ArabicNewSplits4_WithDuplicationsForScore5_FineTuningAraBERT_run1_AugV5_k7_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: 0.9163
• Qwk: 0.4497
• Mse: 0.9163
• Rmse: 0.9572

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	0.0526	2	3.8602	-0.0075	3.8602	1.9647
No log	0.1053	4	2.0502	0.1033	2.0502	1.4318
No log	0.1579	6	1.0036	0.0569	1.0036	1.0018
No log	0.2105	8	0.8022	0.0767	0.8022	0.8956
No log	0.2632	10	0.7628	0.2101	0.7628	0.8734
No log	0.3158	12	0.8904	0.1689	0.8904	0.9436
No log	0.3684	14	0.8421	0.2006	0.8421	0.9177
No log	0.4211	16	0.7616	0.1418	0.7616	0.8727
No log	0.4737	18	0.7596	0.1024	0.7596	0.8716
No log	0.5263	20	0.9649	0.1036	0.9649	0.9823
No log	0.5789	22	0.9713	0.0891	0.9713	0.9855
No log	0.6316	24	0.8241	0.1624	0.8241	0.9078
No log	0.6842	26	0.6995	0.1056	0.6995	0.8363
No log	0.7368	28	0.7167	0.1494	0.7167	0.8466
No log	0.7895	30	0.7387	0.1299	0.7387	0.8595
No log	0.8421	32	0.7327	0.1299	0.7327	0.8560
No log	0.8947	34	0.7350	0.1299	0.7350	0.8573
No log	0.9474	36	0.6986	0.1727	0.6986	0.8358
No log	1.0	38	0.6813	0.2019	0.6813	0.8254
No log	1.0526	40	0.6950	0.1170	0.6950	0.8337
No log	1.1053	42	0.8013	0.0939	0.8013	0.8952
No log	1.1579	44	0.8410	0.0612	0.8410	0.9171
No log	1.2105	46	0.7686	0.0364	0.7686	0.8767
No log	1.2632	48	0.7015	0.1372	0.7015	0.8375
No log	1.3158	50	0.6791	0.1628	0.6791	0.8241
No log	1.3684	52	0.6813	0.2196	0.6813	0.8254
No log	1.4211	54	0.6684	0.1971	0.6684	0.8176
No log	1.4737	56	0.7014	0.2137	0.7014	0.8375
No log	1.5263	58	0.7221	0.2806	0.7221	0.8498
No log	1.5789	60	0.7473	0.3096	0.7473	0.8644
No log	1.6316	62	0.7127	0.2855	0.7127	0.8442
No log	1.6842	64	0.6704	0.3534	0.6704	0.8188
No log	1.7368	66	0.6335	0.3360	0.6335	0.7959
No log	1.7895	68	0.5832	0.3916	0.5832	0.7637
No log	1.8421	70	0.5961	0.3755	0.5961	0.7721
No log	1.8947	72	0.6794	0.3170	0.6794	0.8243
No log	1.9474	74	0.7582	0.3271	0.7582	0.8708
No log	2.0	76	0.8104	0.3518	0.8104	0.9002
No log	2.0526	78	0.8724	0.4108	0.8724	0.9340
No log	2.1053	80	0.8300	0.4144	0.8300	0.9111
No log	2.1579	82	0.7886	0.3850	0.7886	0.8880
No log	2.2105	84	0.7589	0.4738	0.7589	0.8711
No log	2.2632	86	0.6921	0.4787	0.6921	0.8319
No log	2.3158	88	0.6643	0.4355	0.6643	0.8150
No log	2.3684	90	0.6790	0.4348	0.6790	0.8240
No log	2.4211	92	0.6938	0.4592	0.6938	0.8330
No log	2.4737	94	0.8012	0.4341	0.8012	0.8951
No log	2.5263	96	0.9559	0.4049	0.9559	0.9777
No log	2.5789	98	0.8978	0.4377	0.8978	0.9475
No log	2.6316	100	0.9207	0.4243	0.9207	0.9595
No log	2.6842	102	0.9532	0.4243	0.9532	0.9763
No log	2.7368	104	0.9279	0.4207	0.9279	0.9633
No log	2.7895	106	0.8212	0.4495	0.8212	0.9062
No log	2.8421	108	0.8336	0.4457	0.8336	0.9130
No log	2.8947	110	0.9310	0.4247	0.9310	0.9649
No log	2.9474	112	1.0450	0.3876	1.0450	1.0223
No log	3.0	114	1.0876	0.3814	1.0876	1.0429
No log	3.0526	116	1.1339	0.3508	1.1339	1.0649
No log	3.1053	118	1.0475	0.3788	1.0475	1.0235
No log	3.1579	120	0.9433	0.3790	0.9433	0.9712
No log	3.2105	122	0.8946	0.3709	0.8946	0.9458
No log	3.2632	124	0.8187	0.3796	0.8187	0.9048
No log	3.3158	126	0.8813	0.3916	0.8813	0.9388
No log	3.3684	128	1.0411	0.3857	1.0411	1.0203
No log	3.4211	130	1.2436	0.4029	1.2436	1.1152
No log	3.4737	132	1.4599	0.3681	1.4599	1.2082
No log	3.5263	134	1.5030	0.3408	1.5030	1.2260
No log	3.5789	136	1.5084	0.3492	1.5084	1.2282
No log	3.6316	138	1.5340	0.3623	1.5340	1.2385
No log	3.6842	140	1.3817	0.3540	1.3817	1.1755
No log	3.7368	142	1.0375	0.4104	1.0375	1.0186
No log	3.7895	144	0.8105	0.4397	0.8105	0.9003
No log	3.8421	146	0.7328	0.4756	0.7328	0.8560
No log	3.8947	148	0.8295	0.3872	0.8295	0.9108
No log	3.9474	150	0.8284	0.3880	0.8284	0.9102
No log	4.0	152	0.8008	0.4146	0.8008	0.8949
No log	4.0526	154	0.8320	0.4210	0.8320	0.9122
No log	4.1053	156	1.0359	0.4281	1.0359	1.0178
No log	4.1579	158	1.1934	0.4149	1.1934	1.0924
No log	4.2105	160	1.1429	0.4265	1.1429	1.0691
No log	4.2632	162	1.0737	0.4097	1.0737	1.0362
No log	4.3158	164	0.9710	0.4242	0.9710	0.9854
No log	4.3684	166	0.9013	0.4244	0.9013	0.9494
No log	4.4211	168	0.9506	0.4175	0.9506	0.9750
No log	4.4737	170	0.9696	0.3647	0.9696	0.9847
No log	4.5263	172	0.9355	0.4175	0.9355	0.9672
No log	4.5789	174	0.8382	0.4319	0.8382	0.9155
No log	4.6316	176	0.8161	0.4086	0.8161	0.9034
No log	4.6842	178	0.8538	0.4855	0.8538	0.9240
No log	4.7368	180	0.9747	0.4229	0.9747	0.9873
No log	4.7895	182	1.1465	0.4076	1.1465	1.0708
No log	4.8421	184	1.2238	0.4067	1.2238	1.1063
No log	4.8947	186	1.1750	0.4103	1.1750	1.0840
No log	4.9474	188	1.1001	0.3884	1.1001	1.0488
No log	5.0	190	1.0107	0.3604	1.0107	1.0053
No log	5.0526	192	0.9310	0.3786	0.9310	0.9649
No log	5.1053	194	0.8380	0.4264	0.8380	0.9154
No log	5.1579	196	0.7983	0.4078	0.7983	0.8935
No log	5.2105	198	0.8076	0.3864	0.8076	0.8987
No log	5.2632	200	0.8247	0.4041	0.8247	0.9081
No log	5.3158	202	0.8258	0.4043	0.8258	0.9087
No log	5.3684	204	0.8127	0.4110	0.8127	0.9015
No log	5.4211	206	0.8263	0.4387	0.8263	0.9090
No log	5.4737	208	0.8609	0.4086	0.8609	0.9278
No log	5.5263	210	0.9270	0.3926	0.9270	0.9628
No log	5.5789	212	0.9702	0.3615	0.9702	0.9850
No log	5.6316	214	0.9868	0.3517	0.9868	0.9934
No log	5.6842	216	0.9818	0.3349	0.9818	0.9909
No log	5.7368	218	0.9224	0.3683	0.9224	0.9604
No log	5.7895	220	0.8553	0.4367	0.8553	0.9248
No log	5.8421	222	0.7837	0.4478	0.7837	0.8853
No log	5.8947	224	0.7243	0.4947	0.7243	0.8511
No log	5.9474	226	0.7168	0.4535	0.7168	0.8466
No log	6.0	228	0.7669	0.4679	0.7669	0.8757
No log	6.0526	230	0.8583	0.4533	0.8583	0.9264
No log	6.1053	232	0.9875	0.4210	0.9875	0.9937
No log	6.1579	234	1.1331	0.4044	1.1331	1.0645
No log	6.2105	236	1.2105	0.3778	1.2105	1.1002
No log	6.2632	238	1.2038	0.3447	1.2038	1.0972
No log	6.3158	240	1.0919	0.3397	1.0919	1.0449
No log	6.3684	242	0.9591	0.4244	0.9591	0.9793
No log	6.4211	244	0.9081	0.4429	0.9081	0.9529
No log	6.4737	246	0.8941	0.4682	0.8941	0.9456
No log	6.5263	248	0.8924	0.4338	0.8924	0.9446
No log	6.5789	250	0.8720	0.4226	0.8720	0.9338
No log	6.6316	252	0.8286	0.4007	0.8286	0.9103
No log	6.6842	254	0.7867	0.4415	0.7867	0.8870
No log	6.7368	256	0.7480	0.4766	0.7480	0.8649
No log	6.7895	258	0.7346	0.4700	0.7346	0.8571
No log	6.8421	260	0.7330	0.4658	0.7330	0.8562
No log	6.8947	262	0.7643	0.4429	0.7643	0.8743
No log	6.9474	264	0.8357	0.4420	0.8357	0.9141
No log	7.0	266	0.9106	0.4505	0.9106	0.9543
No log	7.0526	268	0.9988	0.4093	0.9988	0.9994
No log	7.1053	270	1.0798	0.4121	1.0798	1.0391
No log	7.1579	272	1.1439	0.4232	1.1439	1.0695
No log	7.2105	274	1.1322	0.4231	1.1322	1.0641
No log	7.2632	276	1.0678	0.4122	1.0678	1.0334
No log	7.3158	278	0.9868	0.4262	0.9868	0.9934
No log	7.3684	280	0.9115	0.4601	0.9115	0.9547
No log	7.4211	282	0.8799	0.4650	0.8799	0.9380
No log	7.4737	284	0.8766	0.4815	0.8766	0.9363
No log	7.5263	286	0.8943	0.4431	0.8943	0.9457
No log	7.5789	288	0.9127	0.4373	0.9127	0.9554
No log	7.6316	290	0.9235	0.4373	0.9235	0.9610
No log	7.6842	292	0.8977	0.4503	0.8977	0.9475
No log	7.7368	294	0.8698	0.4643	0.8698	0.9326
No log	7.7895	296	0.8505	0.4794	0.8505	0.9222
No log	7.8421	298	0.8336	0.4933	0.8336	0.9130
No log	7.8947	300	0.8404	0.4717	0.8404	0.9168
No log	7.9474	302	0.8606	0.4638	0.8606	0.9277
No log	8.0	304	0.8978	0.4301	0.8978	0.9475
No log	8.0526	306	0.8901	0.4564	0.8901	0.9435
No log	8.1053	308	0.8701	0.4638	0.8701	0.9328
No log	8.1579	310	0.8453	0.4638	0.8453	0.9194
No log	8.2105	312	0.8296	0.4653	0.8296	0.9108
No log	8.2632	314	0.8106	0.4513	0.8106	0.9004
No log	8.3158	316	0.7978	0.4663	0.7978	0.8932
No log	8.3684	318	0.7910	0.4678	0.7910	0.8894
No log	8.4211	320	0.8063	0.4513	0.8063	0.8979
No log	8.4737	322	0.8294	0.4527	0.8294	0.9107
No log	8.5263	324	0.8721	0.4521	0.8721	0.9338
No log	8.5789	326	0.9205	0.4321	0.9205	0.9594
No log	8.6316	328	0.9756	0.4353	0.9756	0.9877
No log	8.6842	330	1.0064	0.4364	1.0064	1.0032
No log	8.7368	332	1.0289	0.4313	1.0289	1.0144
No log	8.7895	334	1.0279	0.4187	1.0279	1.0138
No log	8.8421	336	1.0062	0.4186	1.0062	1.0031
No log	8.8947	338	0.9627	0.4349	0.9627	0.9812
No log	8.9474	340	0.9207	0.4371	0.9207	0.9596
No log	9.0	342	0.8870	0.4521	0.8870	0.9418
No log	9.0526	344	0.8579	0.48	0.8579	0.9262
No log	9.1053	346	0.8370	0.4818	0.8370	0.9149
No log	9.1579	348	0.8262	0.4825	0.8262	0.9089
No log	9.2105	350	0.8201	0.4760	0.8201	0.9056
No log	9.2632	352	0.8184	0.4747	0.8184	0.9046
No log	9.3158	354	0.8275	0.4747	0.8275	0.9097
No log	9.3684	356	0.8447	0.4806	0.8447	0.9191
No log	9.4211	358	0.8617	0.4806	0.8617	0.9283
No log	9.4737	360	0.8762	0.4657	0.8762	0.9361
No log	9.5263	362	0.8873	0.4579	0.8873	0.9420
No log	9.5789	364	0.8954	0.4575	0.8954	0.9463
No log	9.6316	366	0.8994	0.4561	0.8994	0.9483
No log	9.6842	368	0.9049	0.4497	0.9049	0.9512
No log	9.7368	370	0.9108	0.4497	0.9108	0.9544
No log	9.7895	372	0.9154	0.4497	0.9154	0.9568
No log	9.8421	374	0.9164	0.4497	0.9164	0.9573
No log	9.8947	376	0.9161	0.4497	0.9161	0.9571
No log	9.9474	378	0.9163	0.4497	0.9163	0.9572
No log	10.0	380	0.9163	0.4497	0.9163	0.9572

Framework versions

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