salohnana2018's picture
Upload tokenizer
3283e23 verified
metadata
license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
  - precision
  - recall
base_model: CAMeL-Lab/bert-base-arabic-camelbert-ca
model-index:
  - name: POEMS-CAMELBERT-CA-RUN4
    results: []

POEMS-CAMELBERT-CA-RUN4

This model is a fine-tuned version of CAMeL-Lab/bert-base-arabic-camelbert-ca on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.1498
  • Accuracy: 0.5966
  • F1: 0.5966
  • Precision: 0.5966
  • Recall: 0.5966

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: 5e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • 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 Accuracy F1 Precision Recall
1.3444 1.0 472 1.2277 0.4552 0.4552 0.4552 0.4552
1.1589 2.0 944 1.0866 0.5275 0.5275 0.5275 0.5275
1.0829 3.0 1416 1.1405 0.5146 0.5146 0.5146 0.5146
1.0 4.0 1888 1.0262 0.5643 0.5643 0.5643 0.5643
0.9288 5.0 2360 1.0574 0.5762 0.5762 0.5762 0.5762
0.8776 6.0 2832 1.0456 0.5838 0.5838 0.5838 0.5838
0.8166 7.0 3304 1.1421 0.5745 0.5745 0.5745 0.5745
0.7636 8.0 3776 1.0959 0.5931 0.5931 0.5931 0.5931
0.7173 9.0 4248 1.1400 0.5851 0.5851 0.5851 0.5851
0.6915 10.0 4720 1.1498 0.5966 0.5966 0.5966 0.5966

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2