ArabicNewSplits6_FineTuningAraBERTFreeze_run2_AugV5_k12_task2_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: 0.6984
• Qwk: 0.5246
• Mse: 0.6984
• Rmse: 0.8357

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	0.0645	2	6.4367	-0.0218	6.4367	2.5371
No log	0.1290	4	4.4635	-0.0328	4.4635	2.1127
No log	0.1935	6	3.0988	-0.0013	3.0988	1.7603
No log	0.2581	8	2.1395	-0.0042	2.1395	1.4627
No log	0.3226	10	1.4861	0.0428	1.4861	1.2190
No log	0.3871	12	1.1807	0.0685	1.1807	1.0866
No log	0.4516	14	1.0932	0.0285	1.0932	1.0456
No log	0.5161	16	1.0606	0.0130	1.0606	1.0299
No log	0.5806	18	0.9992	0.0288	0.9992	0.9996
No log	0.6452	20	0.9611	-0.0125	0.9611	0.9803
No log	0.7097	22	0.9352	0.0132	0.9352	0.9671
No log	0.7742	24	0.8748	0.0946	0.8748	0.9353
No log	0.8387	26	0.8278	0.1139	0.8278	0.9098
No log	0.9032	28	0.7606	0.1557	0.7606	0.8721
No log	0.9677	30	0.7334	0.1438	0.7334	0.8564
No log	1.0323	32	0.7353	0.1363	0.7353	0.8575
No log	1.0968	34	0.7636	0.1725	0.7636	0.8739
No log	1.1613	36	0.8011	0.1725	0.8011	0.8950
No log	1.2258	38	0.8540	0.1990	0.8540	0.9241
No log	1.2903	40	0.8625	0.2247	0.8625	0.9287
No log	1.3548	42	0.8384	0.2388	0.8384	0.9156
No log	1.4194	44	0.8090	0.2097	0.8090	0.8994
No log	1.4839	46	0.8895	0.2227	0.8895	0.9431
No log	1.5484	48	0.8638	0.2665	0.8638	0.9294
No log	1.6129	50	0.8189	0.2856	0.8189	0.9050
No log	1.6774	52	0.6946	0.2953	0.6946	0.8334
No log	1.7419	54	0.6102	0.3639	0.6102	0.7811
No log	1.8065	56	0.5907	0.4118	0.5907	0.7686
No log	1.8710	58	0.6045	0.3850	0.6045	0.7775
No log	1.9355	60	0.6168	0.3696	0.6168	0.7854
No log	2.0	62	0.6437	0.3458	0.6437	0.8023
No log	2.0645	64	0.6953	0.3556	0.6953	0.8339
No log	2.1290	66	0.8366	0.3549	0.8366	0.9146
No log	2.1935	68	0.9943	0.3034	0.9943	0.9971
No log	2.2581	70	0.9459	0.3907	0.9459	0.9726
No log	2.3226	72	0.7922	0.4300	0.7922	0.8900
No log	2.3871	74	0.6983	0.3835	0.6983	0.8356
No log	2.4516	76	0.6600	0.3839	0.6600	0.8124
No log	2.5161	78	0.6932	0.3501	0.6932	0.8326
No log	2.5806	80	0.7508	0.3172	0.7508	0.8665
No log	2.6452	82	0.7171	0.3426	0.7171	0.8468
No log	2.7097	84	0.6547	0.3986	0.6547	0.8091
No log	2.7742	86	0.6341	0.4112	0.6341	0.7963
No log	2.8387	88	0.5942	0.4320	0.5942	0.7708
No log	2.9032	90	0.5584	0.4640	0.5584	0.7473
No log	2.9677	92	0.5250	0.4642	0.5250	0.7245
No log	3.0323	94	0.5167	0.4649	0.5167	0.7188
No log	3.0968	96	0.5178	0.4587	0.5178	0.7196
No log	3.1613	98	0.5152	0.5037	0.5152	0.7177
No log	3.2258	100	0.5545	0.5306	0.5545	0.7446
No log	3.2903	102	0.5991	0.4904	0.5991	0.7740
No log	3.3548	104	0.5995	0.5178	0.5995	0.7743
No log	3.4194	106	0.5699	0.5249	0.5699	0.7549
No log	3.4839	108	0.5649	0.5243	0.5649	0.7516
No log	3.5484	110	0.5432	0.5275	0.5432	0.7370
No log	3.6129	112	0.5234	0.5826	0.5234	0.7235
No log	3.6774	114	0.5199	0.5664	0.5199	0.7210
No log	3.7419	116	0.5377	0.5263	0.5377	0.7333
No log	3.8065	118	0.5513	0.5298	0.5513	0.7425
No log	3.8710	120	0.5596	0.5393	0.5596	0.7480
No log	3.9355	122	0.5919	0.5357	0.5919	0.7694
No log	4.0	124	0.6056	0.5304	0.6056	0.7782
No log	4.0645	126	0.5944	0.5377	0.5944	0.7710
No log	4.1290	128	0.5646	0.5774	0.5646	0.7514
No log	4.1935	130	0.5383	0.5627	0.5383	0.7337
No log	4.2581	132	0.5354	0.5627	0.5354	0.7317
No log	4.3226	134	0.5548	0.5522	0.5548	0.7449
No log	4.3871	136	0.5671	0.5539	0.5671	0.7531
No log	4.4516	138	0.5554	0.5486	0.5554	0.7453
No log	4.5161	140	0.5519	0.5333	0.5519	0.7429
No log	4.5806	142	0.5595	0.5195	0.5595	0.7480
No log	4.6452	144	0.5743	0.5053	0.5743	0.7578
No log	4.7097	146	0.5620	0.5202	0.5620	0.7497
No log	4.7742	148	0.5425	0.5410	0.5425	0.7366
No log	4.8387	150	0.5470	0.5785	0.5470	0.7396
No log	4.9032	152	0.6078	0.5215	0.6078	0.7796
No log	4.9677	154	0.6553	0.4742	0.6553	0.8095
No log	5.0323	156	0.6875	0.4479	0.6875	0.8292
No log	5.0968	158	0.6774	0.4859	0.6774	0.8230
No log	5.1613	160	0.6189	0.5641	0.6189	0.7867
No log	5.2258	162	0.5798	0.5854	0.5798	0.7614
No log	5.2903	164	0.5327	0.5645	0.5327	0.7298
No log	5.3548	166	0.5107	0.5445	0.5107	0.7146
No log	5.4194	168	0.5085	0.5533	0.5085	0.7131
No log	5.4839	170	0.5130	0.5315	0.5130	0.7162
No log	5.5484	172	0.5346	0.5767	0.5346	0.7312
No log	5.6129	174	0.5588	0.5416	0.5588	0.7475
No log	5.6774	176	0.5571	0.5626	0.5571	0.7464
No log	5.7419	178	0.5428	0.5997	0.5428	0.7367
No log	5.8065	180	0.5607	0.5367	0.5607	0.7488
No log	5.8710	182	0.5822	0.4769	0.5822	0.7630
No log	5.9355	184	0.5733	0.5050	0.5733	0.7572
No log	6.0	186	0.5610	0.5382	0.5610	0.7490
No log	6.0645	188	0.5619	0.5651	0.5619	0.7496
No log	6.1290	190	0.5655	0.5882	0.5655	0.7520
No log	6.1935	192	0.5607	0.5898	0.5607	0.7488
No log	6.2581	194	0.5652	0.6123	0.5652	0.7518
No log	6.3226	196	0.5751	0.5805	0.5751	0.7583
No log	6.3871	198	0.5817	0.5636	0.5817	0.7627
No log	6.4516	200	0.5772	0.5554	0.5772	0.7597
No log	6.5161	202	0.5723	0.5620	0.5723	0.7565
No log	6.5806	204	0.5709	0.5502	0.5709	0.7556
No log	6.6452	206	0.5654	0.5718	0.5654	0.7519
No log	6.7097	208	0.5654	0.5718	0.5654	0.7519
No log	6.7742	210	0.5784	0.5249	0.5784	0.7606
No log	6.8387	212	0.5856	0.5718	0.5856	0.7652
No log	6.9032	214	0.5986	0.5684	0.5986	0.7737
No log	6.9677	216	0.6079	0.5572	0.6079	0.7797
No log	7.0323	218	0.5873	0.6072	0.5873	0.7663
No log	7.0968	220	0.5835	0.5596	0.5835	0.7639
No log	7.1613	222	0.5992	0.5180	0.5992	0.7741
No log	7.2258	224	0.6224	0.5166	0.6224	0.7889
No log	7.2903	226	0.6257	0.5700	0.6257	0.7910
No log	7.3548	228	0.6023	0.5728	0.6023	0.7761
No log	7.4194	230	0.5954	0.5779	0.5954	0.7716
No log	7.4839	232	0.5939	0.5791	0.5939	0.7706
No log	7.5484	234	0.5961	0.5970	0.5961	0.7721
No log	7.6129	236	0.5927	0.6025	0.5927	0.7699
No log	7.6774	238	0.5855	0.5843	0.5855	0.7652
No log	7.7419	240	0.5790	0.5769	0.5790	0.7609
No log	7.8065	242	0.5735	0.5356	0.5735	0.7573
No log	7.8710	244	0.5683	0.5438	0.5683	0.7538
No log	7.9355	246	0.5686	0.5247	0.5686	0.7541
No log	8.0	248	0.5812	0.5411	0.5812	0.7624
No log	8.0645	250	0.6007	0.5414	0.6007	0.7751
No log	8.1290	252	0.6175	0.5598	0.6175	0.7858
No log	8.1935	254	0.6630	0.5230	0.6630	0.8143
No log	8.2581	256	0.6900	0.5486	0.6900	0.8306
No log	8.3226	258	0.6763	0.5712	0.6763	0.8223
No log	8.3871	260	0.6580	0.5230	0.6580	0.8112
No log	8.4516	262	0.6332	0.5316	0.6332	0.7957
No log	8.5161	264	0.6410	0.5014	0.6410	0.8006
No log	8.5806	266	0.6737	0.5324	0.6737	0.8208
No log	8.6452	268	0.6712	0.4904	0.6712	0.8193
No log	8.7097	270	0.6479	0.4946	0.6479	0.8049
No log	8.7742	272	0.6487	0.5065	0.6487	0.8054
No log	8.8387	274	0.6682	0.5111	0.6682	0.8174
No log	8.9032	276	0.6725	0.5111	0.6725	0.8201
No log	8.9677	278	0.6666	0.5054	0.6666	0.8165
No log	9.0323	280	0.6544	0.5216	0.6544	0.8089
No log	9.0968	282	0.6567	0.5232	0.6567	0.8103
No log	9.1613	284	0.6566	0.5408	0.6566	0.8103
No log	9.2258	286	0.6647	0.5486	0.6647	0.8153
No log	9.2903	288	0.6608	0.5385	0.6608	0.8129
No log	9.3548	290	0.6598	0.5521	0.6598	0.8123
No log	9.4194	292	0.6592	0.5380	0.6592	0.8119
No log	9.4839	294	0.6531	0.5325	0.6531	0.8082
No log	9.5484	296	0.6516	0.5300	0.6516	0.8072
No log	9.6129	298	0.6534	0.5190	0.6534	0.8083
No log	9.6774	300	0.6525	0.5300	0.6525	0.8077
No log	9.7419	302	0.6574	0.5300	0.6574	0.8108
No log	9.8065	304	0.6561	0.5247	0.6561	0.8100
No log	9.8710	306	0.6568	0.5505	0.6568	0.8104
No log	9.9355	308	0.6529	0.5418	0.6529	0.8080
No log	10.0	310	0.6564	0.5418	0.6564	0.8102
No log	10.0645	312	0.6667	0.5159	0.6667	0.8165
No log	10.1290	314	0.6674	0.5247	0.6674	0.8169
No log	10.1935	316	0.6751	0.5456	0.6751	0.8216
No log	10.2581	318	0.6782	0.5395	0.6782	0.8235
No log	10.3226	320	0.6646	0.5412	0.6646	0.8152
No log	10.3871	322	0.6636	0.5410	0.6636	0.8146
No log	10.4516	324	0.6714	0.5504	0.6714	0.8194
No log	10.5161	326	0.6823	0.5115	0.6823	0.8260
No log	10.5806	328	0.6758	0.5183	0.6758	0.8220
No log	10.6452	330	0.6648	0.5025	0.6648	0.8154
No log	10.7097	332	0.6637	0.5234	0.6637	0.8147
No log	10.7742	334	0.6671	0.5393	0.6671	0.8168
No log	10.8387	336	0.6611	0.5239	0.6611	0.8131
No log	10.9032	338	0.6576	0.5324	0.6576	0.8109
No log	10.9677	340	0.6596	0.5813	0.6596	0.8122
No log	11.0323	342	0.6550	0.5882	0.6550	0.8093
No log	11.0968	344	0.6540	0.5787	0.6540	0.8087
No log	11.1613	346	0.6578	0.5660	0.6578	0.8111
No log	11.2258	348	0.6671	0.5410	0.6671	0.8168
No log	11.2903	350	0.6598	0.5280	0.6598	0.8123
No log	11.3548	352	0.6542	0.4809	0.6542	0.8088
No log	11.4194	354	0.6561	0.5244	0.6561	0.8100
No log	11.4839	356	0.6635	0.5225	0.6635	0.8145
No log	11.5484	358	0.6679	0.5077	0.6679	0.8173
No log	11.6129	360	0.6698	0.4928	0.6698	0.8184
No log	11.6774	362	0.6620	0.5151	0.6620	0.8136
No log	11.7419	364	0.6478	0.5387	0.6478	0.8049
No log	11.8065	366	0.6387	0.5367	0.6387	0.7992
No log	11.8710	368	0.6391	0.5678	0.6391	0.7994
No log	11.9355	370	0.6255	0.5582	0.6255	0.7909
No log	12.0	372	0.6109	0.6098	0.6109	0.7816
No log	12.0645	374	0.6080	0.5927	0.6080	0.7797
No log	12.1290	376	0.6171	0.5531	0.6171	0.7856
No log	12.1935	378	0.6295	0.5516	0.6295	0.7934
No log	12.2581	380	0.6300	0.5141	0.6300	0.7938
No log	12.3226	382	0.6358	0.4939	0.6358	0.7974
No log	12.3871	384	0.6302	0.4949	0.6302	0.7938
No log	12.4516	386	0.6213	0.4997	0.6213	0.7882
No log	12.5161	388	0.6141	0.5267	0.6141	0.7836
No log	12.5806	390	0.6138	0.5224	0.6138	0.7835
No log	12.6452	392	0.6265	0.5182	0.6265	0.7915
No log	12.7097	394	0.6420	0.5021	0.6420	0.8012
No log	12.7742	396	0.6422	0.5190	0.6422	0.8014
No log	12.8387	398	0.6538	0.5224	0.6538	0.8086
No log	12.9032	400	0.6774	0.4885	0.6774	0.8231
No log	12.9677	402	0.7064	0.4693	0.7064	0.8405
No log	13.0323	404	0.7253	0.4970	0.7253	0.8516
No log	13.0968	406	0.7292	0.4842	0.7292	0.8540
No log	13.1613	408	0.7273	0.4767	0.7273	0.8528
No log	13.2258	410	0.7143	0.4912	0.7143	0.8452
No log	13.2903	412	0.6955	0.4964	0.6955	0.8340
No log	13.3548	414	0.6669	0.5068	0.6669	0.8166
No log	13.4194	416	0.6248	0.5782	0.6248	0.7904
No log	13.4839	418	0.6012	0.5981	0.6012	0.7754
No log	13.5484	420	0.6087	0.6180	0.6087	0.7802
No log	13.6129	422	0.6361	0.5674	0.6361	0.7976
No log	13.6774	424	0.6544	0.5496	0.6544	0.8089
No log	13.7419	426	0.6628	0.5506	0.6628	0.8141
No log	13.8065	428	0.6808	0.5331	0.6808	0.8251
No log	13.8710	430	0.7000	0.5181	0.7000	0.8367
No log	13.9355	432	0.6976	0.4980	0.6976	0.8352
No log	14.0	434	0.6826	0.5377	0.6826	0.8262
No log	14.0645	436	0.6892	0.5058	0.6892	0.8302
No log	14.1290	438	0.6892	0.5117	0.6892	0.8302
No log	14.1935	440	0.6676	0.5469	0.6676	0.8171
No log	14.2581	442	0.6399	0.5702	0.6399	0.7999
No log	14.3226	444	0.6453	0.5689	0.6453	0.8033
No log	14.3871	446	0.6628	0.5891	0.6628	0.8142
No log	14.4516	448	0.6894	0.5442	0.6894	0.8303
No log	14.5161	450	0.7012	0.5427	0.7012	0.8374
No log	14.5806	452	0.7244	0.5343	0.7244	0.8511
No log	14.6452	454	0.7649	0.5021	0.7649	0.8746
No log	14.7097	456	0.7798	0.4943	0.7798	0.8831
No log	14.7742	458	0.7552	0.5022	0.7552	0.8690
No log	14.8387	460	0.7079	0.5282	0.7079	0.8414
No log	14.9032	462	0.6818	0.5249	0.6818	0.8257
No log	14.9677	464	0.6785	0.5538	0.6785	0.8237
No log	15.0323	466	0.6673	0.5509	0.6673	0.8169
No log	15.0968	468	0.6652	0.5621	0.6652	0.8156
No log	15.1613	470	0.6683	0.5702	0.6683	0.8175
No log	15.2258	472	0.6670	0.5589	0.6670	0.8167
No log	15.2903	474	0.6584	0.6082	0.6584	0.8114
No log	15.3548	476	0.6636	0.5983	0.6636	0.8146
No log	15.4194	478	0.6711	0.6019	0.6711	0.8192
No log	15.4839	480	0.6922	0.5292	0.6922	0.8320
No log	15.5484	482	0.7104	0.5211	0.7104	0.8429
No log	15.6129	484	0.7238	0.4936	0.7238	0.8508
No log	15.6774	486	0.7214	0.4879	0.7214	0.8493
No log	15.7419	488	0.7104	0.5030	0.7104	0.8429
No log	15.8065	490	0.6750	0.5395	0.6750	0.8216
No log	15.8710	492	0.6474	0.5871	0.6474	0.8046
No log	15.9355	494	0.6394	0.5757	0.6394	0.7996
No log	16.0	496	0.6429	0.5798	0.6429	0.8018
No log	16.0645	498	0.6561	0.5938	0.6561	0.8100
0.5914	16.1290	500	0.6792	0.5630	0.6792	0.8242
0.5914	16.1935	502	0.6800	0.5334	0.6800	0.8246
0.5914	16.2581	504	0.6680	0.5505	0.6680	0.8173
0.5914	16.3226	506	0.6712	0.5433	0.6712	0.8193
0.5914	16.3871	508	0.6888	0.5403	0.6888	0.8299
0.5914	16.4516	510	0.6984	0.5246	0.6984	0.8357

Framework versions

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