ArabicNewSplits6_FineTuningAraBERT_run2_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: 0.6337
• Qwk: 0.7280
• Mse: 0.6337
• Rmse: 0.7961

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	5.1900	-0.0378	5.1900	2.2782
No log	0.2353	4	2.7310	0.1164	2.7310	1.6526
No log	0.3529	6	1.6405	0.1199	1.6405	1.2808
No log	0.4706	8	1.1859	0.2581	1.1859	1.0890
No log	0.5882	10	1.0294	0.3102	1.0294	1.0146
No log	0.7059	12	1.0035	0.3452	1.0035	1.0018
No log	0.8235	14	1.2427	0.3217	1.2427	1.1148
No log	0.9412	16	1.4889	0.1665	1.4889	1.2202
No log	1.0588	18	1.8590	0.1624	1.8590	1.3634
No log	1.1765	20	1.6036	0.1922	1.6036	1.2664
No log	1.2941	22	1.1767	0.3144	1.1767	1.0848
No log	1.4118	24	0.8960	0.4614	0.8960	0.9466
No log	1.5294	26	1.0426	0.4985	1.0426	1.0211
No log	1.6471	28	1.6708	0.2429	1.6708	1.2926
No log	1.7647	30	2.0938	0.2329	2.0938	1.4470
No log	1.8824	32	1.8920	0.2320	1.8920	1.3755
No log	2.0	34	1.3415	0.4196	1.3415	1.1582
No log	2.1176	36	0.8091	0.5055	0.8091	0.8995
No log	2.2353	38	0.8338	0.5090	0.8338	0.9131
No log	2.3529	40	0.8496	0.5279	0.8496	0.9217
No log	2.4706	42	0.7863	0.5485	0.7863	0.8867
No log	2.5882	44	0.7064	0.6031	0.7064	0.8405
No log	2.7059	46	0.6445	0.6327	0.6445	0.8028
No log	2.8235	48	0.6494	0.6621	0.6494	0.8059
No log	2.9412	50	0.7477	0.5985	0.7477	0.8647
No log	3.0588	52	0.8027	0.5909	0.8027	0.8959
No log	3.1765	54	0.7203	0.6595	0.7203	0.8487
No log	3.2941	56	0.6533	0.7183	0.6533	0.8083
No log	3.4118	58	0.6979	0.6641	0.6979	0.8354
No log	3.5294	60	0.7569	0.6654	0.7569	0.8700
No log	3.6471	62	0.6779	0.7187	0.6779	0.8233
No log	3.7647	64	0.6967	0.7063	0.6967	0.8347
No log	3.8824	66	0.9595	0.5856	0.9595	0.9796
No log	4.0	68	0.9952	0.5480	0.9952	0.9976
No log	4.1176	70	0.7720	0.6858	0.7720	0.8786
No log	4.2353	72	0.6374	0.7584	0.6374	0.7984
No log	4.3529	74	0.7774	0.6516	0.7774	0.8817
No log	4.4706	76	0.8485	0.6318	0.8485	0.9211
No log	4.5882	78	0.7677	0.6977	0.7677	0.8762
No log	4.7059	80	0.6427	0.7340	0.6427	0.8017
No log	4.8235	82	0.7606	0.6670	0.7606	0.8721
No log	4.9412	84	0.9762	0.5388	0.9762	0.9880
No log	5.0588	86	0.9779	0.5188	0.9779	0.9889
No log	5.1765	88	0.8004	0.6217	0.8004	0.8946
No log	5.2941	90	0.6151	0.7076	0.6151	0.7843
No log	5.4118	92	0.6094	0.7371	0.6094	0.7807
No log	5.5294	94	0.6705	0.6956	0.6705	0.8189
No log	5.6471	96	0.6405	0.6837	0.6405	0.8003
No log	5.7647	98	0.5844	0.7361	0.5844	0.7644
No log	5.8824	100	0.5785	0.7323	0.5785	0.7606
No log	6.0	102	0.5827	0.7264	0.5827	0.7633
No log	6.1176	104	0.6032	0.6981	0.6032	0.7767
No log	6.2353	106	0.5939	0.7208	0.5939	0.7706
No log	6.3529	108	0.5922	0.7322	0.5922	0.7695
No log	6.4706	110	0.6130	0.7441	0.6130	0.7829
No log	6.5882	112	0.6355	0.7251	0.6355	0.7972
No log	6.7059	114	0.6099	0.7555	0.6099	0.7810
No log	6.8235	116	0.6284	0.7206	0.6284	0.7927
No log	6.9412	118	0.6745	0.6955	0.6745	0.8213
No log	7.0588	120	0.6566	0.6849	0.6566	0.8103
No log	7.1765	122	0.6270	0.7402	0.6270	0.7919
No log	7.2941	124	0.6245	0.7412	0.6245	0.7903
No log	7.4118	126	0.6240	0.7412	0.6240	0.7900
No log	7.5294	128	0.6302	0.7511	0.6302	0.7938
No log	7.6471	130	0.6469	0.7423	0.6469	0.8043
No log	7.7647	132	0.6531	0.7382	0.6531	0.8082
No log	7.8824	134	0.6451	0.7429	0.6451	0.8032
No log	8.0	136	0.6457	0.7420	0.6457	0.8036
No log	8.1176	138	0.6464	0.7081	0.6464	0.8040
No log	8.2353	140	0.6565	0.7117	0.6565	0.8102
No log	8.3529	142	0.6834	0.6867	0.6834	0.8267
No log	8.4706	144	0.6967	0.6830	0.6967	0.8347
No log	8.5882	146	0.6911	0.6842	0.6911	0.8313
No log	8.7059	148	0.6640	0.6947	0.6640	0.8149
No log	8.8235	150	0.6553	0.6977	0.6553	0.8095
No log	8.9412	152	0.6460	0.7270	0.6460	0.8037
No log	9.0588	154	0.6424	0.7156	0.6424	0.8015
No log	9.1765	156	0.6439	0.7289	0.6439	0.8024
No log	9.2941	158	0.6445	0.7368	0.6445	0.8028
No log	9.4118	160	0.6422	0.7368	0.6422	0.8014
No log	9.5294	162	0.6392	0.7353	0.6392	0.7995
No log	9.6471	164	0.6370	0.7274	0.6370	0.7981
No log	9.7647	166	0.6354	0.7274	0.6354	0.7971
No log	9.8824	168	0.6341	0.7274	0.6341	0.7963
No log	10.0	170	0.6337	0.7280	0.6337	0.7961

Framework versions

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