ArabicNewSplits5_FineTuningAraBERT_run2_AugV5_k3_task5_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: 0.6613
• Qwk: 0.7805
• Mse: 0.6613
• Rmse: 0.8132

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	2.3670	0.0017	2.3670	1.5385
No log	0.2353	4	1.5832	0.1655	1.5832	1.2582
No log	0.3529	6	1.2982	0.2295	1.2982	1.1394
No log	0.4706	8	1.2988	0.2073	1.2988	1.1397
No log	0.5882	10	1.3106	0.1968	1.3106	1.1448
No log	0.7059	12	1.3561	0.2489	1.3561	1.1645
No log	0.8235	14	1.6245	0.3610	1.6245	1.2745
No log	0.9412	16	1.5951	0.2916	1.5951	1.2630
No log	1.0588	18	1.5240	0.0848	1.5240	1.2345
No log	1.1765	20	1.3580	0.0848	1.3580	1.1653
No log	1.2941	22	1.2612	0.2061	1.2612	1.1230
No log	1.4118	24	1.2934	0.2600	1.2934	1.1373
No log	1.5294	26	1.2421	0.1952	1.2421	1.1145
No log	1.6471	28	1.1793	0.1682	1.1793	1.0859
No log	1.7647	30	1.1269	0.2781	1.1269	1.0615
No log	1.8824	32	1.0944	0.2991	1.0944	1.0462
No log	2.0	34	1.0596	0.3843	1.0596	1.0294
No log	2.1176	36	1.0473	0.4005	1.0473	1.0234
No log	2.2353	38	1.0269	0.3950	1.0269	1.0133
No log	2.3529	40	1.0358	0.3551	1.0358	1.0178
No log	2.4706	42	0.9960	0.4473	0.9960	0.9980
No log	2.5882	44	0.9529	0.4771	0.9529	0.9762
No log	2.7059	46	0.9043	0.5291	0.9043	0.9509
No log	2.8235	48	0.8291	0.6239	0.8291	0.9106
No log	2.9412	50	0.7733	0.6488	0.7733	0.8794
No log	3.0588	52	0.7214	0.6468	0.7214	0.8494
No log	3.1765	54	0.6894	0.7035	0.6894	0.8303
No log	3.2941	56	0.7178	0.6804	0.7178	0.8472
No log	3.4118	58	0.7292	0.7055	0.7292	0.8539
No log	3.5294	60	0.7603	0.6743	0.7603	0.8719
No log	3.6471	62	0.8099	0.7030	0.8099	0.8999
No log	3.7647	64	0.9092	0.6722	0.9092	0.9535
No log	3.8824	66	0.8899	0.6826	0.8899	0.9433
No log	4.0	68	0.9596	0.6449	0.9596	0.9796
No log	4.1176	70	0.8412	0.6887	0.8412	0.9171
No log	4.2353	72	0.7680	0.7252	0.7680	0.8764
No log	4.3529	74	0.7230	0.7348	0.7230	0.8503
No log	4.4706	76	0.7685	0.7352	0.7685	0.8766
No log	4.5882	78	0.8730	0.6728	0.8730	0.9343
No log	4.7059	80	0.8249	0.6889	0.8249	0.9083
No log	4.8235	82	0.8451	0.6979	0.8451	0.9193
No log	4.9412	84	1.0396	0.6545	1.0396	1.0196
No log	5.0588	86	1.3244	0.5789	1.3244	1.1508
No log	5.1765	88	1.2233	0.6070	1.2233	1.1060
No log	5.2941	90	0.8972	0.6871	0.8972	0.9472
No log	5.4118	92	0.6811	0.7483	0.6811	0.8253
No log	5.5294	94	0.6679	0.7661	0.6679	0.8173
No log	5.6471	96	0.6714	0.7541	0.6714	0.8194
No log	5.7647	98	0.7619	0.7339	0.7619	0.8728
No log	5.8824	100	0.7734	0.7339	0.7734	0.8794
No log	6.0	102	0.7271	0.7467	0.7271	0.8527
No log	6.1176	104	0.7070	0.7535	0.7070	0.8409
No log	6.2353	106	0.6800	0.7619	0.6800	0.8246
No log	6.3529	108	0.7012	0.7577	0.7012	0.8374
No log	6.4706	110	0.7154	0.7398	0.7154	0.8458
No log	6.5882	112	0.6442	0.7872	0.6442	0.8026
No log	6.7059	114	0.6171	0.7628	0.6171	0.7856
No log	6.8235	116	0.6198	0.7702	0.6198	0.7873
No log	6.9412	118	0.6473	0.7872	0.6473	0.8046
No log	7.0588	120	0.7625	0.7425	0.7625	0.8732
No log	7.1765	122	0.8467	0.7263	0.8467	0.9201
No log	7.2941	124	0.8229	0.7320	0.8229	0.9071
No log	7.4118	126	0.7513	0.7463	0.7513	0.8668
No log	7.5294	128	0.6936	0.7692	0.6936	0.8328
No log	7.6471	130	0.6410	0.7764	0.6410	0.8006
No log	7.7647	132	0.6250	0.7805	0.6250	0.7905
No log	7.8824	134	0.6544	0.7764	0.6544	0.8089
No log	8.0	136	0.7394	0.7405	0.7394	0.8599
No log	8.1176	138	0.7840	0.7228	0.7840	0.8854
No log	8.2353	140	0.7718	0.7154	0.7718	0.8785
No log	8.3529	142	0.7329	0.7580	0.7329	0.8561
No log	8.4706	144	0.6685	0.7644	0.6685	0.8176
No log	8.5882	146	0.6322	0.7733	0.6322	0.7951
No log	8.7059	148	0.6051	0.7801	0.6051	0.7779
No log	8.8235	150	0.5913	0.7861	0.5913	0.7690
No log	8.9412	152	0.5958	0.7861	0.5958	0.7719
No log	9.0588	154	0.5966	0.7861	0.5966	0.7724
No log	9.1765	156	0.6065	0.7898	0.6065	0.7788
No log	9.2941	158	0.6215	0.7872	0.6215	0.7883
No log	9.4118	160	0.6298	0.7926	0.6298	0.7936
No log	9.5294	162	0.6343	0.7926	0.6343	0.7964
No log	9.6471	164	0.6414	0.7805	0.6414	0.8009
No log	9.7647	166	0.6504	0.7805	0.6504	0.8065
No log	9.8824	168	0.6584	0.7805	0.6584	0.8114
No log	10.0	170	0.6613	0.7805	0.6613	0.8132

Framework versions

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