Version_concise_ASAP_FineTuningBERT_AugV12_k5_task1_organization_k5_k5_fold1

This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.0082
• Qwk: 0.2349
• Mse: 1.0071
• Rmse: 1.0036

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: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	1.0	5	5.9079	-0.0091	5.9055	2.4301
No log	2.0	10	3.3964	0.0	3.3944	1.8424
No log	3.0	15	2.1392	0.0509	2.1375	1.4620
No log	4.0	20	1.4072	0.0274	1.4058	1.1857
No log	5.0	25	0.9931	0.0	0.9919	0.9959
No log	6.0	30	1.1789	0.0619	1.1777	1.0852
No log	7.0	35	1.4292	0.0482	1.4281	1.1950
No log	8.0	40	1.3560	0.1206	1.3551	1.1641
No log	9.0	45	0.9147	0.1148	0.9136	0.9558
No log	10.0	50	1.2838	0.1409	1.2829	1.1327
No log	11.0	55	1.0846	0.2616	1.0837	1.0410
No log	12.0	60	1.1800	0.1937	1.1791	1.0858
No log	13.0	65	1.4527	0.1030	1.4516	1.2048
No log	14.0	70	1.2451	0.1817	1.2441	1.1154
No log	15.0	75	1.3629	0.1995	1.3621	1.1671
No log	16.0	80	1.2145	0.2249	1.2138	1.1017
No log	17.0	85	1.1639	0.2026	1.1630	1.0784
No log	18.0	90	1.1685	0.2096	1.1675	1.0805
No log	19.0	95	1.4510	0.1435	1.4496	1.2040
No log	20.0	100	0.9683	0.2993	0.9675	0.9836
No log	21.0	105	1.1461	0.2373	1.1451	1.0701
No log	22.0	110	1.2159	0.2055	1.2147	1.1022
No log	23.0	115	0.9776	0.2499	0.9768	0.9883
No log	24.0	120	0.9286	0.2879	0.9278	0.9632
No log	25.0	125	1.0182	0.2672	1.0173	1.0086
No log	26.0	130	1.1489	0.2425	1.1479	1.0714
No log	27.0	135	1.1386	0.2360	1.1376	1.0666
No log	28.0	140	1.1262	0.2096	1.1253	1.0608
No log	29.0	145	0.9602	0.2418	0.9593	0.9795
No log	30.0	150	1.0533	0.2508	1.0524	1.0259
No log	31.0	155	0.8922	0.3243	0.8914	0.9442
No log	32.0	160	0.9735	0.2560	0.9725	0.9862
No log	33.0	165	1.0091	0.2014	1.0081	1.0040
No log	34.0	170	0.9832	0.2459	0.9823	0.9911
No log	35.0	175	0.9670	0.2751	0.9660	0.9829
No log	36.0	180	0.9844	0.2695	0.9833	0.9916
No log	37.0	185	1.0416	0.2174	1.0405	1.0200
No log	38.0	190	1.1179	0.1518	1.1167	1.0567
No log	39.0	195	1.0095	0.2181	1.0084	1.0042
No log	40.0	200	1.0970	0.2046	1.0959	1.0468
No log	41.0	205	0.9266	0.2762	0.9255	0.9621
No log	42.0	210	0.9311	0.2663	0.9301	0.9644
No log	43.0	215	0.9782	0.2222	0.9772	0.9885
No log	44.0	220	0.9708	0.2121	0.9697	0.9848
No log	45.0	225	1.0406	0.1842	1.0395	1.0196
No log	46.0	230	0.9357	0.2455	0.9347	0.9668
No log	47.0	235	0.8769	0.2809	0.8759	0.9359
No log	48.0	240	1.0187	0.2284	1.0176	1.0088
No log	49.0	245	1.0443	0.1842	1.0431	1.0213
No log	50.0	250	0.9069	0.2575	0.9060	0.9518
No log	51.0	255	1.0082	0.2349	1.0071	1.0036

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0