arabert_augmented_only_k1_organization_task3_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: 1.7233
• Qwk: 0.0759
• Mse: 1.7233
• Rmse: 1.3128

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	0.4	2	3.9170	0.0054	3.9170	1.9791
No log	0.8	4	3.8710	0.0	3.8710	1.9675
No log	1.2	6	1.6111	-0.0942	1.6111	1.2693
No log	1.6	8	1.5649	0.0	1.5649	1.2510
No log	2.0	10	1.9175	-0.0942	1.9175	1.3847
No log	2.4	12	2.0645	-0.0115	2.0645	1.4368
No log	2.8	14	1.9348	-0.0288	1.9348	1.3910
No log	3.2	16	1.7084	0.0	1.7084	1.3070
No log	3.6	18	1.5230	0.0	1.5230	1.2341
No log	4.0	20	1.4610	0.0	1.4610	1.2087
No log	4.4	22	1.5176	-0.0087	1.5176	1.2319
No log	4.8	24	1.7634	-0.0273	1.7634	1.3279
No log	5.2	26	1.8522	-0.0273	1.8522	1.3610
No log	5.6	28	1.8703	-0.0273	1.8703	1.3676
No log	6.0	30	1.7647	-0.0273	1.7647	1.3284
No log	6.4	32	1.5617	0.0759	1.5617	1.2497
No log	6.8	34	1.5033	0.0730	1.5033	1.2261
No log	7.2	36	1.5481	0.0759	1.5481	1.2442
No log	7.6	38	1.5563	0.0759	1.5563	1.2475
No log	8.0	40	1.6224	0.0759	1.6224	1.2738
No log	8.4	42	1.7044	0.0743	1.7044	1.3055
No log	8.8	44	1.7980	-0.0273	1.7980	1.3409
No log	9.2	46	1.7865	-0.0273	1.7865	1.3366
No log	9.6	48	1.7368	0.0743	1.7368	1.3179
No log	10.0	50	1.7233	0.0759	1.7233	1.3128

Framework versions

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