ArabicNewSplits4_WithDuplicationsForScore5_FineTuningAraBERT_run3_AugV5_k2_task3_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: 0.8961
• Qwk: 0.2258
• Mse: 0.8961
• Rmse: 0.9466

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	0.1667	2	3.5466	-0.0066	3.5466	1.8832
No log	0.3333	4	1.9614	-0.0370	1.9614	1.4005
No log	0.5	6	1.0359	0.0118	1.0359	1.0178
No log	0.6667	8	0.8280	0.1515	0.8280	0.9100
No log	0.8333	10	0.5973	0.2418	0.5973	0.7729
No log	1.0	12	0.5649	0.0476	0.5649	0.7516
No log	1.1667	14	0.7553	0.0080	0.7553	0.8691
No log	1.3333	16	0.7238	0.0080	0.7238	0.8507
No log	1.5	18	0.6471	0.0	0.6471	0.8045
No log	1.6667	20	0.5891	0.0	0.5891	0.7675
No log	1.8333	22	0.5679	-0.0081	0.5679	0.7536
No log	2.0	24	0.6321	0.2350	0.6321	0.7951
No log	2.1667	26	0.7411	0.0918	0.7411	0.8609
No log	2.3333	28	0.7004	0.1919	0.7004	0.8369
No log	2.5	30	0.5895	0.2308	0.5895	0.7678
No log	2.6667	32	0.6599	0.0	0.6599	0.8124
No log	2.8333	34	0.7185	-0.0732	0.7185	0.8477
No log	3.0	36	0.6905	0.0	0.6905	0.8310
No log	3.1667	38	0.5802	-0.0233	0.5802	0.7617
No log	3.3333	40	0.6392	0.2184	0.6392	0.7995
No log	3.5	42	0.9461	0.0476	0.9461	0.9727
No log	3.6667	44	0.7687	0.1841	0.7687	0.8767
No log	3.8333	46	0.5934	0.1020	0.5934	0.7703
No log	4.0	48	0.6642	0.0769	0.6642	0.8150
No log	4.1667	50	0.6333	0.0728	0.6333	0.7958
No log	4.3333	52	0.6440	0.0769	0.6440	0.8025
No log	4.5	54	0.5927	0.1020	0.5927	0.7698
No log	4.6667	56	0.5996	0.3103	0.5996	0.7743
No log	4.8333	58	0.5805	0.0850	0.5805	0.7619
No log	5.0	60	0.6368	0.1304	0.6368	0.7980
No log	5.1667	62	0.6367	0.1304	0.6367	0.7980
No log	5.3333	64	0.6430	0.2189	0.6430	0.8018
No log	5.5	66	0.7208	0.2233	0.7208	0.8490
No log	5.6667	68	0.6954	0.2811	0.6954	0.8339
No log	5.8333	70	0.6357	0.3469	0.6357	0.7973
No log	6.0	72	0.6878	0.3363	0.6878	0.8294
No log	6.1667	74	0.7794	0.1730	0.7794	0.8828
No log	6.3333	76	0.7753	0.2333	0.7753	0.8805
No log	6.5	78	0.8034	0.2405	0.8034	0.8963
No log	6.6667	80	0.9183	0.2353	0.9183	0.9583
No log	6.8333	82	0.9604	0.2353	0.9604	0.9800
No log	7.0	84	1.0027	0.2340	1.0027	1.0014
No log	7.1667	86	1.0048	0.2340	1.0048	1.0024
No log	7.3333	88	1.1169	0.1515	1.1169	1.0568
No log	7.5	90	1.1196	0.1788	1.1196	1.0581
No log	7.6667	92	0.9666	0.2659	0.9666	0.9832
No log	7.8333	94	0.8605	0.2605	0.8605	0.9276
No log	8.0	96	0.9082	0.2314	0.9082	0.9530
No log	8.1667	98	1.0503	0.2340	1.0503	1.0248
No log	8.3333	100	1.0919	0.1781	1.0919	1.0450
No log	8.5	102	1.2139	0.1304	1.2139	1.1018
No log	8.6667	104	1.2956	0.1373	1.2956	1.1382
No log	8.8333	106	1.2810	0.1362	1.2810	1.1318
No log	9.0	108	1.1861	0.1523	1.1861	1.0891
No log	9.1667	110	1.0801	0.2347	1.0801	1.0393
No log	9.3333	112	0.9878	0.2296	0.9878	0.9939
No log	9.5	114	0.9215	0.2558	0.9215	0.9600
No log	9.6667	116	0.8899	0.2263	0.8899	0.9433
No log	9.8333	118	0.8899	0.2263	0.8899	0.9433
No log	10.0	120	0.8961	0.2258	0.8961	0.9466

Framework versions

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