arabert_cross_organization_task5_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: 1.2242
• Qwk: 0.1257
• Mse: 1.2242

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	0.1176	2	4.3828	-0.0124	4.3828
No log	0.2353	4	1.7251	0.0041	1.7251
No log	0.3529	6	1.2217	0.0734	1.2217
No log	0.4706	8	1.1541	-0.0141	1.1541
No log	0.5882	10	1.1775	-0.0461	1.1775
No log	0.7059	12	1.1336	0.0379	1.1336
No log	0.8235	14	1.1142	0.0423	1.1142
No log	0.9412	16	1.1059	0.0379	1.1059
No log	1.0588	18	1.1059	0.0924	1.1059
No log	1.1765	20	1.1052	0.0709	1.1052
No log	1.2941	22	1.1261	0.0646	1.1261
No log	1.4118	24	1.1338	0.0829	1.1338
No log	1.5294	26	1.1439	0.0944	1.1439
No log	1.6471	28	1.1713	0.0036	1.1713
No log	1.7647	30	1.3086	0.0105	1.3086
No log	1.8824	32	1.5561	-0.0786	1.5561
No log	2.0	34	1.4534	-0.0609	1.4534
No log	2.1176	36	1.2239	0.0407	1.2239
No log	2.2353	38	1.1711	0.0291	1.1711
No log	2.3529	40	1.1836	0.0190	1.1836
No log	2.4706	42	1.1290	0.0963	1.1290
No log	2.5882	44	1.1464	0.0201	1.1464
No log	2.7059	46	1.1366	0.0472	1.1366
No log	2.8235	48	1.1635	0.0397	1.1635
No log	2.9412	50	1.1571	0.0835	1.1571
No log	3.0588	52	1.1920	0.0170	1.1920
No log	3.1765	54	1.1867	0.0170	1.1867
No log	3.2941	56	1.1690	0.0502	1.1690
No log	3.4118	58	1.2051	-0.0577	1.2051
No log	3.5294	60	1.1905	0.0665	1.1905
No log	3.6471	62	1.2133	0.0774	1.2133
No log	3.7647	64	1.2200	0.0563	1.2200
No log	3.8824	66	1.3632	-0.0355	1.3632
No log	4.0	68	1.4047	-0.0128	1.4047
No log	4.1176	70	1.2417	-0.0439	1.2417
No log	4.2353	72	1.1986	0.0762	1.1986
No log	4.3529	74	1.2413	0.0193	1.2413
No log	4.4706	76	1.2285	0.0197	1.2285
No log	4.5882	78	1.1521	0.0963	1.1521
No log	4.7059	80	1.1339	0.1452	1.1339
No log	4.8235	82	1.1310	0.1751	1.1310
No log	4.9412	84	1.1433	0.1167	1.1433
No log	5.0588	86	1.1588	0.1167	1.1588
No log	5.1765	88	1.1625	0.0800	1.1625
No log	5.2941	90	1.1773	0.0762	1.1773
No log	5.4118	92	1.2029	0.0692	1.2029
No log	5.5294	94	1.2328	0.0544	1.2328
No log	5.6471	96	1.2678	0.0635	1.2678
No log	5.7647	98	1.2562	0.0948	1.2562
No log	5.8824	100	1.2431	-0.0243	1.2431
No log	6.0	102	1.2165	-0.0191	1.2165
No log	6.1176	104	1.1810	0.0583	1.1810
No log	6.2353	106	1.1655	0.1009	1.1655
No log	6.3529	108	1.1492	0.1282	1.1492
No log	6.4706	110	1.1516	0.1082	1.1516
No log	6.5882	112	1.1420	0.1282	1.1420
No log	6.7059	114	1.1429	0.0909	1.1429
No log	6.8235	116	1.1601	0.0759	1.1601
No log	6.9412	118	1.1970	0.0482	1.1970
No log	7.0588	120	1.2180	0.0284	1.2180
No log	7.1765	122	1.1913	0.1109	1.1913
No log	7.2941	124	1.2011	0.1239	1.2011
No log	7.4118	126	1.2142	0.1239	1.2142
No log	7.5294	128	1.2462	0.0357	1.2462
No log	7.6471	130	1.2906	0.0199	1.2906
No log	7.7647	132	1.2722	0.0275	1.2722
No log	7.8824	134	1.2418	0.1080	1.2418
No log	8.0	136	1.2319	0.1080	1.2319
No log	8.1176	138	1.2288	0.0696	1.2288
No log	8.2353	140	1.2238	0.0833	1.2238
No log	8.3529	142	1.2114	0.0882	1.2114
No log	8.4706	144	1.2083	0.0747	1.2083
No log	8.5882	146	1.2039	0.0815	1.2039
No log	8.7059	148	1.2096	0.0882	1.2096
No log	8.8235	150	1.2230	0.0814	1.2230
No log	8.9412	152	1.2411	0.0429	1.2411
No log	9.0588	154	1.2602	0.0549	1.2602
No log	9.1765	156	1.2709	0.0659	1.2709
No log	9.2941	158	1.2729	0.0141	1.2729
No log	9.4118	160	1.2582	0.0024	1.2582
No log	9.5294	162	1.2378	0.1169	1.2378
No log	9.6471	164	1.2260	0.1065	1.2260
No log	9.7647	166	1.2223	0.1257	1.2223
No log	9.8824	168	1.2232	0.1257	1.2232
No log	10.0	170	1.2242	0.1257	1.2242

Framework versions

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