metadata

base_model: aubmindlab/bert-base-arabertv02
tags:
  - generated_from_trainer
model-index:
  - name: arabert_cross_vocabulary_task1_fold0
    results: []

arabert_cross_vocabulary_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: 0.9107
Qwk: 0.3160
Mse: 0.9107

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	3.6812	0.0124	3.6812
No log	0.0702	4	2.2449	0.0807	2.2449
No log	0.1053	6	1.7920	0.1291	1.7920
No log	0.1404	8	1.1077	0.2184	1.1077
No log	0.1754	10	1.6727	0.2157	1.6727
No log	0.2105	12	2.3411	0.1852	2.3411
No log	0.2456	14	1.4252	0.2951	1.4252
No log	0.2807	16	0.8885	0.3981	0.8885
No log	0.3158	18	0.6824	0.4387	0.6824
No log	0.3509	20	0.6604	0.4473	0.6604
No log	0.3860	22	0.7208	0.3880	0.7208
No log	0.4211	24	1.1639	0.2846	1.1639
No log	0.4561	26	2.0330	0.1689	2.0330
No log	0.4912	28	2.2500	0.1485	2.2500
No log	0.5263	30	1.8145	0.1758	1.8145
No log	0.5614	32	1.1982	0.2547	1.1982
No log	0.5965	34	0.8111	0.3192	0.8111
No log	0.6316	36	0.7359	0.3443	0.7359
No log	0.6667	38	0.8012	0.3164	0.8012
No log	0.7018	40	0.9036	0.2985	0.9036
No log	0.7368	42	1.0075	0.2804	1.0075
No log	0.7719	44	1.0761	0.2855	1.0761
No log	0.8070	46	1.0400	0.2883	1.0400
No log	0.8421	48	1.0379	0.2963	1.0379
No log	0.8772	50	1.0163	0.3002	1.0163
No log	0.9123	52	0.9760	0.3168	0.9760
No log	0.9474	54	0.9286	0.3206	0.9286
No log	0.9825	56	0.9107	0.3160	0.9107

Framework versions

Transformers 4.44.0
Pytorch 2.4.0
Datasets 2.21.0
Tokenizers 0.19.1