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: 0.1907
Qwk: 0.0246
Mse: 0.1907

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	1.1829	-0.0050	1.1829
No log	0.0702	4	0.2409	0.0099	0.2409
No log	0.1053	6	0.1676	-0.0484	0.1676
No log	0.1404	8	0.1570	0.0130	0.1570
No log	0.1754	10	0.3161	0.0173	0.3161
No log	0.2105	12	0.6111	0.0144	0.6111
No log	0.2456	14	0.4643	0.0505	0.4643
No log	0.2807	16	0.3698	0.0345	0.3698
No log	0.3158	18	0.2920	0.0181	0.2920
No log	0.3509	20	0.2091	0.0235	0.2091
No log	0.3860	22	0.1792	0.0092	0.1792
No log	0.4211	24	0.1670	0.0386	0.1670
No log	0.4561	26	0.1654	0.0258	0.1654
No log	0.4912	28	0.1730	0.0081	0.1730
No log	0.5263	30	0.1851	0.0141	0.1851
No log	0.5614	32	0.2064	0.0092	0.2064
No log	0.5965	34	0.2253	0.0270	0.2253
No log	0.6316	36	0.2300	0.0355	0.2300
No log	0.6667	38	0.2391	0.0339	0.2391
No log	0.7018	40	0.2358	0.0339	0.2358
No log	0.7368	42	0.2370	0.0300	0.2370
No log	0.7719	44	0.2370	0.0361	0.2370
No log	0.8070	46	0.2312	0.0323	0.2312
No log	0.8421	48	0.2215	0.0323	0.2215
No log	0.8772	50	0.2101	0.0358	0.2101
No log	0.9123	52	0.2006	0.0212	0.2006
No log	0.9474	54	0.1943	0.0246	0.1943
No log	0.9825	56	0.1907	0.0246	0.1907

Framework versions

Transformers 4.44.0
Pytorch 2.4.0
Datasets 2.21.0
Tokenizers 0.19.1