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: 0.2406
Qwk: 0.0225
Mse: 0.2406

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	0.5970	0.0065	0.5970
No log	0.0702	4	0.1673	0.0060	0.1673
No log	0.1053	6	0.3299	0.0278	0.3299
No log	0.1404	8	0.7352	0.0065	0.7352
No log	0.1754	10	0.6501	0.0208	0.6501
No log	0.2105	12	0.4790	0.0347	0.4790
No log	0.2456	14	0.3876	0.0363	0.3876
No log	0.2807	16	0.4097	0.0294	0.4097
No log	0.3158	18	0.3925	0.0277	0.3925
No log	0.3509	20	0.3541	0.0310	0.3541
No log	0.3860	22	0.3565	0.0461	0.3565
No log	0.4211	24	0.3341	0.0410	0.3341
No log	0.4561	26	0.3266	0.0480	0.3266
No log	0.4912	28	0.3191	0.0381	0.3191
No log	0.5263	30	0.3104	0.0271	0.3104
No log	0.5614	32	0.3215	0.0271	0.3215
No log	0.5965	34	0.3010	0.0194	0.3010
No log	0.6316	36	0.3055	0.0194	0.3055
No log	0.6667	38	0.3447	0.0254	0.3447
No log	0.7018	40	0.3547	0.0399	0.3547
No log	0.7368	42	0.3642	0.0399	0.3642
No log	0.7719	44	0.3510	0.0327	0.3510
No log	0.8070	46	0.3201	0.0178	0.3201
No log	0.8421	48	0.2882	0.0194	0.2882
No log	0.8772	50	0.2672	0.0209	0.2672
No log	0.9123	52	0.2539	0.0209	0.2539
No log	0.9474	54	0.2455	0.0225	0.2455
No log	0.9825	56	0.2406	0.0225	0.2406

Framework versions

Transformers 4.44.0
Pytorch 2.4.0
Datasets 2.21.0
Tokenizers 0.19.1