ArabicNewSplits4_WithDuplicationsForScore5_FineTuningAraBERT_run2_AugV5_k10_task5_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: 0.6873
• Qwk: 0.7847
• Mse: 0.6873
• Rmse: 0.8290

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	0.0571	2	2.2972	0.0110	2.2972	1.5156
No log	0.1143	4	1.4630	0.2304	1.4630	1.2095
No log	0.1714	6	1.3978	0.1779	1.3978	1.1823
No log	0.2286	8	1.5397	0.2818	1.5397	1.2409
No log	0.2857	10	1.5387	0.1958	1.5387	1.2405
No log	0.3429	12	1.5722	0.1630	1.5722	1.2539
No log	0.4	14	1.6124	0.1450	1.6124	1.2698
No log	0.4571	16	1.6718	0.1215	1.6718	1.2930
No log	0.5143	18	1.9206	0.2437	1.9206	1.3858
No log	0.5714	20	2.1268	0.2464	2.1268	1.4584
No log	0.6286	22	1.9543	0.2903	1.9543	1.3980
No log	0.6857	24	1.7201	0.3319	1.7201	1.3115
No log	0.7429	26	1.5161	0.1445	1.5161	1.2313
No log	0.8	28	1.4194	0.1009	1.4194	1.1914
No log	0.8571	30	1.3716	0.1009	1.3716	1.1711
No log	0.9143	32	1.3518	0.1472	1.3518	1.1627
No log	0.9714	34	1.3477	0.2184	1.3477	1.1609
No log	1.0286	36	1.3176	0.3354	1.3176	1.1479
No log	1.0857	38	1.3512	0.4113	1.3512	1.1624
No log	1.1429	40	1.4065	0.4018	1.4065	1.1859
No log	1.2	42	1.4115	0.4298	1.4115	1.1881
No log	1.2571	44	1.4555	0.4203	1.4555	1.2064
No log	1.3143	46	1.5353	0.4022	1.5353	1.2391
No log	1.3714	48	1.6011	0.4217	1.6011	1.2653
No log	1.4286	50	1.4552	0.4645	1.4552	1.2063
No log	1.4857	52	1.4912	0.4601	1.4912	1.2212
No log	1.5429	54	1.7279	0.4578	1.7279	1.3145
No log	1.6	56	2.0942	0.4444	2.0942	1.4471
No log	1.6571	58	1.9834	0.4573	1.9834	1.4083
No log	1.7143	60	1.3639	0.5101	1.3639	1.1679
No log	1.7714	62	1.1420	0.5077	1.1420	1.0686
No log	1.8286	64	1.1203	0.5111	1.1203	1.0584
No log	1.8857	66	1.1286	0.5382	1.1286	1.0623
No log	1.9429	68	0.9497	0.5708	0.9497	0.9745
No log	2.0	70	0.8276	0.6029	0.8276	0.9097
No log	2.0571	72	0.8756	0.6217	0.8756	0.9357
No log	2.1143	74	0.8333	0.6259	0.8333	0.9129
No log	2.1714	76	0.8119	0.6481	0.8119	0.9011
No log	2.2286	78	0.8326	0.6438	0.8326	0.9125
No log	2.2857	80	0.8643	0.6157	0.8643	0.9297
No log	2.3429	82	1.0641	0.6183	1.0641	1.0315
No log	2.4	84	1.1008	0.5882	1.1008	1.0492
No log	2.4571	86	0.8478	0.6340	0.8478	0.9207
No log	2.5143	88	0.8033	0.6413	0.8033	0.8963
No log	2.5714	90	0.8650	0.6554	0.8650	0.9301
No log	2.6286	92	1.1340	0.6196	1.1340	1.0649
No log	2.6857	94	1.2783	0.5974	1.2783	1.1306
No log	2.7429	96	1.2523	0.5967	1.2523	1.1191
No log	2.8	98	1.0197	0.6358	1.0197	1.0098
No log	2.8571	100	0.8786	0.6832	0.8786	0.9373
No log	2.9143	102	0.8502	0.6645	0.8502	0.9221
No log	2.9714	104	0.7691	0.6958	0.7691	0.8770
No log	3.0286	106	0.6839	0.7037	0.6839	0.8270
No log	3.0857	108	0.7165	0.7287	0.7165	0.8464
No log	3.1429	110	0.8381	0.6636	0.8381	0.9155
No log	3.2	112	0.8038	0.6803	0.8038	0.8966
No log	3.2571	114	0.7185	0.7265	0.7185	0.8476
No log	3.3143	116	0.7568	0.7216	0.7568	0.8700
No log	3.3714	118	0.8417	0.6945	0.8417	0.9174
No log	3.4286	120	0.9808	0.6642	0.9808	0.9904
No log	3.4857	122	0.9354	0.6887	0.9354	0.9672
No log	3.5429	124	0.9772	0.6657	0.9772	0.9885
No log	3.6	126	0.8237	0.7190	0.8237	0.9076
No log	3.6571	128	0.6688	0.7277	0.6688	0.8178
No log	3.7143	130	0.6297	0.6868	0.6297	0.7936
No log	3.7714	132	0.6457	0.6934	0.6457	0.8035
No log	3.8286	134	0.7277	0.7453	0.7277	0.8531
No log	3.8857	136	0.8333	0.6946	0.8333	0.9129
No log	3.9429	138	0.8493	0.6946	0.8493	0.9216
No log	4.0	140	0.8778	0.6882	0.8778	0.9369
No log	4.0571	142	0.7606	0.7493	0.7606	0.8721
No log	4.1143	144	0.6463	0.7260	0.6463	0.8039
No log	4.1714	146	0.6455	0.7387	0.6455	0.8034
No log	4.2286	148	0.6502	0.7290	0.6502	0.8064
No log	4.2857	150	0.7434	0.7555	0.7434	0.8622
No log	4.3429	152	0.9515	0.6886	0.9515	0.9755
No log	4.4	154	0.9937	0.6729	0.9937	0.9968
No log	4.4571	156	0.9299	0.6737	0.9299	0.9643
No log	4.5143	158	0.8904	0.6956	0.8904	0.9436
No log	4.5714	160	0.8180	0.7006	0.8180	0.9044
No log	4.6286	162	0.7805	0.7101	0.7805	0.8834
No log	4.6857	164	0.7791	0.7289	0.7791	0.8827
No log	4.7429	166	0.7820	0.7127	0.7820	0.8843
No log	4.8	168	0.7870	0.7192	0.7870	0.8871
No log	4.8571	170	0.7984	0.7199	0.7984	0.8935
No log	4.9143	172	0.7447	0.7135	0.7447	0.8630
No log	4.9714	174	0.7029	0.7322	0.7029	0.8384
No log	5.0286	176	0.6872	0.7583	0.6872	0.8290
No log	5.0857	178	0.6907	0.7463	0.6907	0.8311
No log	5.1429	180	0.6521	0.7514	0.6521	0.8075
No log	5.2	182	0.6650	0.7529	0.6650	0.8155
No log	5.2571	184	0.6350	0.7472	0.6350	0.7968
No log	5.3143	186	0.6457	0.7472	0.6457	0.8036
No log	5.3714	188	0.6770	0.7464	0.6770	0.8228
No log	5.4286	190	0.6978	0.7431	0.6978	0.8354
No log	5.4857	192	0.6938	0.7605	0.6938	0.8330
No log	5.5429	194	0.6507	0.7678	0.6507	0.8067
No log	5.6	196	0.6803	0.7692	0.6803	0.8248
No log	5.6571	198	0.7667	0.7192	0.7667	0.8756
No log	5.7143	200	0.8994	0.6798	0.8994	0.9484
No log	5.7714	202	0.9168	0.6538	0.9168	0.9575
No log	5.8286	204	0.7982	0.7075	0.7982	0.8934
No log	5.8857	206	0.6725	0.7249	0.6725	0.8201
No log	5.9429	208	0.6533	0.7194	0.6533	0.8083
No log	6.0	210	0.6954	0.7258	0.6954	0.8339
No log	6.0571	212	0.7493	0.7310	0.7493	0.8656
No log	6.1143	214	0.8051	0.6819	0.8051	0.8973
No log	6.1714	216	0.8366	0.6688	0.8366	0.9147
No log	6.2286	218	0.8718	0.6639	0.8718	0.9337
No log	6.2857	220	0.8018	0.6754	0.8018	0.8954
No log	6.3429	222	0.7531	0.7488	0.7531	0.8678
No log	6.4	224	0.6726	0.7548	0.6726	0.8201
No log	6.4571	226	0.6573	0.7698	0.6573	0.8107
No log	6.5143	228	0.7126	0.7735	0.7126	0.8442
No log	6.5714	230	0.8272	0.6794	0.8272	0.9095
No log	6.6286	232	0.9534	0.6750	0.9534	0.9764
No log	6.6857	234	0.9586	0.6750	0.9586	0.9791
No log	6.7429	236	0.9021	0.6911	0.9021	0.9498
No log	6.8	238	0.7900	0.7353	0.7900	0.8888
No log	6.8571	240	0.7562	0.7282	0.7562	0.8696
No log	6.9143	242	0.7580	0.7281	0.7580	0.8706
No log	6.9714	244	0.7137	0.7341	0.7137	0.8448
No log	7.0286	246	0.6601	0.7729	0.6601	0.8125
No log	7.0857	248	0.6108	0.7623	0.6108	0.7815
No log	7.1429	250	0.6012	0.7623	0.6012	0.7754
No log	7.2	252	0.6295	0.7679	0.6295	0.7934
No log	7.2571	254	0.6578	0.7801	0.6578	0.8110
No log	7.3143	256	0.6766	0.7847	0.6766	0.8225
No log	7.3714	258	0.6631	0.7855	0.6631	0.8143
No log	7.4286	260	0.6407	0.7855	0.6407	0.8004
No log	7.4857	262	0.6082	0.7795	0.6082	0.7799
No log	7.5429	264	0.6037	0.7758	0.6037	0.7770
No log	7.6	266	0.6334	0.7824	0.6334	0.7958
No log	7.6571	268	0.6839	0.7687	0.6839	0.8270
No log	7.7143	270	0.7351	0.7563	0.7351	0.8574
No log	7.7714	272	0.7618	0.7301	0.7618	0.8728
No log	7.8286	274	0.7883	0.7282	0.7883	0.8879
No log	7.8857	276	0.7669	0.7282	0.7669	0.8757
No log	7.9429	278	0.7230	0.7492	0.7230	0.8503
No log	8.0	280	0.7164	0.7492	0.7164	0.8464
No log	8.0571	282	0.6915	0.7652	0.6915	0.8316
No log	8.1143	284	0.6893	0.7675	0.6893	0.8302
No log	8.1714	286	0.7147	0.7492	0.7147	0.8454
No log	8.2286	288	0.7700	0.7466	0.7700	0.8775
No log	8.2857	290	0.8042	0.7346	0.8042	0.8968
No log	8.3429	292	0.8034	0.7346	0.8034	0.8964
No log	8.4	294	0.7727	0.7468	0.7727	0.8790
No log	8.4571	296	0.7323	0.7757	0.7323	0.8557
No log	8.5143	298	0.7104	0.7847	0.7104	0.8428
No log	8.5714	300	0.6920	0.7847	0.6920	0.8318
No log	8.6286	302	0.6822	0.7847	0.6822	0.8260
No log	8.6857	304	0.6705	0.7847	0.6705	0.8189
No log	8.7429	306	0.6597	0.7847	0.6597	0.8122
No log	8.8	308	0.6584	0.7847	0.6584	0.8114
No log	8.8571	310	0.6696	0.7847	0.6696	0.8183
No log	8.9143	312	0.6790	0.7847	0.6790	0.8240
No log	8.9714	314	0.6870	0.7847	0.6870	0.8288
No log	9.0286	316	0.6748	0.7847	0.6748	0.8215
No log	9.0857	318	0.6710	0.7847	0.6710	0.8192
No log	9.1429	320	0.6731	0.7847	0.6731	0.8204
No log	9.2	322	0.6693	0.7847	0.6693	0.8181
No log	9.2571	324	0.6705	0.7847	0.6705	0.8189
No log	9.3143	326	0.6662	0.7847	0.6662	0.8162
No log	9.3714	328	0.6690	0.7847	0.6690	0.8179
No log	9.4286	330	0.6714	0.7847	0.6714	0.8194
No log	9.4857	332	0.6693	0.7847	0.6693	0.8181
No log	9.5429	334	0.6660	0.7847	0.6660	0.8161
No log	9.6	336	0.6668	0.7847	0.6668	0.8166
No log	9.6571	338	0.6718	0.7847	0.6718	0.8197
No log	9.7143	340	0.6746	0.7847	0.6746	0.8214
No log	9.7714	342	0.6805	0.7847	0.6805	0.8249
No log	9.8286	344	0.6842	0.7847	0.6842	0.8272
No log	9.8857	346	0.6862	0.7847	0.6862	0.8284
No log	9.9429	348	0.6871	0.7847	0.6871	0.8289
No log	10.0	350	0.6873	0.7847	0.6873	0.8290

Framework versions

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