ArabicNewSplits6_WithDuplicationsForScore5_FineTuningAraBERT_run3_AugV5_k3_task3_organization

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: 0.9597
• Qwk: 0.2061
• Mse: 0.9597
• Rmse: 0.9796

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	0.1176	2	3.3545	-0.0053	3.3545	1.8315
No log	0.2353	4	1.7888	-0.0070	1.7888	1.3375
No log	0.3529	6	0.9820	0.0588	0.9820	0.9910
No log	0.4706	8	0.6632	0.0256	0.6632	0.8144
No log	0.5882	10	0.6018	-0.0732	0.6018	0.7757
No log	0.7059	12	0.6683	0.0	0.6683	0.8175
No log	0.8235	14	0.6379	0.0	0.6379	0.7987
No log	0.9412	16	0.5822	0.0	0.5822	0.7630
No log	1.0588	18	0.5789	0.0	0.5789	0.7609
No log	1.1765	20	0.5785	0.0	0.5785	0.7606
No log	1.2941	22	0.5795	0.0	0.5795	0.7613
No log	1.4118	24	0.6217	0.0	0.6217	0.7885
No log	1.5294	26	0.6327	-0.0081	0.6327	0.7954
No log	1.6471	28	0.6379	-0.0233	0.6379	0.7987
No log	1.7647	30	0.6495	-0.0435	0.6495	0.8059
No log	1.8824	32	0.6494	-0.0435	0.6494	0.8059
No log	2.0	34	0.6992	-0.0233	0.6992	0.8362
No log	2.1176	36	0.6833	-0.0233	0.6833	0.8266
No log	2.2353	38	0.6845	-0.0219	0.6845	0.8273
No log	2.3529	40	0.6763	-0.0196	0.6763	0.8224
No log	2.4706	42	0.7006	0.1579	0.7006	0.8370
No log	2.5882	44	0.6528	0.0728	0.6528	0.8080
No log	2.7059	46	0.6353	0.2000	0.6353	0.7971
No log	2.8235	48	0.6380	0.2189	0.6380	0.7988
No log	2.9412	50	0.6842	0.2099	0.6842	0.8272
No log	3.0588	52	0.7184	0.2093	0.7184	0.8476
No log	3.1765	54	0.6804	0.0391	0.6804	0.8249
No log	3.2941	56	0.7506	0.0	0.7506	0.8664
No log	3.4118	58	0.7076	0.1910	0.7076	0.8412
No log	3.5294	60	0.8540	0.1321	0.8540	0.9241
No log	3.6471	62	0.7598	0.1917	0.7598	0.8717
No log	3.7647	64	0.8635	0.0909	0.8635	0.9292
No log	3.8824	66	0.7334	0.2487	0.7334	0.8564
No log	4.0	68	0.7910	0.2161	0.7910	0.8894
No log	4.1176	70	0.9028	0.1493	0.9028	0.9501
No log	4.2353	72	1.1575	0.1939	1.1575	1.0759
No log	4.3529	74	0.8635	0.1927	0.8635	0.9292
No log	4.4706	76	0.8466	0.2511	0.8466	0.9201
No log	4.5882	78	0.8408	0.0459	0.8408	0.9169
No log	4.7059	80	1.1573	0.1608	1.1573	1.0758
No log	4.8235	82	1.6520	0.0	1.6520	1.2853
No log	4.9412	84	1.4376	-0.0157	1.4376	1.1990
No log	5.0588	86	0.9637	0.1165	0.9637	0.9817
No log	5.1765	88	0.8698	0.3585	0.8698	0.9326
No log	5.2941	90	0.8423	0.3585	0.8423	0.9177
No log	5.4118	92	0.8359	0.1429	0.8359	0.9143
No log	5.5294	94	1.1761	0.1396	1.1761	1.0845
No log	5.6471	96	1.3664	0.0968	1.3664	1.1689
No log	5.7647	98	1.1367	0.2000	1.1367	1.0661
No log	5.8824	100	0.8012	0.1781	0.8012	0.8951
No log	6.0	102	0.7316	0.1179	0.7316	0.8553
No log	6.1176	104	0.8224	0.2287	0.8224	0.9069
No log	6.2353	106	1.1108	0.2314	1.1108	1.0539
No log	6.3529	108	1.2197	0.2000	1.2197	1.1044
No log	6.4706	110	1.1164	0.1692	1.1164	1.0566
No log	6.5882	112	0.8306	0.2146	0.8306	0.9114
No log	6.7059	114	0.7787	0.1855	0.7787	0.8824
No log	6.8235	116	0.8891	0.2469	0.8891	0.9429
No log	6.9412	118	1.0055	0.2124	1.0055	1.0027
No log	7.0588	120	1.2651	0.1729	1.2651	1.1248
No log	7.1765	122	1.2741	0.2000	1.2741	1.1288
No log	7.2941	124	1.1810	0.2111	1.1810	1.0867
No log	7.4118	126	1.2253	0.2593	1.2253	1.1069
No log	7.5294	128	1.1604	0.2058	1.1604	1.0772
No log	7.6471	130	1.1888	0.1822	1.1888	1.0903
No log	7.7647	132	1.2952	0.1798	1.2952	1.1381
No log	7.8824	134	1.2999	0.1894	1.2999	1.1402
No log	8.0	136	1.4927	0.0769	1.4927	1.2218
No log	8.1176	138	1.5196	0.0769	1.5196	1.2327
No log	8.2353	140	1.3401	0.1733	1.3401	1.1576
No log	8.3529	142	1.1203	0.2409	1.1203	1.0585
No log	8.4706	144	0.9717	0.2061	0.9717	0.9858
No log	8.5882	146	0.9147	0.2061	0.9147	0.9564
No log	8.7059	148	0.9405	0.2061	0.9405	0.9698
No log	8.8235	150	1.0117	0.2061	1.0117	1.0058
No log	8.9412	152	1.0438	0.2571	1.0438	1.0216
No log	9.0588	154	1.0751	0.2347	1.0751	1.0369
No log	9.1765	156	1.0535	0.2360	1.0535	1.0264
No log	9.2941	158	0.9994	0.2061	0.9994	0.9997
No log	9.4118	160	0.9798	0.2061	0.9798	0.9898
No log	9.5294	162	0.9840	0.2061	0.9840	0.9920
No log	9.6471	164	0.9762	0.2061	0.9762	0.9880
No log	9.7647	166	0.9616	0.2061	0.9616	0.9806
No log	9.8824	168	0.9577	0.2061	0.9577	0.9786
No log	10.0	170	0.9597	0.2061	0.9597	0.9796

Framework versions

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