arabert_cross_organization_task1_fold0

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: 0.6973
• Qwk: 0.4121
• Mse: 0.6973

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	2.5684	0.0116	2.5684
No log	0.2667	4	1.7358	0.0856	1.7358
No log	0.4	6	0.7580	0.1307	0.7580
No log	0.5333	8	1.0787	0.0341	1.0787
No log	0.6667	10	0.9103	0.1678	0.9103
No log	0.8	12	1.1212	0.2241	1.1212
No log	0.9333	14	1.2424	0.2061	1.2424
No log	1.0667	16	0.9462	0.2685	0.9462
No log	1.2	18	0.6233	0.4273	0.6233
No log	1.3333	20	0.5885	0.4743	0.5885
No log	1.4667	22	0.6616	0.3952	0.6616
No log	1.6	24	0.8153	0.3126	0.8153
No log	1.7333	26	0.8278	0.3127	0.8278
No log	1.8667	28	0.6680	0.3884	0.6680
No log	2.0	30	0.5761	0.4959	0.5761
No log	2.1333	32	0.5793	0.4845	0.5793
No log	2.2667	34	0.6288	0.4575	0.6288
No log	2.4	36	0.8037	0.3583	0.8037
No log	2.5333	38	0.9122	0.3147	0.9122
No log	2.6667	40	0.8141	0.3536	0.8141
No log	2.8	42	0.6941	0.3971	0.6941
No log	2.9333	44	0.5685	0.4691	0.5685
No log	3.0667	46	0.5381	0.5160	0.5381
No log	3.2	48	0.5770	0.4617	0.5770
No log	3.3333	50	0.6630	0.4108	0.6630
No log	3.4667	52	0.6155	0.4490	0.6155
No log	3.6	54	0.5977	0.4930	0.5977
No log	3.7333	56	0.6466	0.4721	0.6466
No log	3.8667	58	0.6835	0.4250	0.6835
No log	4.0	60	0.7296	0.3879	0.7296
No log	4.1333	62	0.6819	0.4354	0.6819
No log	4.2667	64	0.5945	0.4884	0.5945
No log	4.4	66	0.5786	0.5050	0.5786
No log	4.5333	68	0.6160	0.4670	0.6160
No log	4.6667	70	0.7401	0.3934	0.7401
No log	4.8	72	0.8433	0.3505	0.8433
No log	4.9333	74	0.7844	0.3718	0.7844
No log	5.0667	76	0.6636	0.4417	0.6636
No log	5.2	78	0.5945	0.4591	0.5945
No log	5.3333	80	0.5972	0.4543	0.5972
No log	5.4667	82	0.6419	0.4316	0.6419
No log	5.6	84	0.6847	0.4354	0.6847
No log	5.7333	86	0.6772	0.4472	0.6772
No log	5.8667	88	0.6758	0.4430	0.6758
No log	6.0	90	0.7271	0.4105	0.7271
No log	6.1333	92	0.8108	0.3650	0.8108
No log	6.2667	94	0.7936	0.3602	0.7936
No log	6.4	96	0.6779	0.4077	0.6779
No log	6.5333	98	0.5967	0.4507	0.5967
No log	6.6667	100	0.5802	0.4695	0.5802
No log	6.8	102	0.6079	0.4518	0.6079
No log	6.9333	104	0.6858	0.4235	0.6858
No log	7.0667	106	0.7702	0.3774	0.7702
No log	7.2	108	0.8119	0.3543	0.8119
No log	7.3333	110	0.7674	0.3774	0.7674
No log	7.4667	112	0.6887	0.4250	0.6887
No log	7.6	114	0.6566	0.4371	0.6566
No log	7.7333	116	0.6477	0.4363	0.6477
No log	7.8667	118	0.6556	0.4276	0.6556
No log	8.0	120	0.6794	0.4219	0.6794
No log	8.1333	122	0.7142	0.4001	0.7142
No log	8.2667	124	0.7342	0.3849	0.7342
No log	8.4	126	0.7384	0.3907	0.7384
No log	8.5333	128	0.7240	0.3993	0.7240
No log	8.6667	130	0.7146	0.4095	0.7146
No log	8.8	132	0.7179	0.4131	0.7179
No log	8.9333	134	0.7112	0.4145	0.7112
No log	9.0667	136	0.7020	0.4168	0.7020
No log	9.2	138	0.7089	0.4124	0.7089
No log	9.3333	140	0.7179	0.4051	0.7179
No log	9.4667	142	0.7143	0.4015	0.7143
No log	9.6	144	0.7043	0.4104	0.7043
No log	9.7333	146	0.6982	0.4121	0.6982
No log	9.8667	148	0.6980	0.4121	0.6980
No log	10.0	150	0.6973	0.4121	0.6973

Framework versions

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