arabert_baseline_augmented_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: 0.5936
• Qwk: 0.6341
• Mse: 0.5936
• Rmse: 0.7705

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	0.1333	2	3.0841	0.0302	3.0841	1.7562
No log	0.2667	4	1.4917	-0.0310	1.4917	1.2214
No log	0.4	6	0.8151	0.1901	0.8151	0.9028
No log	0.5333	8	0.7692	0.1355	0.7692	0.8770
No log	0.6667	10	0.6718	0.3913	0.6718	0.8196
No log	0.8	12	0.6380	0.4141	0.6380	0.7987
No log	0.9333	14	0.6826	0.3778	0.6826	0.8262
No log	1.0667	16	0.8820	0.3212	0.8820	0.9391
No log	1.2	18	0.6164	0.4085	0.6164	0.7851
No log	1.3333	20	0.6655	0.5116	0.6655	0.8158
No log	1.4667	22	0.7851	0.5116	0.7851	0.8861
No log	1.6	24	0.6450	0.6354	0.6450	0.8031
No log	1.7333	26	0.5017	0.5581	0.5017	0.7083
No log	1.8667	28	0.9415	0.2524	0.9415	0.9703
No log	2.0	30	0.6734	0.4615	0.6734	0.8206
No log	2.1333	32	0.4050	0.5984	0.4050	0.6364
No log	2.2667	34	0.5873	0.6051	0.5873	0.7663
No log	2.4	36	0.6292	0.6051	0.6292	0.7932
No log	2.5333	38	0.4895	0.6051	0.4895	0.6996
No log	2.6667	40	0.4042	0.4893	0.4042	0.6358
No log	2.8	42	0.4005	0.5543	0.4005	0.6329
No log	2.9333	44	0.4059	0.5977	0.4059	0.6371
No log	3.0667	46	0.4222	0.5468	0.4222	0.6497
No log	3.2	48	0.5120	0.7004	0.5120	0.7155
No log	3.3333	50	0.6828	0.6486	0.6828	0.8263
No log	3.4667	52	0.6311	0.6316	0.6311	0.7944
No log	3.6	54	0.5075	0.5987	0.5075	0.7124
No log	3.7333	56	0.5206	0.5106	0.5206	0.7216
No log	3.8667	58	0.5476	0.5157	0.5476	0.7400
No log	4.0	60	0.4934	0.5205	0.4934	0.7024
No log	4.1333	62	0.5593	0.5751	0.5593	0.7479
No log	4.2667	64	0.8046	0.6883	0.8046	0.8970
No log	4.4	66	0.8289	0.7131	0.8289	0.9104
No log	4.5333	68	0.7470	0.6957	0.7470	0.8643
No log	4.6667	70	0.5733	0.6028	0.5733	0.7572
No log	4.8	72	0.5127	0.5205	0.5127	0.7160
No log	4.9333	74	0.5790	0.5581	0.5790	0.7609
No log	5.0667	76	0.5315	0.5772	0.5315	0.7290
No log	5.2	78	0.4861	0.5611	0.4861	0.6972
No log	5.3333	80	0.6214	0.6172	0.6214	0.7883
No log	5.4667	82	0.7550	0.7131	0.7550	0.8689
No log	5.6	84	0.7349	0.7131	0.7349	0.8572
No log	5.7333	86	0.6173	0.6056	0.6173	0.7857
No log	5.8667	88	0.5064	0.6209	0.5064	0.7116
No log	6.0	90	0.5083	0.5882	0.5083	0.7129
No log	6.1333	92	0.5456	0.5581	0.5456	0.7386
No log	6.2667	94	0.5064	0.5882	0.5064	0.7116
No log	6.4	96	0.4834	0.5576	0.4834	0.6953
No log	6.5333	98	0.5811	0.6341	0.5811	0.7623
No log	6.6667	100	0.6637	0.6818	0.6637	0.8147
No log	6.8	102	0.6741	0.6067	0.6741	0.8210
No log	6.9333	104	0.6070	0.6067	0.6070	0.7791
No log	7.0667	106	0.5169	0.6525	0.5169	0.7190
No log	7.2	108	0.4812	0.6465	0.4812	0.6937
No log	7.3333	110	0.4903	0.6879	0.4903	0.7002
No log	7.4667	112	0.5035	0.6405	0.5035	0.7096
No log	7.6	114	0.5003	0.6879	0.5003	0.7073
No log	7.7333	116	0.5243	0.7016	0.5243	0.7241
No log	7.8667	118	0.5949	0.6776	0.5949	0.7713
No log	8.0	120	0.6398	0.6341	0.6398	0.7999
No log	8.1333	122	0.6353	0.6341	0.6353	0.7970
No log	8.2667	124	0.6012	0.6341	0.6012	0.7754
No log	8.4	126	0.5564	0.6957	0.5564	0.7459
No log	8.5333	128	0.5379	0.6957	0.5379	0.7334
No log	8.6667	130	0.5384	0.6525	0.5384	0.7338
No log	8.8	132	0.5411	0.6525	0.5411	0.7356
No log	8.9333	134	0.5647	0.6449	0.5647	0.7514
No log	9.0667	136	0.5841	0.6341	0.5841	0.7643
No log	9.2	138	0.5972	0.6341	0.5972	0.7728
No log	9.3333	140	0.5998	0.6341	0.5998	0.7745
No log	9.4667	142	0.5996	0.6341	0.5996	0.7743
No log	9.6	144	0.6022	0.6341	0.6022	0.7760
No log	9.7333	146	0.5983	0.6341	0.5983	0.7735
No log	9.8667	148	0.5937	0.6341	0.5937	0.7705
No log	10.0	150	0.5936	0.6341	0.5936	0.7705

Framework versions

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