arabert_baseline_augmented_organization_task1_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: 0.4730
• Qwk: 0.8435
• Mse: 0.4730
• Rmse: 0.6878

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	0.1429	2	3.1510	-0.0180	3.1510	1.7751
No log	0.2857	4	1.6460	0.0523	1.6460	1.2829
No log	0.4286	6	0.8622	0.1026	0.8622	0.9285
No log	0.5714	8	0.8307	0.1171	0.8307	0.9114
No log	0.7143	10	0.7807	0.3304	0.7807	0.8836
No log	0.8571	12	0.7471	0.1714	0.7471	0.8643
No log	1.0	14	0.8469	0.2119	0.8469	0.9203
No log	1.1429	16	0.7275	0.2759	0.7275	0.8529
No log	1.2857	18	0.4908	0.496	0.4908	0.7006
No log	1.4286	20	0.5878	0.5377	0.5878	0.7667
No log	1.5714	22	0.6832	0.3396	0.6832	0.8266
No log	1.7143	24	0.6444	0.4836	0.6444	0.8028
No log	1.8571	26	0.5840	0.496	0.5840	0.7642
No log	2.0	28	0.4910	0.4207	0.4910	0.7007
No log	2.1429	30	0.4882	0.4776	0.4882	0.6987
No log	2.2857	32	0.4197	0.5685	0.4197	0.6478
No log	2.4286	34	0.4341	0.6723	0.4341	0.6589
No log	2.5714	36	0.4761	0.6638	0.4761	0.6900
No log	2.7143	38	0.4480	0.6908	0.4480	0.6693
No log	2.8571	40	0.4294	0.7220	0.4294	0.6553
No log	3.0	42	0.4167	0.5302	0.4167	0.6455
No log	3.1429	44	0.4095	0.5966	0.4095	0.6399
No log	3.2857	46	0.4096	0.7220	0.4096	0.6400
No log	3.4286	48	0.4673	0.6769	0.4673	0.6836
No log	3.5714	50	0.4072	0.7072	0.4072	0.6382
No log	3.7143	52	0.3888	0.7138	0.3888	0.6235
No log	3.8571	54	0.4052	0.7072	0.4052	0.6366
No log	4.0	56	0.4011	0.75	0.4011	0.6334
No log	4.1429	58	0.4191	0.5706	0.4191	0.6474
No log	4.2857	60	0.4523	0.5706	0.4523	0.6726
No log	4.4286	62	0.4722	0.6433	0.4722	0.6872
No log	4.5714	64	0.5382	0.7407	0.5382	0.7336
No log	4.7143	66	0.5638	0.7697	0.5638	0.7509
No log	4.8571	68	0.6073	0.7697	0.6073	0.7793
No log	5.0	70	0.5386	0.6510	0.5386	0.7339
No log	5.1429	72	0.5475	0.6379	0.5475	0.7399
No log	5.2857	74	0.6053	0.4262	0.6053	0.7780
No log	5.4286	76	0.5524	0.5532	0.5524	0.7432
No log	5.5714	78	0.5098	0.6267	0.5098	0.7140
No log	5.7143	80	0.5837	0.6260	0.5837	0.7640
No log	5.8571	82	0.6227	0.7027	0.6227	0.7891
No log	6.0	84	0.6339	0.7027	0.6339	0.7962
No log	6.1429	86	0.5640	0.6807	0.5640	0.7510
No log	6.2857	88	0.5049	0.5795	0.5049	0.7106
No log	6.4286	90	0.4991	0.5164	0.4991	0.7065
No log	6.5714	92	0.5075	0.5164	0.5075	0.7124
No log	6.7143	94	0.5036	0.5882	0.5036	0.7097
No log	6.8571	96	0.5153	0.6423	0.5153	0.7179
No log	7.0	98	0.5427	0.7464	0.5427	0.7367
No log	7.1429	100	0.5207	0.7464	0.5207	0.7216
No log	7.2857	102	0.4633	0.7072	0.4633	0.6806
No log	7.4286	104	0.4399	0.7072	0.4399	0.6633
No log	7.5714	106	0.4346	0.7072	0.4346	0.6592
No log	7.7143	108	0.4279	0.6667	0.4279	0.6541
No log	7.8571	110	0.4345	0.7072	0.4345	0.6592
No log	8.0	112	0.4419	0.7445	0.4419	0.6647
No log	8.1429	114	0.4579	0.7445	0.4579	0.6767
No log	8.2857	116	0.4917	0.7850	0.4917	0.7012
No log	8.4286	118	0.5267	0.7317	0.5267	0.7257
No log	8.5714	120	0.5243	0.7317	0.5243	0.7241
No log	8.7143	122	0.5205	0.7317	0.5205	0.7214
No log	8.8571	124	0.4941	0.8435	0.4941	0.7029
No log	9.0	126	0.4803	0.8435	0.4803	0.6930
No log	9.1429	128	0.4792	0.8435	0.4792	0.6922
No log	9.2857	130	0.4765	0.8435	0.4765	0.6903
No log	9.4286	132	0.4739	0.8435	0.4739	0.6884
No log	9.5714	134	0.4751	0.8435	0.4751	0.6892
No log	9.7143	136	0.4742	0.8435	0.4742	0.6886
No log	9.8571	138	0.4728	0.8435	0.4728	0.6876
No log	10.0	140	0.4730	0.8435	0.4730	0.6878

Framework versions

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