metadata

base_model: aubmindlab/bert-base-arabertv02
tags:
  - generated_from_trainer
model-index:
  - name: arabert_cross_relevance_task1_fold3
    results: []

arabert_cross_relevance_task1_fold3

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: 0.2991
Qwk: 0.5026
Mse: 0.2991

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	1.0137	0.0171	1.0137
No log	0.0702	4	0.6105	0.1259	0.6105
No log	0.1053	6	0.6101	0.4090	0.6101
No log	0.1404	8	0.5978	0.3841	0.5978
No log	0.1754	10	0.4704	0.2193	0.4704
No log	0.2105	12	0.3969	0.1722	0.3969
No log	0.2456	14	0.4062	0.2387	0.4062
No log	0.2807	16	0.3689	0.2173	0.3689
No log	0.3158	18	0.3622	0.2224	0.3622
No log	0.3509	20	0.3775	0.2202	0.3775
No log	0.3860	22	0.3739	0.2294	0.3739
No log	0.4211	24	0.3817	0.2153	0.3817
No log	0.4561	26	0.3802	0.2316	0.3802
No log	0.4912	28	0.3706	0.2936	0.3706
No log	0.5263	30	0.3544	0.2687	0.3544
No log	0.5614	32	0.3300	0.2840	0.3300
No log	0.5965	34	0.3051	0.3286	0.3051
No log	0.6316	36	0.2877	0.3503	0.2877
No log	0.6667	38	0.2875	0.3784	0.2875
No log	0.7018	40	0.2986	0.4873	0.2986
No log	0.7368	42	0.3064	0.5052	0.3064
No log	0.7719	44	0.3065	0.5343	0.3065
No log	0.8070	46	0.2939	0.4736	0.2939
No log	0.8421	48	0.2887	0.4490	0.2887
No log	0.8772	50	0.2881	0.4490	0.2881
No log	0.9123	52	0.2916	0.4637	0.2916
No log	0.9474	54	0.2967	0.4885	0.2967
No log	0.9825	56	0.2991	0.5026	0.2991

Framework versions

Transformers 4.44.0
Pytorch 2.4.0
Datasets 2.21.0
Tokenizers 0.19.1