Version_concise_ASAP_FineTuningBERT_AugV12_k1_task1_organization_k1_k1_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: 0.5914
• Qwk: 0.6288
• Mse: 0.5909
• Rmse: 0.7687

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	2	12.6254	0.0	12.6225	3.5528
No log	2.0	4	11.7677	0.0	11.7650	3.4300
No log	3.0	6	11.2421	-0.0228	11.2395	3.3525
No log	4.0	8	10.5051	0.0	10.5025	3.2408
No log	5.0	10	9.1808	0.0	9.1784	3.0296
No log	6.0	12	7.3316	0.0	7.3293	2.7073
No log	7.0	14	5.4161	0.0342	5.4140	2.3268
No log	8.0	16	4.3836	0.0	4.3816	2.0932
No log	9.0	18	3.2766	0.0	3.2747	1.8096
No log	10.0	20	2.4316	0.0005	2.4298	1.5588
No log	11.0	22	1.7215	0.0211	1.7200	1.3115
No log	12.0	24	1.3203	0.0	1.3189	1.1484
No log	13.0	26	1.2706	0.0	1.2692	1.1266
No log	14.0	28	1.0687	0.0	1.0674	1.0332
No log	15.0	30	0.9480	0.0052	0.9468	0.9730
No log	16.0	32	1.0421	0.0106	1.0408	1.0202
No log	17.0	34	0.9772	0.0211	0.9759	0.9879
No log	18.0	36	0.7763	0.4630	0.7752	0.8804
No log	19.0	38	0.7409	0.4576	0.7399	0.8602
No log	20.0	40	0.7992	0.3732	0.7982	0.8934
No log	21.0	42	0.7297	0.4692	0.7287	0.8536
No log	22.0	44	0.6089	0.5214	0.6080	0.7797
No log	23.0	46	0.5899	0.5293	0.5890	0.7675
No log	24.0	48	0.5768	0.5123	0.5760	0.7589
No log	25.0	50	0.6013	0.4755	0.6004	0.7748
No log	26.0	52	0.6364	0.4036	0.6354	0.7971
No log	27.0	54	0.6726	0.3835	0.6718	0.8196
No log	28.0	56	0.6289	0.4102	0.6281	0.7925
No log	29.0	58	0.5149	0.5001	0.5140	0.7169
No log	30.0	60	0.5054	0.5199	0.5045	0.7103
No log	31.0	62	0.5400	0.5923	0.5393	0.7344
No log	32.0	64	0.5796	0.6189	0.5790	0.7609
No log	33.0	66	0.4992	0.6071	0.4984	0.7060
No log	34.0	68	0.4969	0.6307	0.4961	0.7043
No log	35.0	70	0.6292	0.6071	0.6286	0.7929
No log	36.0	72	0.5141	0.6477	0.5135	0.7166
No log	37.0	74	0.4541	0.6400	0.4533	0.6733
No log	38.0	76	0.4776	0.6232	0.4768	0.6905
No log	39.0	78	0.5928	0.6060	0.5921	0.7695
No log	40.0	80	0.6188	0.6071	0.6181	0.7862
No log	41.0	82	0.5156	0.6358	0.5148	0.7175
No log	42.0	84	0.5825	0.6148	0.5818	0.7628
No log	43.0	86	0.5248	0.6388	0.5241	0.7239
No log	44.0	88	0.4917	0.6545	0.4909	0.7007
No log	45.0	90	0.6324	0.6144	0.6317	0.7948
No log	46.0	92	0.8192	0.5665	0.8186	0.9047
No log	47.0	94	0.7559	0.5951	0.7552	0.8690
No log	48.0	96	0.7117	0.6065	0.7111	0.8433
No log	49.0	98	0.8234	0.5901	0.8228	0.9071
No log	50.0	100	0.5934	0.6326	0.5928	0.7699
No log	51.0	102	0.5456	0.6448	0.5450	0.7382
No log	52.0	104	0.7431	0.6060	0.7426	0.8617
No log	53.0	106	0.7111	0.5980	0.7105	0.8429
No log	54.0	108	0.5804	0.6172	0.5796	0.7613
No log	55.0	110	0.6717	0.5912	0.6711	0.8192
No log	56.0	112	0.8626	0.5524	0.8621	0.9285
No log	57.0	114	0.6684	0.6042	0.6678	0.8172
No log	58.0	116	0.4849	0.6541	0.4841	0.6958
No log	59.0	118	0.4744	0.6535	0.4737	0.6883
No log	60.0	120	0.5376	0.6520	0.5371	0.7329
No log	61.0	122	0.6361	0.6326	0.6356	0.7972
No log	62.0	124	0.6973	0.6139	0.6968	0.8347
No log	63.0	126	0.6606	0.6060	0.6601	0.8124
No log	64.0	128	0.5914	0.6288	0.5909	0.7687

Framework versions

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