arabert_baseline_organization_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: 0.7080
• Qwk: 0.6596
• Mse: 0.7206

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: 16
• eval_batch_size: 16
• 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	0.3333	2	4.7375	-0.0187	4.6528
No log	0.6667	4	2.9523	0.0354	2.8976
No log	1.0	6	1.9933	0.0369	1.9520
No log	1.3333	8	1.4358	0.1414	1.4243
No log	1.6667	10	1.3507	0.0742	1.3574
No log	2.0	12	1.2869	0.3309	1.2992
No log	2.3333	14	1.3060	0.4324	1.3235
No log	2.6667	16	1.2124	0.4085	1.2278
No log	3.0	18	1.0567	0.4854	1.0647
No log	3.3333	20	0.9500	0.4639	0.9565
No log	3.6667	22	0.8719	0.5769	0.8846
No log	4.0	24	0.7991	0.5769	0.8115
No log	4.3333	26	0.7537	0.5769	0.7666
No log	4.6667	28	0.7147	0.5514	0.7274
No log	5.0	30	0.6387	0.5811	0.6471
No log	5.3333	32	0.6221	0.5748	0.6286
No log	5.6667	34	0.6363	0.5811	0.6453
No log	6.0	36	0.6849	0.5811	0.6955
No log	6.3333	38	0.6868	0.5811	0.6971
No log	6.6667	40	0.6843	0.5435	0.6932
No log	7.0	42	0.7048	0.5081	0.7131
No log	7.3333	44	0.7116	0.5804	0.7201
No log	7.6667	46	0.7162	0.5779	0.7250
No log	8.0	48	0.7262	0.5779	0.7360
No log	8.3333	50	0.7157	0.5779	0.7258
No log	8.6667	52	0.7189	0.5779	0.7301
No log	9.0	54	0.7090	0.6547	0.7206
No log	9.3333	56	0.7059	0.6547	0.7179
No log	9.6667	58	0.7067	0.6547	0.7191
No log	10.0	60	0.7080	0.6596	0.7206

Framework versions

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