arabert_baseline_organization_task1_fold1

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: 0.7406
• Qwk: 0.7336
• Mse: 0.7406
• Rmse: 0.8606

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	0.1818	2	3.0376	0.0094	3.0376	1.7429
No log	0.3636	4	1.6849	-0.0143	1.6849	1.2980
No log	0.5455	6	1.2236	0.0597	1.2236	1.1061
No log	0.7273	8	1.2683	-0.0302	1.2683	1.1262
No log	0.9091	10	1.1217	-0.0161	1.1217	1.0591
No log	1.0909	12	0.9264	-0.0467	0.9264	0.9625
No log	1.2727	14	0.8294	-0.0284	0.8294	0.9107
No log	1.4545	16	0.8008	0.0427	0.8008	0.8949
No log	1.6364	18	0.7784	0.0427	0.7784	0.8823
No log	1.8182	20	0.7216	0.0	0.7216	0.8495
No log	2.0	22	0.7271	0.2857	0.7271	0.8527
No log	2.1818	24	0.7480	0.3090	0.7480	0.8649
No log	2.3636	26	0.6967	0.3109	0.6967	0.8347
No log	2.5455	28	0.6857	0.4	0.6857	0.8281
No log	2.7273	30	0.6479	0.5926	0.6479	0.8049
No log	2.9091	32	0.6868	0.5926	0.6868	0.8287
No log	3.0909	34	0.6055	0.6316	0.6055	0.7781
No log	3.2727	36	0.5330	0.5776	0.5330	0.7301
No log	3.4545	38	0.4870	0.6345	0.4870	0.6979
No log	3.6364	40	0.5030	0.6638	0.5030	0.7093
No log	3.8182	42	0.4888	0.5767	0.4888	0.6991
No log	4.0	44	0.4738	0.5767	0.4738	0.6884
No log	4.1818	46	0.5713	0.6410	0.5713	0.7559
No log	4.3636	48	0.7034	0.7482	0.7034	0.8387
No log	4.5455	50	0.7505	0.7426	0.7505	0.8663
No log	4.7273	52	0.7736	0.7426	0.7736	0.8796
No log	4.9091	54	0.6137	0.7390	0.6137	0.7834
No log	5.0909	56	0.6615	0.7390	0.6615	0.8133
No log	5.2727	58	0.8090	0.7138	0.8090	0.8995
No log	5.4545	60	0.7775	0.7287	0.7775	0.8818
No log	5.6364	62	0.6471	0.7107	0.6471	0.8045
No log	5.8182	64	0.5071	0.6547	0.5071	0.7121
No log	6.0	66	0.4469	0.6500	0.4469	0.6685
No log	6.1818	68	0.4640	0.6866	0.4640	0.6812
No log	6.3636	70	0.6052	0.7266	0.6052	0.7779
No log	6.5455	72	0.8728	0.6873	0.8728	0.9342
No log	6.7273	74	0.9762	0.7219	0.9762	0.9880
No log	6.9091	76	0.8461	0.6873	0.8461	0.9198
No log	7.0909	78	0.6379	0.7181	0.6379	0.7987
No log	7.2727	80	0.5480	0.6839	0.5480	0.7403
No log	7.4545	82	0.5355	0.6839	0.5355	0.7318
No log	7.6364	84	0.5699	0.7162	0.5699	0.7549
No log	7.8182	86	0.6654	0.6915	0.6654	0.8157
No log	8.0	88	0.8127	0.7	0.8127	0.9015
No log	8.1818	90	0.8907	0.7	0.8907	0.9438
No log	8.3636	92	0.8716	0.7	0.8716	0.9336
No log	8.5455	94	0.8174	0.72	0.8174	0.9041
No log	8.7273	96	0.7611	0.7336	0.7611	0.8724
No log	8.9091	98	0.7738	0.7336	0.7738	0.8797
No log	9.0909	100	0.7710	0.7336	0.7710	0.8781
No log	9.2727	102	0.7508	0.7336	0.7508	0.8665
No log	9.4545	104	0.7428	0.7336	0.7428	0.8619
No log	9.6364	106	0.7452	0.7336	0.7452	0.8633
No log	9.8182	108	0.7414	0.7336	0.7414	0.8611
No log	10.0	110	0.7406	0.7336	0.7406	0.8606

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu118
• Datasets 2.21.0
• Tokenizers 0.19.1