metadata

base_model: aubmindlab/bert-base-arabertv02
tags:
  - generated_from_trainer
model-index:
  - name: arabert_cross_relevance_task1_fold5
    results: []

arabert_cross_relevance_task1_fold5

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: 0.1955
Qwk: 0.3846
Mse: 0.1955

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	0.3613	0.2826	0.3613
No log	0.0702	4	0.4116	0.5484	0.4116
No log	0.1053	6	0.2771	0.4880	0.2771
No log	0.1404	8	0.2157	0.3346	0.2157
No log	0.1754	10	0.2149	0.3324	0.2149
No log	0.2105	12	0.2119	0.3302	0.2119
No log	0.2456	14	0.2146	0.3336	0.2146
No log	0.2807	16	0.2085	0.3319	0.2085
No log	0.3158	18	0.2118	0.3641	0.2118
No log	0.3509	20	0.2261	0.4439	0.2261
No log	0.3860	22	0.2392	0.4713	0.2392
No log	0.4211	24	0.2344	0.4095	0.2344
No log	0.4561	26	0.2151	0.3602	0.2151
No log	0.4912	28	0.2029	0.3304	0.2029
No log	0.5263	30	0.2041	0.3227	0.2041
No log	0.5614	32	0.2085	0.3015	0.2085
No log	0.5965	34	0.2114	0.2998	0.2114
No log	0.6316	36	0.2114	0.2998	0.2114
No log	0.6667	38	0.2041	0.3156	0.2041
No log	0.7018	40	0.1985	0.3186	0.1985
No log	0.7368	42	0.1948	0.3490	0.1948
No log	0.7719	44	0.1925	0.3543	0.1925
No log	0.8070	46	0.1939	0.3667	0.1939
No log	0.8421	48	0.1928	0.3684	0.1928
No log	0.8772	50	0.1932	0.3736	0.1932
No log	0.9123	52	0.1942	0.3795	0.1942
No log	0.9474	54	0.1952	0.3846	0.1952
No log	0.9825	56	0.1955	0.3846	0.1955

Framework versions

Transformers 4.44.0
Pytorch 2.4.0
Datasets 2.21.0
Tokenizers 0.19.1