Version_Test_ASAP_FineTuningBERT_AugV14_k3_task1_organization_k3_k3_fold0

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: 0.6550
• Qwk: 0.6231
• Mse: 0.6550
• Rmse: 0.8093

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	10.4028	0.0054	10.4028	3.2253
No log	2.0	6	7.5088	0.0	7.5088	2.7402
No log	3.0	9	5.6328	0.0435	5.6328	2.3733
No log	4.0	12	4.0678	0.0115	4.0678	2.0169
No log	5.0	15	2.9845	0.0077	2.9845	1.7276
No log	6.0	18	2.1322	0.0942	2.1322	1.4602
No log	7.0	21	1.5600	0.0316	1.5600	1.2490
No log	8.0	24	1.1292	0.0316	1.1292	1.0626
No log	9.0	27	0.8760	0.1215	0.8760	0.9360
No log	10.0	30	0.7488	0.1954	0.7488	0.8653
No log	11.0	33	0.6869	0.1756	0.6869	0.8288
No log	12.0	36	0.6085	0.2436	0.6085	0.7800
No log	13.0	39	0.4681	0.4806	0.4681	0.6842
No log	14.0	42	0.4883	0.6137	0.4883	0.6988
No log	15.0	45	0.7964	0.5063	0.7964	0.8924
No log	16.0	48	0.5164	0.6148	0.5164	0.7186
No log	17.0	51	0.5528	0.5617	0.5528	0.7435
No log	18.0	54	0.8015	0.5280	0.8015	0.8953
No log	19.0	57	0.5562	0.6180	0.5562	0.7458
No log	20.0	60	0.5415	0.6243	0.5415	0.7358
No log	21.0	63	0.5694	0.6155	0.5694	0.7546
No log	22.0	66	0.5739	0.5836	0.5739	0.7576
No log	23.0	69	0.8284	0.5289	0.8284	0.9101
No log	24.0	72	0.5537	0.6171	0.5537	0.7441
No log	25.0	75	0.7509	0.5531	0.7509	0.8666
No log	26.0	78	0.6316	0.6037	0.6316	0.7948
No log	27.0	81	0.6543	0.6080	0.6543	0.8089
No log	28.0	84	0.6408	0.6211	0.6408	0.8005
No log	29.0	87	0.6612	0.6246	0.6612	0.8132
No log	30.0	90	0.7492	0.5808	0.7492	0.8656
No log	31.0	93	0.6959	0.5974	0.6959	0.8342
No log	32.0	96	0.6640	0.6212	0.6640	0.8148
No log	33.0	99	0.6369	0.6083	0.6369	0.7981
No log	34.0	102	0.7664	0.5722	0.7664	0.8754
No log	35.0	105	0.6597	0.6221	0.6597	0.8122
No log	36.0	108	0.6333	0.6172	0.6333	0.7958
No log	37.0	111	0.7306	0.5908	0.7306	0.8547
No log	38.0	114	0.6727	0.6008	0.6727	0.8202
No log	39.0	117	0.7912	0.5694	0.7912	0.8895
No log	40.0	120	0.6527	0.6262	0.6527	0.8079
No log	41.0	123	0.6892	0.5846	0.6892	0.8302
No log	42.0	126	0.6332	0.6281	0.6332	0.7957
No log	43.0	129	0.6322	0.6232	0.6322	0.7951
No log	44.0	132	0.6541	0.6176	0.6541	0.8088
No log	45.0	135	0.6453	0.6135	0.6453	0.8033
No log	46.0	138	0.6257	0.6177	0.6257	0.7910
No log	47.0	141	0.6561	0.6307	0.6561	0.8100
No log	48.0	144	0.6380	0.6119	0.6380	0.7988
No log	49.0	147	0.6820	0.6190	0.6820	0.8258
No log	50.0	150	0.6393	0.6119	0.6393	0.7995
No log	51.0	153	0.6625	0.6184	0.6625	0.8139
No log	52.0	156	0.6410	0.5946	0.6410	0.8006
No log	53.0	159	0.6957	0.6125	0.6957	0.8341
No log	54.0	162	0.6319	0.6126	0.6319	0.7949
No log	55.0	165	0.6780	0.6083	0.6780	0.8234
No log	56.0	168	0.7005	0.5749	0.7005	0.8370
No log	57.0	171	0.6624	0.6010	0.6624	0.8139
No log	58.0	174	0.8261	0.5429	0.8261	0.9089
No log	59.0	177	0.6549	0.5989	0.6549	0.8093
No log	60.0	180	0.6499	0.5981	0.6499	0.8062
No log	61.0	183	0.8449	0.5390	0.8449	0.9192
No log	62.0	186	0.6954	0.5914	0.6954	0.8339
No log	63.0	189	0.6019	0.6190	0.6019	0.7758
No log	64.0	192	0.7059	0.5872	0.7059	0.8402
No log	65.0	195	0.7238	0.5934	0.7238	0.8507
No log	66.0	198	0.6351	0.6122	0.6351	0.7969
No log	67.0	201	0.6550	0.6231	0.6550	0.8093

Framework versions

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