ASAP_FineTuningBERT_AugV8_k1_task1_organization_fold2

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: 0.6421
• Qwk: 0.5223
• Mse: 0.6422
• Rmse: 0.8014

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	11.8464	-0.0226	11.8459	3.4418
No log	2.0	4	9.4643	0.0	9.4641	3.0764
No log	3.0	6	7.6978	0.0	7.6974	2.7744
No log	4.0	8	6.1688	0.0012	6.1685	2.4837
7.2247	5.0	10	4.8597	0.0078	4.8596	2.2044
7.2247	6.0	12	3.8287	0.0	3.8286	1.9567
7.2247	7.0	14	3.0989	0.0	3.0988	1.7603
7.2247	8.0	16	2.3868	0.1570	2.3867	1.5449
7.2247	9.0	18	1.8838	0.0280	1.8839	1.3726
3.0413	10.0	20	1.5678	0.0213	1.5679	1.2522
3.0413	11.0	22	1.3523	0.0107	1.3524	1.1629
3.0413	12.0	24	1.2264	0.0107	1.2264	1.1074
3.0413	13.0	26	1.0188	0.0107	1.0190	1.0094
3.0413	14.0	28	0.8806	0.0437	0.8808	0.9385
1.9988	15.0	30	0.9711	0.0433	0.9713	0.9855
1.9988	16.0	32	0.9896	0.1024	0.9898	0.9949
1.9988	17.0	34	0.7479	0.3769	0.7482	0.8650
1.9988	18.0	36	0.6923	0.4393	0.6926	0.8322
1.9988	19.0	38	0.7163	0.4268	0.7165	0.8465
1.6487	20.0	40	0.6737	0.4279	0.6740	0.8210
1.6487	21.0	42	0.7314	0.2754	0.7315	0.8553
1.6487	22.0	44	0.7017	0.3049	0.7019	0.8378
1.6487	23.0	46	0.6585	0.4105	0.6590	0.8118
1.6487	24.0	48	0.6354	0.4555	0.6358	0.7974
1.0887	25.0	50	0.5627	0.4077	0.5629	0.7503
1.0887	26.0	52	0.5995	0.3888	0.5998	0.7745
1.0887	27.0	54	0.5505	0.4578	0.5508	0.7422
1.0887	28.0	56	0.6032	0.4617	0.6036	0.7769
1.0887	29.0	58	0.5959	0.4348	0.5963	0.7722
0.6773	30.0	60	0.7497	0.3657	0.7500	0.8660
0.6773	31.0	62	0.7740	0.3685	0.7743	0.8799
0.6773	32.0	64	0.5952	0.5164	0.5954	0.7716
0.6773	33.0	66	0.5649	0.5137	0.5652	0.7518
0.6773	34.0	68	0.5498	0.5267	0.5500	0.7416
0.5486	35.0	70	0.6386	0.5215	0.6388	0.7992
0.5486	36.0	72	0.7330	0.4579	0.7331	0.8562
0.5486	37.0	74	0.6378	0.5221	0.6380	0.7987
0.5486	38.0	76	0.6178	0.5325	0.6180	0.7861
0.5486	39.0	78	0.6468	0.5338	0.6470	0.8043
0.2651	40.0	80	0.6196	0.5346	0.6198	0.7873
0.2651	41.0	82	0.6299	0.4857	0.6301	0.7938
0.2651	42.0	84	0.6860	0.4442	0.6862	0.8284
0.2651	43.0	86	0.8729	0.4357	0.8730	0.9343
0.2651	44.0	88	0.7930	0.4600	0.7931	0.8905
0.1976	45.0	90	0.6246	0.4982	0.6248	0.7904
0.1976	46.0	92	0.7254	0.4959	0.7254	0.8517
0.1976	47.0	94	0.8174	0.4747	0.8174	0.9041
0.1976	48.0	96	0.7223	0.4925	0.7223	0.8499
0.1976	49.0	98	0.7536	0.4879	0.7536	0.8681
0.1469	50.0	100	0.6598	0.5261	0.6598	0.8123
0.1469	51.0	102	0.7180	0.5168	0.7180	0.8473
0.1469	52.0	104	0.6602	0.5571	0.6603	0.8126
0.1469	53.0	106	0.5827	0.5681	0.5828	0.7634
0.1469	54.0	108	0.6290	0.5513	0.6290	0.7931
0.0836	55.0	110	0.6384	0.5465	0.6385	0.7990
0.0836	56.0	112	0.7172	0.5025	0.7173	0.8469
0.0836	57.0	114	0.7311	0.4992	0.7312	0.8551
0.0836	58.0	116	0.5856	0.5558	0.5857	0.7653
0.0836	59.0	118	0.5399	0.5634	0.5401	0.7349
0.1237	60.0	120	0.5588	0.5362	0.5589	0.7476
0.1237	61.0	122	0.7607	0.4785	0.7607	0.8722
0.1237	62.0	124	0.8659	0.4445	0.8659	0.9305
0.1237	63.0	126	0.7247	0.4722	0.7248	0.8513
0.1237	64.0	128	0.6317	0.5206	0.6317	0.7948
0.1108	65.0	130	0.6443	0.5265	0.6444	0.8028
0.1108	66.0	132	0.7474	0.5059	0.7475	0.8646
0.1108	67.0	134	0.6988	0.5202	0.6990	0.8360
0.1108	68.0	136	0.5804	0.5534	0.5806	0.7619
0.1108	69.0	138	0.5723	0.5504	0.5724	0.7566
0.1058	70.0	140	0.6308	0.5187	0.6309	0.7943
0.1058	71.0	142	0.7664	0.4307	0.7665	0.8755
0.1058	72.0	144	0.7773	0.4209	0.7775	0.8817
0.1058	73.0	146	0.7165	0.4348	0.7166	0.8465
0.1058	74.0	148	0.7079	0.4765	0.7081	0.8415
0.0732	75.0	150	0.7750	0.4550	0.7751	0.8804
0.0732	76.0	152	0.7501	0.5001	0.7502	0.8661
0.0732	77.0	154	0.6424	0.5251	0.6425	0.8015
0.0732	78.0	156	0.5994	0.5550	0.5995	0.7743
0.0732	79.0	158	0.6118	0.5553	0.6120	0.7823
0.0765	80.0	160	0.6589	0.5342	0.6590	0.8118
0.0765	81.0	162	0.6734	0.5321	0.6735	0.8206
0.0765	82.0	164	0.6775	0.5230	0.6776	0.8232
0.0765	83.0	166	0.6463	0.5046	0.6464	0.8040
0.0765	84.0	168	0.6425	0.4966	0.6426	0.8016
0.0519	85.0	170	0.6701	0.5025	0.6701	0.8186
0.0519	86.0	172	0.7268	0.4906	0.7269	0.8526
0.0519	87.0	174	0.7423	0.4876	0.7423	0.8616
0.0519	88.0	176	0.7178	0.5050	0.7179	0.8473
0.0519	89.0	178	0.6593	0.5114	0.6594	0.8120
0.0626	90.0	180	0.6210	0.5320	0.6211	0.7881
0.0626	91.0	182	0.6235	0.5191	0.6236	0.7897
0.0626	92.0	184	0.6473	0.5068	0.6474	0.8046
0.0626	93.0	186	0.6657	0.5167	0.6659	0.8160
0.0626	94.0	188	0.6634	0.5182	0.6635	0.8145
0.0528	95.0	190	0.6543	0.5154	0.6545	0.8090
0.0528	96.0	192	0.6452	0.5222	0.6453	0.8033
0.0528	97.0	194	0.6381	0.5177	0.6382	0.7989
0.0528	98.0	196	0.6379	0.5163	0.6381	0.7988
0.0528	99.0	198	0.6411	0.5223	0.6412	0.8007
0.0508	100.0	200	0.6421	0.5223	0.6422	0.8014

Framework versions

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