README.md

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-RUN4-20-fullDatafreez
    results: []

POEMS-CAMELBERT-CA-RUN4-20-fullDatafreez

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: 1.2919
• Accuracy: 0.7047
• F1: 0.7047
• Precision: 0.7047
• Recall: 0.7047

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: 13

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
1.1886	1.0	695	1.0872	0.5447	0.5447	0.5447	0.5447
1.0357	2.0	1390	1.0129	0.5831	0.5831	0.5831	0.5831
0.9067	3.0	2085	1.0089	0.5954	0.5954	0.5954	0.5954
0.7858	4.0	2780	0.9204	0.6453	0.6453	0.6453	0.6453
0.6709	5.0	3475	0.9971	0.6442	0.6442	0.6442	0.6442
0.582	6.0	4170	0.9662	0.6739	0.6739	0.6739	0.6739
0.5098	7.0	4865	1.0057	0.6855	0.6855	0.6855	0.6855
0.4498	8.0	5560	1.1139	0.6851	0.6851	0.6851	0.6851
0.4037	9.0	6255	1.1494	0.6862	0.6862	0.6862	0.6862
0.3609	10.0	6950	1.1697	0.6996	0.6996	0.6996	0.6996
0.3328	11.0	7645	1.2636	0.6967	0.6967	0.6967	0.6967
0.3092	12.0	8340	1.2772	0.6956	0.6956	0.6956	0.6956
0.2943	13.0	9035	1.2919	0.7047	0.7047	0.7047	0.7047

Framework versions

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