metadata

base_model: aubmindlab/bert-base-arabertv02
tags:
  - generated_from_trainer
model-index:
  - name: arabert_cross_relevance_task2_fold3
    results: []

arabert_cross_relevance_task2_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: 0.2961
Qwk: 0.3277
Mse: 0.2961

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	1.1621	0.0229	1.1621
No log	0.0702	4	0.5340	0.1841	0.5340
No log	0.1053	6	0.5506	0.1500	0.5506
No log	0.1404	8	0.5057	0.1888	0.5057
No log	0.1754	10	0.4434	0.1993	0.4434
No log	0.2105	12	0.4171	0.2214	0.4171
No log	0.2456	14	0.3762	0.2316	0.3762
No log	0.2807	16	0.3295	0.2935	0.3295
No log	0.3158	18	0.3210	0.2948	0.3210
No log	0.3509	20	0.3093	0.2948	0.3093
No log	0.3860	22	0.3105	0.3062	0.3105
No log	0.4211	24	0.3464	0.3679	0.3464
No log	0.4561	26	0.3981	0.6151	0.3981
No log	0.4912	28	0.3851	0.6021	0.3851
No log	0.5263	30	0.3431	0.4831	0.3431
No log	0.5614	32	0.3017	0.3166	0.3017
No log	0.5965	34	0.2863	0.3277	0.2863
No log	0.6316	36	0.2906	0.3407	0.2906
No log	0.6667	38	0.2981	0.3509	0.2981
No log	0.7018	40	0.2999	0.3509	0.2999
No log	0.7368	42	0.2988	0.3391	0.2988
No log	0.7719	44	0.2970	0.3148	0.2970
No log	0.8070	46	0.2972	0.3126	0.2972
No log	0.8421	48	0.2982	0.3126	0.2982
No log	0.8772	50	0.2966	0.3158	0.2966
No log	0.9123	52	0.2961	0.3277	0.2961
No log	0.9474	54	0.2957	0.3286	0.2957
No log	0.9825	56	0.2961	0.3277	0.2961

Framework versions

Transformers 4.44.0
Pytorch 2.4.0
Datasets 2.21.0
Tokenizers 0.19.1