Version_weird_ASAP_FineTuningBERT_AugV12_k15_task1_organization_k15_k15_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: 0.9513
• Qwk: 0.5470
• Mse: 0.9509
• Rmse: 0.9752

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	3	10.4482	-0.0072	10.4459	3.2320
No log	2.0	6	7.4753	0.0	7.4731	2.7337
No log	3.0	9	5.0845	0.0118	5.0823	2.2544
No log	4.0	12	3.6009	0.0	3.5989	1.8971
No log	5.0	15	2.6022	0.0	2.6004	1.6126
No log	6.0	18	1.8218	0.0315	1.8202	1.3491
No log	7.0	21	1.3690	0.0	1.3675	1.1694
No log	8.0	24	1.0505	0.0	1.0491	1.0243
No log	9.0	27	0.9151	0.1120	0.9140	0.9560
No log	10.0	30	0.9265	0.0429	0.9255	0.9620
No log	11.0	33	1.1403	0.0429	1.1395	1.0675
No log	12.0	36	1.3652	0.1718	1.3645	1.1681
No log	13.0	39	1.4218	0.2260	1.4212	1.1921
No log	14.0	42	1.7763	0.1913	1.7759	1.3326
No log	15.0	45	1.4090	0.3023	1.4085	1.1868
No log	16.0	48	0.5185	0.5804	0.5177	0.7195
No log	17.0	51	0.4690	0.6585	0.4682	0.6842
No log	18.0	54	0.4507	0.7013	0.4501	0.6709
No log	19.0	57	0.5190	0.7074	0.5186	0.7201
No log	20.0	60	0.6897	0.6530	0.6895	0.8303
No log	21.0	63	0.7672	0.6346	0.7670	0.8758
No log	22.0	66	1.0355	0.5614	1.0353	1.0175
No log	23.0	69	1.0384	0.5631	1.0383	1.0189
No log	24.0	72	0.7359	0.6521	0.7357	0.8577
No log	25.0	75	1.7462	0.4538	1.7460	1.3214
No log	26.0	78	0.5689	0.6818	0.5687	0.7541
No log	27.0	81	1.3437	0.5012	1.3436	1.1591
No log	28.0	84	0.5869	0.6912	0.5867	0.7659
No log	29.0	87	1.3578	0.4926	1.3576	1.1651
No log	30.0	90	0.6226	0.6555	0.6221	0.7887
No log	31.0	93	1.3525	0.4792	1.3522	1.1628
No log	32.0	96	0.5314	0.6771	0.5310	0.7287
No log	33.0	99	0.8834	0.6115	0.8832	0.9398
No log	34.0	102	0.7571	0.6360	0.7570	0.8701
No log	35.0	105	0.4899	0.7227	0.4897	0.6998
No log	36.0	108	1.2831	0.4970	1.2830	1.1327
No log	37.0	111	0.8070	0.5908	0.8066	0.8981
No log	38.0	114	0.8400	0.5913	0.8396	0.9163
No log	39.0	117	0.6635	0.6453	0.6632	0.8144
No log	40.0	120	1.0155	0.5500	1.0152	1.0076
No log	41.0	123	0.8890	0.5636	0.8886	0.9427
No log	42.0	126	0.9799	0.5411	0.9796	0.9897
No log	43.0	129	0.8360	0.6080	0.8358	0.9142
No log	44.0	132	0.9687	0.5573	0.9684	0.9841
No log	45.0	135	0.8720	0.5721	0.8717	0.9336
No log	46.0	138	1.1820	0.4946	1.1817	1.0871
No log	47.0	141	0.7276	0.6349	0.7273	0.8528
No log	48.0	144	1.0224	0.5494	1.0222	1.0110
No log	49.0	147	0.7543	0.6011	0.7540	0.8683
No log	50.0	150	1.2295	0.4756	1.2292	1.1087
No log	51.0	153	0.8990	0.5508	0.8987	0.9480
No log	52.0	156	1.0261	0.5414	1.0258	1.0128
No log	53.0	159	0.8859	0.6087	0.8857	0.9411
No log	54.0	162	0.7708	0.6402	0.7705	0.8778
No log	55.0	165	0.9513	0.5470	0.9509	0.9752

Framework versions

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