arabert_cross_organization_task7_fold1

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: 1.0235
• Qwk: 0.3186
• Mse: 1.0235

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	4.5492	0.0033	4.5492
No log	0.2667	4	2.3313	0.0265	2.3313
No log	0.4	6	0.9380	0.1593	0.9380
No log	0.5333	8	0.7299	0.3211	0.7299
No log	0.6667	10	1.0765	0.2403	1.0765
No log	0.8	12	0.9948	0.2992	0.9948
No log	0.9333	14	0.7246	0.3691	0.7246
No log	1.0667	16	0.8317	0.3374	0.8317
No log	1.2	18	1.1310	0.2565	1.1310
No log	1.3333	20	0.8172	0.3590	0.8172
No log	1.4667	22	0.6362	0.4637	0.6362
No log	1.6	24	0.7141	0.4179	0.7141
No log	1.7333	26	0.8099	0.3916	0.8099
No log	1.8667	28	0.8171	0.3801	0.8171
No log	2.0	30	0.6256	0.4325	0.6256
No log	2.1333	32	0.6044	0.4368	0.6044
No log	2.2667	34	0.6559	0.4218	0.6559
No log	2.4	36	0.6944	0.4358	0.6944
No log	2.5333	38	0.8347	0.3992	0.8347
No log	2.6667	40	0.7015	0.4476	0.7015
No log	2.8	42	0.5980	0.4984	0.5980
No log	2.9333	44	0.6999	0.4162	0.6999
No log	3.0667	46	0.9852	0.3253	0.9852
No log	3.2	48	0.8781	0.3521	0.8781
No log	3.3333	50	0.6081	0.4705	0.6081
No log	3.4667	52	0.5650	0.5161	0.5650
No log	3.6	54	0.6909	0.4496	0.6909
No log	3.7333	56	0.9750	0.3479	0.9750
No log	3.8667	58	1.0120	0.3345	1.0120
No log	4.0	60	0.7745	0.3864	0.7745
No log	4.1333	62	0.5602	0.4789	0.5602
No log	4.2667	64	0.5317	0.5191	0.5317
No log	4.4	66	0.6043	0.4530	0.6043
No log	4.5333	68	0.9138	0.3450	0.9138
No log	4.6667	70	1.0543	0.2899	1.0543
No log	4.8	72	0.9173	0.3364	0.9173
No log	4.9333	74	0.6723	0.4180	0.6723
No log	5.0667	76	0.6232	0.4325	0.6232
No log	5.2	78	0.7547	0.3914	0.7547
No log	5.3333	80	0.9923	0.3422	0.9923
No log	5.4667	82	1.1410	0.3118	1.1410
No log	5.6	84	0.9779	0.3534	0.9779
No log	5.7333	86	0.8238	0.4080	0.8238
No log	5.8667	88	0.8201	0.4073	0.8201
No log	6.0	90	0.9149	0.3516	0.9149
No log	6.1333	92	1.0529	0.3263	1.0529
No log	6.2667	94	1.0383	0.3165	1.0383
No log	6.4	96	0.9200	0.3612	0.9200
No log	6.5333	98	0.8061	0.3776	0.8061
No log	6.6667	100	0.8442	0.3648	0.8442
No log	6.8	102	0.8632	0.3618	0.8632
No log	6.9333	104	0.8772	0.3675	0.8772
No log	7.0667	106	0.9942	0.3310	0.9942
No log	7.2	108	1.0411	0.3115	1.0411
No log	7.3333	110	0.9094	0.3720	0.9094
No log	7.4667	112	0.8811	0.3764	0.8811
No log	7.6	114	0.9874	0.3393	0.9874
No log	7.7333	116	1.1141	0.2953	1.1141
No log	7.8667	118	1.1732	0.2682	1.1732
No log	8.0	120	1.2079	0.2587	1.2079
No log	8.1333	122	1.1465	0.2875	1.1465
No log	8.2667	124	1.0235	0.3252	1.0235
No log	8.4	126	0.9569	0.3373	0.9569
No log	8.5333	128	0.9933	0.3246	0.9933
No log	8.6667	130	1.0961	0.2757	1.0961
No log	8.8	132	1.2178	0.2280	1.2178
No log	8.9333	134	1.2733	0.2266	1.2733
No log	9.0667	136	1.3165	0.2226	1.3165
No log	9.2	138	1.2781	0.2220	1.2781
No log	9.3333	140	1.2042	0.2320	1.2042
No log	9.4667	142	1.1543	0.2486	1.1543
No log	9.6	144	1.0986	0.2779	1.0986
No log	9.7333	146	1.0621	0.2914	1.0621
No log	9.8667	148	1.0338	0.3043	1.0338
No log	10.0	150	1.0235	0.3186	1.0235

Framework versions

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