ArabicNewSplits6_FineTuningAraBERT_run3_AugV5_k3_task1_organization

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: 0.5809
• Qwk: 0.7486
• Mse: 0.5809
• Rmse: 0.7622

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	0.1176	2	5.0846	-0.0054	5.0846	2.2549
No log	0.2353	4	2.9215	0.0796	2.9215	1.7092
No log	0.3529	6	2.2312	-0.0727	2.2312	1.4937
No log	0.4706	8	1.9189	0.0312	1.9189	1.3853
No log	0.5882	10	1.2316	0.2394	1.2316	1.1098
No log	0.7059	12	1.8284	0.1210	1.8284	1.3522
No log	0.8235	14	2.0300	0.1378	2.0300	1.4248
No log	0.9412	16	1.3165	0.1698	1.3165	1.1474
No log	1.0588	18	1.0604	0.2370	1.0604	1.0298
No log	1.1765	20	1.1628	0.2040	1.1628	1.0783
No log	1.2941	22	1.0857	0.1839	1.0857	1.0420
No log	1.4118	24	0.9699	0.2761	0.9699	0.9848
No log	1.5294	26	0.9550	0.4330	0.9550	0.9773
No log	1.6471	28	0.9316	0.4789	0.9316	0.9652
No log	1.7647	30	0.9310	0.4579	0.9310	0.9649
No log	1.8824	32	0.9851	0.4543	0.9851	0.9925
No log	2.0	34	1.0213	0.4981	1.0213	1.0106
No log	2.1176	36	1.1710	0.4483	1.1710	1.0821
No log	2.2353	38	1.0630	0.5026	1.0630	1.0310
No log	2.3529	40	0.7961	0.6026	0.7961	0.8922
No log	2.4706	42	0.6829	0.6138	0.6829	0.8264
No log	2.5882	44	0.7190	0.6467	0.7190	0.8479
No log	2.7059	46	0.7345	0.6472	0.7345	0.8570
No log	2.8235	48	0.8543	0.6103	0.8543	0.9243
No log	2.9412	50	1.0043	0.5578	1.0043	1.0021
No log	3.0588	52	0.7794	0.6583	0.7794	0.8829
No log	3.1765	54	0.7556	0.6825	0.7556	0.8693
No log	3.2941	56	0.7753	0.6952	0.7753	0.8805
No log	3.4118	58	0.7160	0.7066	0.7160	0.8462
No log	3.5294	60	0.6196	0.6646	0.6196	0.7871
No log	3.6471	62	0.6189	0.6870	0.6189	0.7867
No log	3.7647	64	0.6083	0.6980	0.6083	0.7799
No log	3.8824	66	0.6949	0.6987	0.6949	0.8336
No log	4.0	68	0.9935	0.5402	0.9935	0.9967
No log	4.1176	70	1.2862	0.4826	1.2862	1.1341
No log	4.2353	72	1.1649	0.5171	1.1649	1.0793
No log	4.3529	74	0.7753	0.6409	0.7753	0.8805
No log	4.4706	76	0.5847	0.7087	0.5847	0.7647
No log	4.5882	78	0.5858	0.7283	0.5858	0.7654
No log	4.7059	80	0.5825	0.7060	0.5825	0.7632
No log	4.8235	82	0.5988	0.7146	0.5988	0.7739
No log	4.9412	84	0.6937	0.7150	0.6937	0.8329
No log	5.0588	86	0.7410	0.6926	0.7410	0.8608
No log	5.1765	88	0.6819	0.7476	0.6819	0.8258
No log	5.2941	90	0.6052	0.7267	0.6052	0.7780
No log	5.4118	92	0.5742	0.7471	0.5742	0.7577
No log	5.5294	94	0.5667	0.7407	0.5667	0.7528
No log	5.6471	96	0.5852	0.7282	0.5852	0.7650
No log	5.7647	98	0.6127	0.7176	0.6127	0.7827
No log	5.8824	100	0.5955	0.7176	0.5955	0.7717
No log	6.0	102	0.5494	0.7572	0.5494	0.7412
No log	6.1176	104	0.5471	0.7532	0.5471	0.7396
No log	6.2353	106	0.5648	0.7601	0.5648	0.7515
No log	6.3529	108	0.6008	0.7023	0.6008	0.7751
No log	6.4706	110	0.5846	0.7062	0.5846	0.7646
No log	6.5882	112	0.5628	0.7545	0.5628	0.7502
No log	6.7059	114	0.5647	0.7623	0.5647	0.7515
No log	6.8235	116	0.5686	0.7660	0.5686	0.7541
No log	6.9412	118	0.6007	0.7382	0.6007	0.7750
No log	7.0588	120	0.6184	0.7287	0.6184	0.7864
No log	7.1765	122	0.5974	0.7417	0.5974	0.7729
No log	7.2941	124	0.5832	0.7555	0.5832	0.7636
No log	7.4118	126	0.5697	0.7543	0.5697	0.7548
No log	7.5294	128	0.5715	0.7543	0.5715	0.7560
No log	7.6471	130	0.5758	0.7572	0.5758	0.7588
No log	7.7647	132	0.5993	0.7399	0.5993	0.7742
No log	7.8824	134	0.6164	0.7178	0.6164	0.7851
No log	8.0	136	0.6078	0.7235	0.6078	0.7796
No log	8.1176	138	0.5796	0.7576	0.5796	0.7613
No log	8.2353	140	0.5705	0.7619	0.5705	0.7553
No log	8.3529	142	0.5721	0.7674	0.5721	0.7564
No log	8.4706	144	0.5685	0.7647	0.5685	0.7540
No log	8.5882	146	0.5724	0.7454	0.5724	0.7566
No log	8.7059	148	0.5876	0.7363	0.5876	0.7665
No log	8.8235	150	0.5940	0.7271	0.5940	0.7707
No log	8.9412	152	0.5863	0.7327	0.5863	0.7657
No log	9.0588	154	0.5729	0.7594	0.5729	0.7569
No log	9.1765	156	0.5682	0.7526	0.5682	0.7538
No log	9.2941	158	0.5676	0.7526	0.5676	0.7534
No log	9.4118	160	0.5695	0.7526	0.5695	0.7546
No log	9.5294	162	0.5724	0.7594	0.5724	0.7566
No log	9.6471	164	0.5769	0.7558	0.5769	0.7596
No log	9.7647	166	0.5804	0.7445	0.5804	0.7619
No log	9.8824	168	0.5812	0.7486	0.5812	0.7624
No log	10.0	170	0.5809	0.7486	0.5809	0.7622

Framework versions

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