README.md

metadata

library_name: transformers
base_model: aubmindlab/bert-base-arabertv02
tags:
  - generated_from_trainer
model-index:
  - name: >-
      ArabicNewSplits7_OSS_usingWellWrittenEssays_FineTuningAraBERT_run2_AugV5_k6_task1_organization
    results: []

ArabicNewSplits7_OSS_usingWellWrittenEssays_FineTuningAraBERT_run2_AugV5_k6_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: 0.6526
• Qwk: 0.7429
• Mse: 0.6526
• Rmse: 0.8079

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: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	0.0444	2	6.6114	0.0123	6.6114	2.5713
No log	0.0889	4	4.4043	0.0732	4.4043	2.0986
No log	0.1333	6	2.8803	0.0952	2.8803	1.6971
No log	0.1778	8	2.4508	0.0284	2.4508	1.5655
No log	0.2222	10	2.0040	0.2143	2.0040	1.4156
No log	0.2667	12	1.7093	0.1667	1.7093	1.3074
No log	0.3111	14	1.6180	0.1869	1.6180	1.2720
No log	0.3556	16	1.4972	0.1698	1.4972	1.2236
No log	0.4	18	1.3365	0.2545	1.3365	1.1561
No log	0.4444	20	1.4337	0.3511	1.4337	1.1974
No log	0.4889	22	1.9006	0.3709	1.9006	1.3786
No log	0.5333	24	1.7709	0.4027	1.7709	1.3308
No log	0.5778	26	1.0056	0.6015	1.0056	1.0028
No log	0.6222	28	0.9092	0.6917	0.9092	0.9535
No log	0.6667	30	1.1067	0.6222	1.1067	1.0520
No log	0.7111	32	0.8426	0.7206	0.8426	0.9179
No log	0.7556	34	0.8974	0.6176	0.8974	0.9473
No log	0.8	36	0.9845	0.6216	0.9845	0.9922
No log	0.8444	38	1.2358	0.6265	1.2358	1.1116
No log	0.8889	40	0.8465	0.7262	0.8465	0.9201
No log	0.9333	42	0.5996	0.7950	0.5996	0.7743
No log	0.9778	44	0.5743	0.7898	0.5743	0.7578
No log	1.0222	46	0.7228	0.7561	0.7228	0.8502
No log	1.0667	48	1.6150	0.4859	1.6150	1.2708
No log	1.1111	50	1.9330	0.4565	1.9330	1.3903
No log	1.1556	52	1.2424	0.6092	1.2424	1.1146
No log	1.2	54	0.6106	0.7953	0.6106	0.7814
No log	1.2444	56	0.7013	0.7632	0.7013	0.8374
No log	1.2889	58	0.6970	0.7273	0.6970	0.8349
No log	1.3333	60	0.6694	0.75	0.6694	0.8182
No log	1.3778	62	0.6057	0.7347	0.6057	0.7783
No log	1.4222	64	0.6522	0.76	0.6522	0.8076
No log	1.4667	66	0.6435	0.7310	0.6435	0.8022
No log	1.5111	68	0.7914	0.6842	0.7914	0.8896
No log	1.5556	70	0.6505	0.7843	0.6505	0.8065
No log	1.6	72	0.6023	0.7692	0.6023	0.7761
No log	1.6444	74	0.5897	0.75	0.5897	0.7679
No log	1.6889	76	0.5682	0.75	0.5682	0.7538
No log	1.7333	78	0.6418	0.7821	0.6418	0.8011
No log	1.7778	80	0.7812	0.7665	0.7812	0.8839
No log	1.8222	82	0.7934	0.7746	0.7934	0.8907
No log	1.8667	84	0.6417	0.7636	0.6417	0.8011
No log	1.9111	86	0.5897	0.775	0.5897	0.7679
No log	1.9556	88	0.7395	0.7484	0.7395	0.8600
No log	2.0	90	0.8112	0.7368	0.8112	0.9007
No log	2.0444	92	0.7697	0.7248	0.7697	0.8773
No log	2.0889	94	0.7133	0.7368	0.7133	0.8445
No log	2.1333	96	0.7442	0.7484	0.7442	0.8627
No log	2.1778	98	0.7393	0.7531	0.7393	0.8598
No log	2.2222	100	0.6957	0.7816	0.6957	0.8341
No log	2.2667	102	0.7206	0.8020	0.7206	0.8489
No log	2.3111	104	0.6310	0.8023	0.6310	0.7944
No log	2.3556	106	0.6352	0.8144	0.6352	0.7970
No log	2.4	108	0.7417	0.7574	0.7417	0.8612
No log	2.4444	110	0.6060	0.7950	0.6060	0.7785
No log	2.4889	112	0.5565	0.8025	0.5565	0.7460
No log	2.5333	114	0.5538	0.7975	0.5538	0.7442
No log	2.5778	116	0.6619	0.7389	0.6619	0.8135
No log	2.6222	118	0.6718	0.75	0.6718	0.8196
No log	2.6667	120	0.5412	0.8075	0.5412	0.7357
No log	2.7111	122	0.5753	0.7853	0.5753	0.7585
No log	2.7556	124	0.6027	0.8144	0.6027	0.7763
No log	2.8	126	0.4854	0.8434	0.4854	0.6967
No log	2.8444	128	0.5949	0.7784	0.5949	0.7713
No log	2.8889	130	0.9325	0.7059	0.9325	0.9657
No log	2.9333	132	1.0228	0.7120	1.0228	1.0114
No log	2.9778	134	0.6469	0.7791	0.6469	0.8043
No log	3.0222	136	0.5702	0.8049	0.5702	0.7551
No log	3.0667	138	0.6165	0.7875	0.6165	0.7851
No log	3.1111	140	0.5653	0.8428	0.5653	0.7519
No log	3.1556	142	0.6222	0.7821	0.6222	0.7888
No log	3.2	144	0.6146	0.7712	0.6146	0.7839
No log	3.2444	146	0.5631	0.7949	0.5631	0.7504
No log	3.2889	148	0.5401	0.8333	0.5401	0.7349
No log	3.3333	150	0.5195	0.8409	0.5195	0.7208
No log	3.3778	152	0.5100	0.8306	0.5100	0.7142
No log	3.4222	154	0.5096	0.8434	0.5096	0.7139
No log	3.4667	156	0.5120	0.8304	0.5120	0.7155
No log	3.5111	158	0.5583	0.8187	0.5583	0.7472
No log	3.5556	160	0.6196	0.7826	0.6196	0.7872
No log	3.6	162	0.6098	0.7949	0.6098	0.7809
No log	3.6444	164	0.6061	0.8052	0.6061	0.7785
No log	3.6889	166	0.6081	0.8077	0.6081	0.7798
No log	3.7333	168	0.5628	0.8098	0.5628	0.7502
No log	3.7778	170	0.8343	0.7374	0.8343	0.9134
No log	3.8222	172	0.9469	0.6936	0.9469	0.9731
No log	3.8667	174	0.7277	0.6849	0.7277	0.8530
No log	3.9111	176	0.6042	0.8077	0.6042	0.7773
No log	3.9556	178	0.6312	0.7799	0.6312	0.7945
No log	4.0	180	0.5510	0.8025	0.5510	0.7423
No log	4.0444	182	0.5365	0.8380	0.5365	0.7325
No log	4.0889	184	0.6132	0.8187	0.6132	0.7831
No log	4.1333	186	0.5215	0.8525	0.5215	0.7222
No log	4.1778	188	0.5144	0.8492	0.5144	0.7173
No log	4.2222	190	0.5815	0.8177	0.5815	0.7625
No log	4.2667	192	0.5696	0.8177	0.5696	0.7547
No log	4.3111	194	0.5859	0.8068	0.5859	0.7654
No log	4.3556	196	0.5982	0.8024	0.5982	0.7734
No log	4.4	198	0.5708	0.8221	0.5708	0.7555
No log	4.4444	200	0.5794	0.8025	0.5794	0.7612
No log	4.4889	202	0.6168	0.7922	0.6168	0.7854
No log	4.5333	204	0.6735	0.76	0.6735	0.8207
No log	4.5778	206	0.6790	0.76	0.6790	0.8240
No log	4.6222	208	0.6946	0.7389	0.6946	0.8334
No log	4.6667	210	0.6741	0.7758	0.6741	0.8210
No log	4.7111	212	0.5764	0.8263	0.5764	0.7592
No log	4.7556	214	0.5793	0.8095	0.5793	0.7611
No log	4.8	216	0.5634	0.8193	0.5634	0.7506
No log	4.8444	218	0.5970	0.7758	0.5970	0.7727
No log	4.8889	220	0.6534	0.7578	0.6534	0.8083
No log	4.9333	222	0.6353	0.7468	0.6353	0.7970
No log	4.9778	224	0.5538	0.7792	0.5538	0.7442
No log	5.0222	226	0.5325	0.8344	0.5325	0.7297
No log	5.0667	228	0.5234	0.8272	0.5234	0.7235
No log	5.1111	230	0.5838	0.7950	0.5838	0.7640
No log	5.1556	232	0.6177	0.7875	0.6177	0.7859
No log	5.2	234	0.6114	0.7792	0.6114	0.7819
No log	5.2444	236	0.6375	0.7586	0.6375	0.7984
No log	5.2889	238	0.6570	0.7568	0.6570	0.8106
No log	5.3333	240	0.6343	0.7568	0.6343	0.7964
No log	5.3778	242	0.6049	0.7632	0.6049	0.7778
No log	5.4222	244	0.6262	0.7550	0.6262	0.7913
No log	5.4667	246	0.6235	0.7568	0.6235	0.7896
No log	5.5111	248	0.6353	0.7568	0.6353	0.7970
No log	5.5556	250	0.6581	0.7285	0.6581	0.8112
No log	5.6	252	0.6473	0.7172	0.6473	0.8046
No log	5.6444	254	0.6317	0.7413	0.6317	0.7948
No log	5.6889	256	0.6310	0.7286	0.6310	0.7944
No log	5.7333	258	0.6335	0.7571	0.6335	0.7959
No log	5.7778	260	0.6349	0.7286	0.6349	0.7968
No log	5.8222	262	0.6375	0.7324	0.6375	0.7984
No log	5.8667	264	0.7811	0.7237	0.7811	0.8838
No log	5.9111	266	0.8595	0.6982	0.8595	0.9271
No log	5.9556	268	0.6906	0.7237	0.6906	0.8310
No log	6.0	270	0.5657	0.8108	0.5657	0.7521
No log	6.0444	272	0.6042	0.7724	0.6042	0.7773
No log	6.0889	274	0.7426	0.7152	0.7426	0.8617
No log	6.1333	276	0.6104	0.7843	0.6104	0.7813
No log	6.1778	278	0.5099	0.8485	0.5099	0.7141
No log	6.2222	280	0.6144	0.8065	0.6144	0.7838
No log	6.2667	282	0.5796	0.8136	0.5796	0.7613
No log	6.3111	284	0.5364	0.8375	0.5364	0.7324
No log	6.3556	286	0.5674	0.8129	0.5674	0.7533
No log	6.4	288	0.6034	0.7843	0.6034	0.7768
No log	6.4444	290	0.6041	0.7974	0.6041	0.7773
No log	6.4889	292	0.6783	0.7114	0.6783	0.8236
No log	6.5333	294	0.8656	0.6957	0.8656	0.9304
No log	6.5778	296	0.9134	0.6533	0.9134	0.9557
No log	6.6222	298	0.8012	0.6475	0.8012	0.8951
No log	6.6667	300	0.7039	0.7338	0.7039	0.8390
No log	6.7111	302	0.6879	0.7568	0.6879	0.8294
No log	6.7556	304	0.7020	0.7417	0.7020	0.8379
No log	6.8	306	0.7252	0.7595	0.7252	0.8516
No log	6.8444	308	0.6971	0.7561	0.6971	0.8349
No log	6.8889	310	0.5765	0.7875	0.5765	0.7593
No log	6.9333	312	0.5433	0.8293	0.5433	0.7371
No log	6.9778	314	0.7664	0.75	0.7664	0.8755
No log	7.0222	316	0.8730	0.7253	0.8730	0.9344
No log	7.0667	318	0.7974	0.7226	0.7974	0.8930
No log	7.1111	320	0.6831	0.7552	0.6831	0.8265
No log	7.1556	322	0.6717	0.7552	0.6717	0.8196
No log	7.2	324	0.6482	0.7324	0.6482	0.8051
No log	7.2444	326	0.6234	0.75	0.6234	0.7896
No log	7.2889	328	0.6360	0.8	0.6360	0.7975
No log	7.3333	330	0.6000	0.8066	0.6000	0.7746
No log	7.3778	332	0.6453	0.7845	0.6453	0.8033
No log	7.4222	334	0.6075	0.7912	0.6075	0.7794
No log	7.4667	336	0.6057	0.7746	0.6057	0.7782
No log	7.5111	338	0.5724	0.7733	0.5724	0.7566
No log	7.5556	340	0.5803	0.7778	0.5803	0.7618
No log	7.6	342	0.6287	0.7286	0.6287	0.7929
No log	7.6444	344	0.6474	0.7606	0.6474	0.8046
No log	7.6889	346	0.6749	0.7234	0.6749	0.8215
No log	7.7333	348	0.6331	0.7361	0.6331	0.7957
No log	7.7778	350	0.5819	0.7891	0.5819	0.7628
No log	7.8222	352	0.5479	0.7843	0.5479	0.7402
No log	7.8667	354	0.5309	0.8263	0.5309	0.7286
No log	7.9111	356	0.5479	0.8052	0.5479	0.7402
No log	7.9556	358	0.5783	0.7763	0.5783	0.7605
No log	8.0	360	0.5649	0.7671	0.5649	0.7516
No log	8.0444	362	0.6276	0.7532	0.6276	0.7922
No log	8.0889	364	0.7619	0.7425	0.7619	0.8729
No log	8.1333	366	0.7498	0.7320	0.7498	0.8659
No log	8.1778	368	0.6637	0.7448	0.6637	0.8147
No log	8.2222	370	0.6423	0.7397	0.6423	0.8014
No log	8.2667	372	0.6098	0.7483	0.6098	0.7809
No log	8.3111	374	0.5812	0.8025	0.5812	0.7623
No log	8.3556	376	0.5601	0.8324	0.5601	0.7484
No log	8.4	378	0.5586	0.8304	0.5586	0.7474
No log	8.4444	380	0.5477	0.8171	0.5477	0.7401
No log	8.4889	382	0.5582	0.7922	0.5582	0.7471
No log	8.5333	384	0.5502	0.8000	0.5502	0.7417
No log	8.5778	386	0.5179	0.8503	0.5179	0.7197
No log	8.6222	388	0.5224	0.8208	0.5224	0.7228
No log	8.6667	390	0.5071	0.8492	0.5071	0.7121
No log	8.7111	392	0.5047	0.8523	0.5047	0.7104
No log	8.7556	394	0.4992	0.8492	0.4992	0.7065
No log	8.8	396	0.4897	0.8475	0.4897	0.6998
No log	8.8444	398	0.5070	0.8606	0.5070	0.7121
No log	8.8889	400	0.5536	0.7808	0.5536	0.7441
No log	8.9333	402	0.5909	0.7586	0.5909	0.7687
No log	8.9778	404	0.6079	0.7586	0.6079	0.7796
No log	9.0222	406	0.6305	0.75	0.6305	0.7940
No log	9.0667	408	0.6599	0.7222	0.6599	0.8123
No log	9.1111	410	0.6034	0.7586	0.6034	0.7768
No log	9.1556	412	0.6246	0.7947	0.6246	0.7903
No log	9.2	414	0.6614	0.76	0.6614	0.8133
No log	9.2444	416	0.6011	0.8105	0.6011	0.7753
No log	9.2889	418	0.6029	0.7517	0.6029	0.7765
No log	9.3333	420	0.8385	0.7219	0.8385	0.9157
No log	9.3778	422	1.0277	0.6705	1.0277	1.0137
No log	9.4222	424	0.9828	0.6216	0.9828	0.9914
No log	9.4667	426	0.8437	0.6853	0.8437	0.9185
No log	9.5111	428	0.6707	0.7324	0.6707	0.8190
No log	9.5556	430	0.6017	0.7361	0.6017	0.7757
No log	9.6	432	0.5792	0.7417	0.5792	0.7610
No log	9.6444	434	0.5700	0.7730	0.5700	0.7550
No log	9.6889	436	0.5775	0.7861	0.5775	0.7599
No log	9.7333	438	0.5584	0.7977	0.5584	0.7473
No log	9.7778	440	0.5143	0.8354	0.5143	0.7171
No log	9.8222	442	0.5308	0.8153	0.5308	0.7286
No log	9.8667	444	0.5678	0.8129	0.5678	0.7535
No log	9.9111	446	0.5905	0.7755	0.5905	0.7684
No log	9.9556	448	0.6385	0.7671	0.6385	0.7991
No log	10.0	450	0.6558	0.75	0.6558	0.8098
No log	10.0444	452	0.6559	0.7552	0.6559	0.8099
No log	10.0889	454	0.6374	0.7639	0.6374	0.7984
No log	10.1333	456	0.6132	0.7755	0.6132	0.7831
No log	10.1778	458	0.5976	0.7568	0.5976	0.7730
No log	10.2222	460	0.5756	0.7853	0.5756	0.7587
No log	10.2667	462	0.5710	0.7853	0.5710	0.7556
No log	10.3111	464	0.5776	0.7867	0.5776	0.7600
No log	10.3556	466	0.6501	0.7361	0.6501	0.8063
No log	10.4	468	0.7655	0.7042	0.7655	0.8749
No log	10.4444	470	0.8029	0.6957	0.8029	0.8961
No log	10.4889	472	0.7443	0.7234	0.7443	0.8627
No log	10.5333	474	0.6264	0.7413	0.6264	0.7915
No log	10.5778	476	0.5276	0.8289	0.5276	0.7264
No log	10.6222	478	0.4788	0.8375	0.4788	0.6920
No log	10.6667	480	0.4495	0.8721	0.4495	0.6704
No log	10.7111	482	0.4472	0.8686	0.4472	0.6688
No log	10.7556	484	0.4392	0.8621	0.4392	0.6627
No log	10.8	486	0.4495	0.8655	0.4495	0.6705
No log	10.8444	488	0.4826	0.8553	0.4826	0.6947
No log	10.8889	490	0.5865	0.7484	0.5865	0.7659
No log	10.9333	492	0.6696	0.7403	0.6696	0.8183
No log	10.9778	494	0.6510	0.7248	0.6510	0.8068
No log	11.0222	496	0.6093	0.7862	0.6093	0.7806
No log	11.0667	498	0.5671	0.8056	0.5671	0.7531
0.365	11.1111	500	0.5384	0.8138	0.5384	0.7338
0.365	11.1556	502	0.5049	0.8289	0.5049	0.7106
0.365	11.2	504	0.4819	0.8642	0.4819	0.6942
0.365	11.2444	506	0.4799	0.8554	0.4799	0.6928
0.365	11.2889	508	0.4839	0.8503	0.4839	0.6957
0.365	11.3333	510	0.4889	0.8415	0.4889	0.6992
0.365	11.3778	512	0.5011	0.8375	0.5011	0.7079
0.365	11.4222	514	0.5409	0.7758	0.5409	0.7355
0.365	11.4667	516	0.5545	0.7448	0.5545	0.7447
0.365	11.5111	518	0.6007	0.7413	0.6007	0.7751
0.365	11.5556	520	0.6531	0.7518	0.6531	0.8081
0.365	11.6	522	0.6526	0.7429	0.6526	0.8079

Framework versions

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