metadata

base_model: aubmindlab/bert-base-arabertv02
tags:
  - generated_from_trainer
model-index:
  - name: arabert_cross_relevance_task1_fold0
    results: []

arabert_cross_relevance_task1_fold0

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: 0.1989
Qwk: 0.0319
Mse: 0.1989

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	0.0351	2	0.4878	0.0163	0.4878
No log	0.0702	4	0.1886	0.0202	0.1886
No log	0.1053	6	0.1831	0.0185	0.1831
No log	0.1404	8	0.2686	0.0273	0.2686
No log	0.1754	10	0.2485	0.0273	0.2485
No log	0.2105	12	0.2552	0.0273	0.2552
No log	0.2456	14	0.2716	0.0254	0.2716
No log	0.2807	16	0.3347	0.0217	0.3347
No log	0.3158	18	0.3725	0.0323	0.3725
No log	0.3509	20	0.3182	0.0361	0.3182
No log	0.3860	22	0.2412	0.0319	0.2412
No log	0.4211	24	0.1936	0.0319	0.1936
No log	0.4561	26	0.1659	0.0319	0.1659
No log	0.4912	28	0.1540	0.0339	0.1540
No log	0.5263	30	0.1483	0.0254	0.1483
No log	0.5614	32	0.1525	0.0273	0.1525
No log	0.5965	34	0.1560	0.0359	0.1560
No log	0.6316	36	0.1603	0.0339	0.1603
No log	0.6667	38	0.1720	0.0319	0.1720
No log	0.7018	40	0.1847	0.0319	0.1847
No log	0.7368	42	0.2033	0.0319	0.2033
No log	0.7719	44	0.2175	0.0319	0.2175
No log	0.8070	46	0.2213	0.0319	0.2213
No log	0.8421	48	0.2184	0.0319	0.2184
No log	0.8772	50	0.2126	0.0319	0.2126
No log	0.9123	52	0.2064	0.0319	0.2064
No log	0.9474	54	0.2016	0.0319	0.2016
No log	0.9825	56	0.1989	0.0319	0.1989

Framework versions

Transformers 4.44.0
Pytorch 2.4.0
Datasets 2.21.0
Tokenizers 0.19.1