arabert_cross_organization_task2_fold3

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: 0.5676
• Qwk: 0.8167
• Mse: 0.5676

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: 64
• eval_batch_size: 64
• 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
No log	0.1333	2	1.8692	0.1353	1.8692
No log	0.2667	4	1.4213	0.1397	1.4213
No log	0.4	6	1.4691	0.3731	1.4691
No log	0.5333	8	1.1350	0.5085	1.1350
No log	0.6667	10	1.0589	0.4468	1.0589
No log	0.8	12	0.6836	0.7114	0.6836
No log	0.9333	14	0.7934	0.7564	0.7934
No log	1.0667	16	0.6366	0.7754	0.6366
No log	1.2	18	0.6294	0.6090	0.6294
No log	1.3333	20	0.5984	0.6582	0.5984
No log	1.4667	22	0.6612	0.7573	0.6612
No log	1.6	24	0.6149	0.7707	0.6149
No log	1.7333	26	0.5768	0.7921	0.5768
No log	1.8667	28	0.5478	0.7836	0.5478
No log	2.0	30	0.6323	0.7873	0.6323
No log	2.1333	32	0.7541	0.7799	0.7541
No log	2.2667	34	0.5899	0.7730	0.5899
No log	2.4	36	0.5646	0.7204	0.5646
No log	2.5333	38	0.5812	0.7665	0.5812
No log	2.6667	40	0.7559	0.7804	0.7559
No log	2.8	42	0.6782	0.7852	0.6782
No log	2.9333	44	0.5336	0.7721	0.5336
No log	3.0667	46	0.5156	0.7461	0.5156
No log	3.2	48	0.5374	0.7842	0.5374
No log	3.3333	50	0.6264	0.7999	0.6264
No log	3.4667	52	0.8571	0.7933	0.8571
No log	3.6	54	0.7545	0.8124	0.7545
No log	3.7333	56	0.5238	0.7922	0.5238
No log	3.8667	58	0.4796	0.7536	0.4796
No log	4.0	60	0.4953	0.7964	0.4953
No log	4.1333	62	0.6345	0.7733	0.6345
No log	4.2667	64	0.7544	0.7901	0.7544
No log	4.4	66	0.6943	0.7949	0.6943
No log	4.5333	68	0.5528	0.8088	0.5528
No log	4.6667	70	0.4774	0.7978	0.4774
No log	4.8	72	0.5067	0.7997	0.5067
No log	4.9333	74	0.6779	0.8166	0.6779
No log	5.0667	76	0.7490	0.8085	0.7490
No log	5.2	78	0.6112	0.8038	0.6112
No log	5.3333	80	0.5181	0.7860	0.5181
No log	5.4667	82	0.5173	0.7861	0.5173
No log	5.6	84	0.5810	0.8108	0.5810
No log	5.7333	86	0.6378	0.8013	0.6378
No log	5.8667	88	0.7117	0.8099	0.7117
No log	6.0	90	0.6295	0.8118	0.6295
No log	6.1333	92	0.5548	0.8052	0.5548
No log	6.2667	94	0.5066	0.7699	0.5066
No log	6.4	96	0.5174	0.7849	0.5174
No log	6.5333	98	0.6036	0.8042	0.6036
No log	6.6667	100	0.7393	0.8146	0.7393
No log	6.8	102	0.7344	0.8098	0.7344
No log	6.9333	104	0.6184	0.8121	0.6184
No log	7.0667	106	0.5416	0.7974	0.5416
No log	7.2	108	0.5343	0.7929	0.5343
No log	7.3333	110	0.5632	0.8094	0.5632
No log	7.4667	112	0.5781	0.8097	0.5781
No log	7.6	114	0.6404	0.8068	0.6404
No log	7.7333	116	0.6828	0.8187	0.6828
No log	7.8667	118	0.6504	0.8045	0.6504
No log	8.0	120	0.5838	0.8057	0.5838
No log	8.1333	122	0.5378	0.8062	0.5378
No log	8.2667	124	0.5466	0.8079	0.5466
No log	8.4	126	0.5939	0.8052	0.5939
No log	8.5333	128	0.6680	0.8023	0.6680
No log	8.6667	130	0.6894	0.8051	0.6894
No log	8.8	132	0.6689	0.8044	0.6689
No log	8.9333	134	0.6450	0.8040	0.6450
No log	9.0667	136	0.5946	0.8173	0.5946
No log	9.2	138	0.5617	0.8132	0.5617
No log	9.3333	140	0.5493	0.8151	0.5493
No log	9.4667	142	0.5410	0.8105	0.5410
No log	9.6	144	0.5422	0.8142	0.5422
No log	9.7333	146	0.5512	0.8086	0.5512
No log	9.8667	148	0.5620	0.8148	0.5620
No log	10.0	150	0.5676	0.8167	0.5676

Framework versions

• Transformers 4.44.0
• Pytorch 2.4.0
• Datasets 2.21.0
• Tokenizers 0.19.1