metadata

base_model: aubmindlab/bert-base-arabert
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: results
    results: []

results

This model is a fine-tuned version of aubmindlab/bert-base-arabert on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.4485
Accuracy: 0.7656
Precision: 0.7688
Recall: 0.7656
F1: 0.7650
Mrr: 0.8440

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: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 320
num_epochs: 12

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	Mrr
0.9496	1.0	2250	0.9448	0.69	0.7197	0.69	0.6896	0.8003
0.7839	2.0	4500	0.8385	0.7	0.7302	0.7	0.7032	0.8101
0.4602	3.0	6750	0.9599	0.745	0.7524	0.745	0.7421	0.8346
0.4453	4.0	9000	0.9992	0.7325	0.7474	0.7325	0.7353	0.8342
0.3919	5.0	11250	1.2636	0.7425	0.7551	0.7425	0.7413	0.8312
0.313	6.0	13500	1.3639	0.7625	0.7679	0.7625	0.7628	0.8442
0.2186	7.0	15750	1.6281	0.745	0.7566	0.745	0.7461	0.8369
0.1942	8.0	18000	1.5611	0.775	0.7822	0.775	0.7752	0.8486
0.128	9.0	20250	1.7601	0.74	0.7504	0.74	0.7412	0.8341
0.0598	10.0	22500	1.6894	0.7725	0.7761	0.7725	0.7725	0.8548
0.0699	11.0	24750	1.8025	0.765	0.7698	0.765	0.7645	0.8460
0.0292	12.0	27000	1.8754	0.76	0.7621	0.76	0.7592	0.8451

Framework versions

Transformers 4.38.2
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2