ArabicNewSplits6_FineTuningAraBERTFreeze_run3_AugV5_k10_task1_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: 0.7199
• Qwk: 0.7043
• Mse: 0.7199
• Rmse: 0.8485

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: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	0.0769	2	7.8469	-0.0499	7.8469	2.8012
No log	0.1538	4	5.4795	-0.0366	5.4795	2.3408
No log	0.2308	6	3.9465	0.0377	3.9465	1.9866
No log	0.3077	8	2.9814	0.1235	2.9814	1.7267
No log	0.3846	10	2.2630	0.1472	2.2630	1.5043
No log	0.4615	12	1.7839	0.1165	1.7839	1.3356
No log	0.5385	14	1.5466	0.1497	1.5466	1.2436
No log	0.6154	16	1.4225	0.1135	1.4225	1.1927
No log	0.6923	18	1.2909	0.1777	1.2909	1.1362
No log	0.7692	20	1.1674	0.2738	1.1674	1.0805
No log	0.8462	22	1.0692	0.3929	1.0692	1.0340
No log	0.9231	24	1.0981	0.4791	1.0981	1.0479
No log	1.0	26	1.1982	0.3418	1.1982	1.0946
No log	1.0769	28	1.1608	0.3995	1.1608	1.0774
No log	1.1538	30	1.1424	0.3995	1.1424	1.0688
No log	1.2308	32	1.0699	0.3934	1.0699	1.0343
No log	1.3077	34	0.9715	0.4883	0.9715	0.9856
No log	1.3846	36	0.9448	0.4945	0.9448	0.9720
No log	1.4615	38	0.9001	0.4977	0.9001	0.9487
No log	1.5385	40	0.8571	0.5239	0.8571	0.9258
No log	1.6154	42	0.8595	0.5083	0.8595	0.9271
No log	1.6923	44	0.8576	0.5248	0.8576	0.9261
No log	1.7692	46	0.8775	0.5186	0.8775	0.9368
No log	1.8462	48	0.9526	0.5179	0.9526	0.9760
No log	1.9231	50	1.0473	0.4514	1.0473	1.0234
No log	2.0	52	1.0246	0.4569	1.0246	1.0122
No log	2.0769	54	0.9468	0.5287	0.9468	0.9730
No log	2.1538	56	0.8303	0.5487	0.8303	0.9112
No log	2.2308	58	0.8307	0.5008	0.8307	0.9114
No log	2.3077	60	0.8554	0.5255	0.8554	0.9249
No log	2.3846	62	0.7846	0.5340	0.7846	0.8858
No log	2.4615	64	0.7820	0.5908	0.7820	0.8843
No log	2.5385	66	1.0198	0.4877	1.0198	1.0098
No log	2.6154	68	1.2727	0.4714	1.2727	1.1281
No log	2.6923	70	1.2793	0.4669	1.2793	1.1311
No log	2.7692	72	1.0957	0.4635	1.0957	1.0468
No log	2.8462	74	0.8613	0.5860	0.8613	0.9281
No log	2.9231	76	0.7507	0.5923	0.7507	0.8665
No log	3.0	78	0.7069	0.6092	0.7069	0.8408
No log	3.0769	80	0.6910	0.5860	0.6910	0.8313
No log	3.1538	82	0.6946	0.5885	0.6946	0.8334
No log	3.2308	84	0.6927	0.6055	0.6927	0.8323
No log	3.3077	86	0.7180	0.6245	0.7180	0.8473
No log	3.3846	88	0.7345	0.6202	0.7345	0.8570
No log	3.4615	90	0.7502	0.6212	0.7502	0.8661
No log	3.5385	92	0.7492	0.6048	0.7492	0.8656
No log	3.6154	94	0.7673	0.6123	0.7673	0.8760
No log	3.6923	96	0.7525	0.6328	0.7525	0.8675
No log	3.7692	98	0.7204	0.5962	0.7204	0.8488
No log	3.8462	100	0.7356	0.5306	0.7356	0.8577
No log	3.9231	102	0.7514	0.5064	0.7514	0.8668
No log	4.0	104	0.7420	0.5306	0.7420	0.8614
No log	4.0769	106	0.7393	0.5368	0.7393	0.8598
No log	4.1538	108	0.7310	0.5920	0.7310	0.8550
No log	4.2308	110	0.7877	0.6106	0.7877	0.8875
No log	4.3077	112	0.8119	0.6244	0.8119	0.9011
No log	4.3846	114	0.7814	0.6191	0.7814	0.8840
No log	4.4615	116	0.7234	0.5954	0.7234	0.8506
No log	4.5385	118	0.6818	0.6017	0.6818	0.8257
No log	4.6154	120	0.6793	0.6184	0.6793	0.8242
No log	4.6923	122	0.7154	0.6372	0.7154	0.8458
No log	4.7692	124	0.7951	0.6318	0.7951	0.8917
No log	4.8462	126	0.8228	0.6390	0.8228	0.9071
No log	4.9231	128	0.7674	0.6487	0.7674	0.8760
No log	5.0	130	0.7368	0.6578	0.7368	0.8584
No log	5.0769	132	0.7293	0.6456	0.7293	0.8540
No log	5.1538	134	0.7163	0.6489	0.7163	0.8463
No log	5.2308	136	0.7481	0.6488	0.7481	0.8649
No log	5.3077	138	0.7710	0.6447	0.7710	0.8781
No log	5.3846	140	0.7557	0.6488	0.7557	0.8693
No log	5.4615	142	0.6835	0.6519	0.6835	0.8267
No log	5.5385	144	0.6762	0.6495	0.6762	0.8223
No log	5.6154	146	0.6785	0.6770	0.6785	0.8237
No log	5.6923	148	0.6806	0.6829	0.6806	0.8250
No log	5.7692	150	0.6918	0.6588	0.6918	0.8317
No log	5.8462	152	0.7033	0.6719	0.7033	0.8386
No log	5.9231	154	0.7554	0.6770	0.7554	0.8691
No log	6.0	156	0.8665	0.6388	0.8665	0.9308
No log	6.0769	158	0.9243	0.6009	0.9243	0.9614
No log	6.1538	160	0.8117	0.6350	0.8117	0.9009
No log	6.2308	162	0.6988	0.6704	0.6988	0.8359
No log	6.3077	164	0.7205	0.6343	0.7205	0.8488
No log	6.3846	166	0.7188	0.6228	0.7188	0.8478
No log	6.4615	168	0.6783	0.6658	0.6783	0.8236
No log	6.5385	170	0.7060	0.6915	0.7060	0.8402
No log	6.6154	172	0.7530	0.6691	0.7530	0.8678
No log	6.6923	174	0.7312	0.6781	0.7312	0.8551
No log	6.7692	176	0.7481	0.6605	0.7481	0.8649
No log	6.8462	178	0.7200	0.6781	0.7200	0.8485
No log	6.9231	180	0.6702	0.7081	0.6702	0.8186
No log	7.0	182	0.7054	0.6566	0.7054	0.8399
No log	7.0769	184	0.7898	0.5731	0.7898	0.8887
No log	7.1538	186	0.7677	0.5719	0.7677	0.8762
No log	7.2308	188	0.6806	0.6403	0.6806	0.8250
No log	7.3077	190	0.6879	0.6894	0.6879	0.8294
No log	7.3846	192	0.8409	0.6466	0.8409	0.9170
No log	7.4615	194	0.9175	0.6270	0.9175	0.9579
No log	7.5385	196	0.8392	0.6344	0.8392	0.9161
No log	7.6154	198	0.7126	0.6800	0.7126	0.8441
No log	7.6923	200	0.6548	0.6719	0.6548	0.8092
No log	7.7692	202	0.6518	0.7089	0.6518	0.8073
No log	7.8462	204	0.6574	0.7096	0.6574	0.8108
No log	7.9231	206	0.7029	0.6921	0.7029	0.8384
No log	8.0	208	0.8248	0.6434	0.8248	0.9082
No log	8.0769	210	0.8242	0.6208	0.8242	0.9079
No log	8.1538	212	0.7240	0.7104	0.7240	0.8509
No log	8.2308	214	0.6864	0.7123	0.6864	0.8285
No log	8.3077	216	0.6794	0.6478	0.6794	0.8243
No log	8.3846	218	0.6844	0.6517	0.6844	0.8273
No log	8.4615	220	0.6975	0.6246	0.6975	0.8352
No log	8.5385	222	0.7062	0.6134	0.7062	0.8404
No log	8.6154	224	0.7053	0.6497	0.7053	0.8398
No log	8.6923	226	0.6907	0.6516	0.6907	0.8311
No log	8.7692	228	0.7048	0.6618	0.7048	0.8395
No log	8.8462	230	0.7093	0.6474	0.7093	0.8422
No log	8.9231	232	0.7077	0.6203	0.7077	0.8413
No log	9.0	234	0.7161	0.6146	0.7161	0.8462
No log	9.0769	236	0.7408	0.6851	0.7408	0.8607
No log	9.1538	238	0.7331	0.6493	0.7331	0.8562
No log	9.2308	240	0.7331	0.6200	0.7331	0.8562
No log	9.3077	242	0.7893	0.6179	0.7893	0.8884
No log	9.3846	244	0.7699	0.6183	0.7699	0.8774
No log	9.4615	246	0.7454	0.6304	0.7454	0.8633
No log	9.5385	248	0.7224	0.6619	0.7224	0.8500
No log	9.6154	250	0.7305	0.6733	0.7305	0.8547
No log	9.6923	252	0.7200	0.6774	0.7200	0.8486
No log	9.7692	254	0.7096	0.6546	0.7096	0.8424
No log	9.8462	256	0.7238	0.6696	0.7238	0.8507
No log	9.9231	258	0.7223	0.6721	0.7223	0.8499
No log	10.0	260	0.7287	0.6723	0.7287	0.8536
No log	10.0769	262	0.7167	0.6720	0.7167	0.8466
No log	10.1538	264	0.6901	0.6859	0.6901	0.8307
No log	10.2308	266	0.6936	0.7191	0.6936	0.8328
No log	10.3077	268	0.6810	0.6999	0.6810	0.8252
No log	10.3846	270	0.7223	0.6925	0.7223	0.8499
No log	10.4615	272	0.8004	0.6470	0.8004	0.8946
No log	10.5385	274	0.7823	0.6420	0.7823	0.8845
No log	10.6154	276	0.7240	0.6753	0.7240	0.8509
No log	10.6923	278	0.6872	0.6819	0.6872	0.8290
No log	10.7692	280	0.6970	0.6772	0.6970	0.8348
No log	10.8462	282	0.7099	0.6891	0.7099	0.8426
No log	10.9231	284	0.7257	0.6698	0.7257	0.8519
No log	11.0	286	0.7915	0.6491	0.7915	0.8897
No log	11.0769	288	0.8201	0.6283	0.8201	0.9056
No log	11.1538	290	0.7775	0.6486	0.7775	0.8818
No log	11.2308	292	0.7470	0.6528	0.7470	0.8643
No log	11.3077	294	0.7414	0.6642	0.7414	0.8611
No log	11.3846	296	0.7432	0.6869	0.7432	0.8621
No log	11.4615	298	0.7949	0.6209	0.7949	0.8916
No log	11.5385	300	0.8661	0.5506	0.8661	0.9307
No log	11.6154	302	0.8423	0.5736	0.8423	0.9178
No log	11.6923	304	0.7663	0.6171	0.7663	0.8754
No log	11.7692	306	0.7077	0.7043	0.7077	0.8413
No log	11.8462	308	0.7077	0.6727	0.7077	0.8413
No log	11.9231	310	0.7146	0.6932	0.7146	0.8454
No log	12.0	312	0.7106	0.7006	0.7106	0.8430
No log	12.0769	314	0.7188	0.6688	0.7188	0.8478
No log	12.1538	316	0.7201	0.6688	0.7201	0.8486
No log	12.2308	318	0.7260	0.6954	0.7260	0.8521
No log	12.3077	320	0.7320	0.7124	0.7320	0.8556
No log	12.3846	322	0.7299	0.6736	0.7299	0.8543
No log	12.4615	324	0.7339	0.6701	0.7339	0.8567
No log	12.5385	326	0.7516	0.6676	0.7516	0.8669
No log	12.6154	328	0.7923	0.6475	0.7923	0.8901
No log	12.6923	330	0.7973	0.6475	0.7973	0.8929
No log	12.7692	332	0.7499	0.6701	0.7499	0.8659
No log	12.8462	334	0.7771	0.6673	0.7771	0.8815
No log	12.9231	336	0.8431	0.6310	0.8431	0.9182
No log	13.0	338	0.8184	0.6447	0.8184	0.9047
No log	13.0769	340	0.7430	0.6772	0.7430	0.8619
No log	13.1538	342	0.7279	0.6752	0.7279	0.8531
No log	13.2308	344	0.7611	0.6716	0.7611	0.8724
No log	13.3077	346	0.7567	0.6787	0.7567	0.8699
No log	13.3846	348	0.7211	0.6876	0.7211	0.8492
No log	13.4615	350	0.7057	0.6960	0.7057	0.8401
No log	13.5385	352	0.7135	0.6924	0.7135	0.8447
No log	13.6154	354	0.6982	0.7134	0.6982	0.8356
No log	13.6923	356	0.7062	0.6876	0.7062	0.8404
No log	13.7692	358	0.8130	0.6344	0.8130	0.9017
No log	13.8462	360	0.8875	0.6057	0.8875	0.9421
No log	13.9231	362	0.8551	0.6070	0.8551	0.9247
No log	14.0	364	0.7435	0.6339	0.7435	0.8623
No log	14.0769	366	0.6733	0.7150	0.6733	0.8205
No log	14.1538	368	0.6646	0.7086	0.6646	0.8152
No log	14.2308	370	0.6683	0.6999	0.6683	0.8175
No log	14.3077	372	0.6986	0.6965	0.6986	0.8358
No log	14.3846	374	0.7062	0.6945	0.7062	0.8404
No log	14.4615	376	0.7093	0.6952	0.7093	0.8422
No log	14.5385	378	0.7334	0.6723	0.7334	0.8564
No log	14.6154	380	0.7824	0.6718	0.7824	0.8845
No log	14.6923	382	0.7523	0.6734	0.7523	0.8674
No log	14.7692	384	0.7107	0.6971	0.7107	0.8431
No log	14.8462	386	0.6887	0.7035	0.6887	0.8299
No log	14.9231	388	0.6828	0.7055	0.6828	0.8263
No log	15.0	390	0.7011	0.7181	0.7011	0.8373
No log	15.0769	392	0.7308	0.6807	0.7308	0.8549
No log	15.1538	394	0.7009	0.7319	0.7009	0.8372
No log	15.2308	396	0.6558	0.7008	0.6558	0.8098
No log	15.3077	398	0.6539	0.7107	0.6539	0.8087
No log	15.3846	400	0.6705	0.6943	0.6705	0.8189
No log	15.4615	402	0.6786	0.6943	0.6786	0.8237
No log	15.5385	404	0.6905	0.6903	0.6905	0.8310
No log	15.6154	406	0.7384	0.6823	0.7384	0.8593
No log	15.6923	408	0.7536	0.6805	0.7536	0.8681
No log	15.7692	410	0.7558	0.6615	0.7558	0.8694
No log	15.8462	412	0.7558	0.6929	0.7558	0.8694
No log	15.9231	414	0.7557	0.6966	0.7557	0.8693
No log	16.0	416	0.7555	0.6978	0.7555	0.8692
No log	16.0769	418	0.7602	0.6965	0.7602	0.8719
No log	16.1538	420	0.7838	0.6727	0.7838	0.8853
No log	16.2308	422	0.8104	0.6652	0.8104	0.9002
No log	16.3077	424	0.7879	0.6676	0.7879	0.8877
No log	16.3846	426	0.7619	0.6891	0.7619	0.8729
No log	16.4615	428	0.7668	0.6891	0.7668	0.8757
No log	16.5385	430	0.7656	0.6960	0.7656	0.8750
No log	16.6154	432	0.8202	0.6446	0.8202	0.9057
No log	16.6923	434	0.8645	0.6058	0.8645	0.9298
No log	16.7692	436	0.8579	0.6223	0.8579	0.9262
No log	16.8462	438	0.7905	0.6475	0.7905	0.8891
No log	16.9231	440	0.7549	0.6870	0.7549	0.8688
No log	17.0	442	0.7538	0.6826	0.7538	0.8682
No log	17.0769	444	0.7572	0.6727	0.7572	0.8702
No log	17.1538	446	0.7888	0.6725	0.7888	0.8882
No log	17.2308	448	0.7760	0.6819	0.7760	0.8809
No log	17.3077	450	0.7861	0.6761	0.7861	0.8866
No log	17.3846	452	0.8154	0.6384	0.8154	0.9030
No log	17.4615	454	0.7811	0.6772	0.7811	0.8838
No log	17.5385	456	0.7363	0.6958	0.7363	0.8581
No log	17.6154	458	0.7278	0.7083	0.7278	0.8531
No log	17.6923	460	0.7275	0.7059	0.7275	0.8530
No log	17.7692	462	0.7556	0.6982	0.7556	0.8693
No log	17.8462	464	0.7730	0.6828	0.7730	0.8792
No log	17.9231	466	0.7441	0.6932	0.7441	0.8626
No log	18.0	468	0.7330	0.7011	0.7330	0.8562
No log	18.0769	470	0.7397	0.6774	0.7397	0.8601
No log	18.1538	472	0.7595	0.6831	0.7595	0.8715
No log	18.2308	474	0.7861	0.6854	0.7861	0.8866
No log	18.3077	476	0.7729	0.6797	0.7729	0.8792
No log	18.3846	478	0.7410	0.6920	0.7410	0.8608
No log	18.4615	480	0.7353	0.6932	0.7353	0.8575
No log	18.5385	482	0.7405	0.6769	0.7405	0.8605
No log	18.6154	484	0.7529	0.6557	0.7529	0.8677
No log	18.6923	486	0.7596	0.6333	0.7596	0.8715
No log	18.7692	488	0.7208	0.6780	0.7208	0.8490
No log	18.8462	490	0.7181	0.6861	0.7181	0.8474
No log	18.9231	492	0.7055	0.7035	0.7055	0.8399
No log	19.0	494	0.7000	0.7359	0.7000	0.8366
No log	19.0769	496	0.7207	0.7164	0.7207	0.8489
No log	19.1538	498	0.7267	0.7143	0.7267	0.8524
0.5564	19.2308	500	0.7239	0.7247	0.7239	0.8508
0.5564	19.3077	502	0.7295	0.6906	0.7295	0.8541
0.5564	19.3846	504	0.7041	0.7185	0.7041	0.8391
0.5564	19.4615	506	0.6906	0.7226	0.6906	0.8310
0.5564	19.5385	508	0.6932	0.7174	0.6932	0.8326
0.5564	19.6154	510	0.7199	0.7043	0.7199	0.8485

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.2.0
• Tokenizers 0.19.1