arabert_augWithOrig_disEquV3_k1_organization_task3_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: 0.9649
• Qwk: 0.0
• Mse: 0.9649
• Rmse: 0.9823

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: 8
• eval_batch_size: 8
• 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	Rmse
No log	0.2	2	3.9047	-0.0035	3.9047	1.9760
No log	0.4	4	2.3346	0.0	2.3346	1.5280
No log	0.6	6	1.2287	-0.0168	1.2287	1.1085
No log	0.8	8	0.8765	0.0	0.8765	0.9362
No log	1.0	10	1.0024	0.0	1.0024	1.0012
No log	1.2	12	0.8315	0.0	0.8315	0.9119
No log	1.4	14	0.7368	0.0	0.7368	0.8584
No log	1.6	16	0.6708	0.0	0.6708	0.8190
No log	1.8	18	0.6907	0.0	0.6907	0.8311
No log	2.0	20	0.8553	0.0	0.8553	0.9248
No log	2.2	22	1.1118	0.0	1.1118	1.0544
No log	2.4	24	1.0590	0.0	1.0590	1.0291
No log	2.6	26	1.0336	0.0	1.0336	1.0167
No log	2.8	28	0.9557	0.0	0.9557	0.9776
No log	3.0	30	0.9211	0.0	0.9211	0.9597
No log	3.2	32	0.9684	0.0	0.9684	0.9841
No log	3.4	34	1.0564	0.0	1.0564	1.0278
No log	3.6	36	1.0047	0.0	1.0047	1.0023
No log	3.8	38	0.9292	0.0	0.9292	0.9639
No log	4.0	40	0.8528	0.0	0.8528	0.9235
No log	4.2	42	0.8006	0.0	0.8006	0.8948
No log	4.4	44	0.8097	0.0	0.8097	0.8998
No log	4.6	46	0.8304	0.0	0.8304	0.9113
No log	4.8	48	0.8237	0.0	0.8237	0.9076
No log	5.0	50	0.8253	0.0	0.8253	0.9084
No log	5.2	52	0.8166	0.0	0.8166	0.9037
No log	5.4	54	0.8073	0.0	0.8073	0.8985
No log	5.6	56	0.8143	0.0	0.8143	0.9024
No log	5.8	58	0.8348	0.0	0.8348	0.9137
No log	6.0	60	0.8535	0.0	0.8535	0.9238
No log	6.2	62	0.8792	0.0	0.8792	0.9377
No log	6.4	64	0.8852	0.0	0.8852	0.9409
No log	6.6	66	0.8798	0.0	0.8798	0.9380
No log	6.8	68	0.8647	0.0	0.8647	0.9299
No log	7.0	70	0.8784	0.0	0.8784	0.9372
No log	7.2	72	0.8873	0.0	0.8873	0.9420
No log	7.4	74	0.9084	0.0	0.9084	0.9531
No log	7.6	76	0.9269	0.0	0.9269	0.9627
No log	7.8	78	0.9476	0.0	0.9476	0.9735
No log	8.0	80	0.9881	0.0	0.9881	0.9940
No log	8.2	82	1.0230	0.0	1.0230	1.0114
No log	8.4	84	1.0435	0.0	1.0435	1.0215
No log	8.6	86	1.0709	0.0	1.0709	1.0349
No log	8.8	88	1.0761	0.0	1.0761	1.0374
No log	9.0	90	1.0563	0.0	1.0563	1.0278
No log	9.2	92	1.0280	0.0	1.0280	1.0139
No log	9.4	94	1.0031	0.0	1.0031	1.0016
No log	9.6	96	0.9859	0.0	0.9859	0.9929
No log	9.8	98	0.9703	0.0	0.9703	0.9850
No log	10.0	100	0.9649	0.0	0.9649	0.9823

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu118
• Datasets 2.21.0
• Tokenizers 0.19.1