrics Community
arabert_cross_relevance_task2_fold0 / README.md
salbatarni's picture
salbatarni
Training in progress, step 57
b87113e verified
preview code
|
raw
history blame
3.45 kB
metadata
base_model: aubmindlab/bert-base-arabertv02
tags:
  - generated_from_trainer
model-index:
  - name: arabert_cross_relevance_task1_fold6
    results: []

arabert_cross_relevance_task1_fold6

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: 0.2541
  • Qwk: 0.2373
  • Mse: 0.2539

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 0.0333 2 0.3369 0.1172 0.3369
No log 0.0667 4 0.4978 0.3977 0.4978
No log 0.1 6 0.4733 0.3519 0.4733
No log 0.1333 8 0.3071 0.0964 0.3071
No log 0.1667 10 0.2732 0.1475 0.2733
No log 0.2 12 0.2941 0.2325 0.2943
No log 0.2333 14 0.2888 0.2076 0.2890
No log 0.2667 16 0.2781 0.2076 0.2782
No log 0.3 18 0.3038 0.2583 0.3038
No log 0.3333 20 0.3106 0.2515 0.3105
No log 0.3667 22 0.2932 0.2691 0.2930
No log 0.4 24 0.2674 0.2167 0.2669
No log 0.4333 26 0.2571 0.2325 0.2564
No log 0.4667 28 0.2516 0.2282 0.2509
No log 0.5 30 0.2513 0.2352 0.2506
No log 0.5333 32 0.2536 0.2414 0.2531
No log 0.5667 34 0.2678 0.2304 0.2674
No log 0.6 36 0.2837 0.2448 0.2832
No log 0.6333 38 0.3006 0.2257 0.3000
No log 0.6667 40 0.3090 0.2226 0.3084
No log 0.7 42 0.2975 0.2250 0.2971
No log 0.7333 44 0.2897 0.2572 0.2894
No log 0.7667 46 0.2878 0.2779 0.2875
No log 0.8 48 0.2796 0.2786 0.2794
No log 0.8333 50 0.2697 0.2649 0.2695
No log 0.8667 52 0.2639 0.2578 0.2637
No log 0.9 54 0.2596 0.2436 0.2594
No log 0.9333 56 0.2564 0.2443 0.2562
No log 0.9667 58 0.2544 0.2373 0.2543
No log 1.0 60 0.2541 0.2373 0.2539

Framework versions

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