arabert_cross_relevance_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: 0.2694
Qwk: 0.0109
Mse: 0.2694

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	2.2712	0.0	2.2712
No log	0.2667	4	0.8815	0.0019	0.8815
No log	0.4	6	0.2576	0.0339	0.2576
No log	0.5333	8	0.2104	0.0276	0.2104
No log	0.6667	10	0.3374	0.0345	0.3374
No log	0.8	12	0.2690	0.0323	0.2690
No log	0.9333	14	0.1682	0.0249	0.1682
No log	1.0667	16	0.1503	0.0339	0.1503
No log	1.2	18	0.1672	0.0339	0.1672
No log	1.3333	20	0.2563	0.0263	0.2563
No log	1.4667	22	0.3596	0.0519	0.3596
No log	1.6	24	0.3144	0.0507	0.3144
No log	1.7333	26	0.1940	0.0263	0.1940
No log	1.8667	28	0.1460	0.0400	0.1460
No log	2.0	30	0.1369	0.0364	0.1369
No log	2.1333	32	0.1324	0.0372	0.1324
No log	2.2667	34	0.1415	0.0339	0.1415
No log	2.4	36	0.1809	0.0339	0.1809
No log	2.5333	38	0.2294	0.0339	0.2294
No log	2.6667	40	0.2654	0.0281	0.2654
No log	2.8	42	0.2940	0.0245	0.2940
No log	2.9333	44	0.2676	0.0245	0.2676
No log	3.0667	46	0.2359	0.0245	0.2359
No log	3.2	48	0.2040	0.0263	0.2040
No log	3.3333	50	0.1696	0.0300	0.1696
No log	3.4667	52	0.1616	0.0339	0.1616
No log	3.6	54	0.1702	0.0319	0.1702
No log	3.7333	56	0.2010	0.0281	0.2010
No log	3.8667	58	0.2570	0.0228	0.2570
No log	4.0	60	0.3107	0.0327	0.3107
No log	4.1333	62	0.3132	0.0327	0.3132
No log	4.2667	64	0.2646	0.0288	0.2646
No log	4.4	66	0.2086	0.0263	0.2086
No log	4.5333	68	0.1708	0.0300	0.1708
No log	4.6667	70	0.1646	0.0179	0.1646
No log	4.8	72	0.1786	0.0144	0.1786
No log	4.9333	74	0.2198	0.0281	0.2198
No log	5.0667	76	0.2585	0.0245	0.2585
No log	5.2	78	0.2513	0.0263	0.2513
No log	5.3333	80	0.2441	0.0263	0.2441
No log	5.4667	82	0.2186	0.0197	0.2186
No log	5.6	84	0.2061	0.0197	0.2061
No log	5.7333	86	0.2178	0.0197	0.2178
No log	5.8667	88	0.2322	0.0197	0.2322
No log	6.0	90	0.2425	0.0245	0.2425
No log	6.1333	92	0.2585	0.0245	0.2585
No log	6.2667	94	0.2369	0.0195	0.2369
No log	6.4	96	0.2110	0.0158	0.2110
No log	6.5333	98	0.2006	0.0158	0.2006
No log	6.6667	100	0.2175	0.0158	0.2175
No log	6.8	102	0.2464	0.0210	0.2464
No log	6.9333	104	0.2615	0.0225	0.2615
No log	7.0667	106	0.2784	0.0288	0.2784
No log	7.2	108	0.2991	0.0327	0.2991
No log	7.3333	110	0.2942	0.0327	0.2942
No log	7.4667	112	0.3083	0.0399	0.3083
No log	7.6	114	0.2910	0.0221	0.2910
No log	7.7333	116	0.2561	0.0093	0.2561
No log	7.8667	118	0.2246	0.0125	0.2246
No log	8.0	120	0.2152	0.0156	0.2152
No log	8.1333	122	0.2131	0.0156	0.2131
No log	8.2667	124	0.2238	0.0140	0.2238
No log	8.4	126	0.2341	0.0123	0.2341
No log	8.5333	128	0.2459	0.0123	0.2459
No log	8.6667	130	0.2510	0.0123	0.2510
No log	8.8	132	0.2702	0.0109	0.2702
No log	8.9333	134	0.2776	0.0093	0.2776
No log	9.0667	136	0.2862	0.0173	0.2862
No log	9.2	138	0.2916	0.0158	0.2916
No log	9.3333	140	0.2853	0.0158	0.2853
No log	9.4667	142	0.2781	0.0173	0.2781
No log	9.6	144	0.2737	0.0093	0.2737
No log	9.7333	146	0.2709	0.0109	0.2709
No log	9.8667	148	0.2693	0.0109	0.2693
No log	10.0	150	0.2694	0.0109	0.2694

Framework versions

Transformers 4.44.0
Pytorch 2.4.0
Datasets 2.21.0
Tokenizers 0.19.1

salbatarni
/

arabert_cross_relevance_task1_fold0

arabert_cross_relevance_task1_fold0

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Model tree for salbatarni/arabert_cross_relevance_task1_fold0

Evaluation results