ASAP_FineTuningBERT_AugV5_k2_task1_organization_fold3

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: 1.8308
• Qwk: 0.0153
• Mse: 1.8322
• Rmse: 1.3536

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	1.0	2	12.0369	-0.0273	12.0357	3.4693
No log	2.0	4	9.4633	0.0	9.4626	3.0761
No log	3.0	6	7.6049	0.0	7.6043	2.7576
No log	4.0	8	6.1200	0.0394	6.1197	2.4738
5.8531	5.0	10	4.8031	0.0137	4.8029	2.1915
5.8531	6.0	12	3.7971	0.0038	3.7971	1.9486
5.8531	7.0	14	2.9654	0.0	2.9655	1.7221
5.8531	8.0	16	2.3844	0.1111	2.3847	1.5443
5.8531	9.0	18	2.0331	0.0319	2.0335	1.4260
2.2417	10.0	20	1.7194	0.0365	1.7199	1.3115
2.2417	11.0	22	1.5676	0.0302	1.5682	1.2523
2.2417	12.0	24	1.6589	0.0302	1.6595	1.2882
2.2417	13.0	26	1.6020	0.0302	1.6026	1.2660
2.2417	14.0	28	1.6796	0.0302	1.6803	1.2963
1.7667	15.0	30	2.0104	0.0707	2.0111	1.4181
1.7667	16.0	32	1.8425	0.0599	1.8432	1.3576
1.7667	17.0	34	1.6998	0.0355	1.7005	1.3040
1.7667	18.0	36	1.6369	0.0309	1.6376	1.2797
1.7667	19.0	38	1.9033	0.0547	1.9041	1.3799
1.4086	20.0	40	1.7512	0.0608	1.7521	1.3237
1.4086	21.0	42	1.6642	0.0402	1.6652	1.2904
1.4086	22.0	44	1.9396	0.0050	1.9407	1.3931
1.4086	23.0	46	2.6915	-0.0257	2.6927	1.6410
1.4086	24.0	48	1.6074	0.0326	1.6086	1.2683
0.825	25.0	50	1.4112	0.0872	1.4123	1.1884
0.825	26.0	52	2.1640	-0.0085	2.1654	1.4715
0.825	27.0	54	1.7786	0.0414	1.7800	1.3342
0.825	28.0	56	2.2321	-0.0188	2.2335	1.4945
0.825	29.0	58	2.3537	-0.0237	2.3550	1.5346
0.3847	30.0	60	1.8764	0.0021	1.8777	1.3703
0.3847	31.0	62	2.3506	-0.0218	2.3521	1.5336
0.3847	32.0	64	2.0331	-0.0125	2.0345	1.4264
0.3847	33.0	66	1.8347	-0.0136	1.8361	1.3550
0.3847	34.0	68	2.4934	-0.0734	2.4950	1.5796
0.1882	35.0	70	1.9518	-0.0191	1.9533	1.3976
0.1882	36.0	72	2.4960	-0.0770	2.4976	1.5804
0.1882	37.0	74	2.0666	-0.0314	2.0682	1.4381
0.1882	38.0	76	1.4082	0.0106	1.4096	1.1873
0.1882	39.0	78	1.9355	-0.0371	1.9370	1.3918
0.1584	40.0	80	2.0086	-0.0278	2.0101	1.4178
0.1584	41.0	82	2.1254	-0.0314	2.1269	1.4584
0.1584	42.0	84	2.0757	-0.0343	2.0772	1.4412
0.1584	43.0	86	1.8165	-0.0132	1.8178	1.3483
0.1584	44.0	88	2.1088	-0.0377	2.1102	1.4526
0.1235	45.0	90	1.5843	0.0297	1.5856	1.2592
0.1235	46.0	92	1.6366	0.0256	1.6379	1.2798
0.1235	47.0	94	2.0505	-0.0217	2.0520	1.4325
0.1235	48.0	96	1.6414	0.0389	1.6428	1.2817
0.1235	49.0	98	1.6070	0.0497	1.6083	1.2682
0.1145	50.0	100	2.4329	-0.0471	2.4346	1.5603
0.1145	51.0	102	2.5226	-0.0446	2.5243	1.5888
0.1145	52.0	104	1.6179	0.0373	1.6193	1.2725
0.1145	53.0	106	1.3149	0.0712	1.3162	1.1473
0.1145	54.0	108	1.6557	0.0193	1.6571	1.2873
0.1446	55.0	110	2.3991	-0.0183	2.4007	1.5494
0.1446	56.0	112	2.2054	-0.0162	2.2068	1.4855
0.1446	57.0	114	1.6303	0.0156	1.6316	1.2773
0.1446	58.0	116	1.2630	0.0890	1.2642	1.1244
0.1446	59.0	118	1.4344	0.0540	1.4357	1.1982
0.1445	60.0	120	1.9633	-0.0091	1.9649	1.4017
0.1445	61.0	122	1.9406	-0.0021	1.9421	1.3936
0.1445	62.0	124	1.5698	0.0287	1.5712	1.2535
0.1445	63.0	126	1.6071	0.0147	1.6085	1.2683
0.1445	64.0	128	1.6257	0.0053	1.6271	1.2756
0.0793	65.0	130	1.8527	-0.0048	1.8541	1.3617
0.0793	66.0	132	1.6608	0.0188	1.6622	1.2893
0.0793	67.0	134	1.6487	0.0233	1.6501	1.2846
0.0793	68.0	136	1.8753	0.0045	1.8767	1.3699
0.0793	69.0	138	1.8249	0.0138	1.8263	1.3514
0.0791	70.0	140	1.6280	0.0077	1.6294	1.2765
0.0791	71.0	142	1.7595	0.0256	1.7609	1.3270
0.0791	72.0	144	1.7854	0.0145	1.7869	1.3367
0.0791	73.0	146	1.6080	0.0223	1.6094	1.2686
0.0791	74.0	148	1.6178	0.0268	1.6192	1.2725
0.0593	75.0	150	1.9138	0.0195	1.9153	1.3839
0.0593	76.0	152	1.9964	0.0048	1.9979	1.4135
0.0593	77.0	154	1.7318	0.0332	1.7333	1.3165
0.0593	78.0	156	1.5459	0.0377	1.5473	1.2439
0.0593	79.0	158	1.6575	0.0342	1.6589	1.2880
0.063	80.0	160	1.8827	0.0202	1.8842	1.3727
0.063	81.0	162	1.9555	0.0209	1.9569	1.3989
0.063	82.0	164	1.8205	0.0137	1.8220	1.3498
0.063	83.0	166	1.8068	0.0151	1.8083	1.3447
0.063	84.0	168	1.8039	0.0201	1.8053	1.3436
0.0575	85.0	170	1.7190	0.0185	1.7204	1.3117
0.0575	86.0	172	1.7114	0.0224	1.7128	1.3088
0.0575	87.0	174	1.8460	0.0180	1.8474	1.3592
0.0575	88.0	176	2.0094	-0.0061	2.0109	1.4181
0.0575	89.0	178	2.0401	-0.0065	2.0416	1.4288
0.0587	90.0	180	1.9117	0.0064	1.9131	1.3832
0.0587	91.0	182	1.7337	0.0181	1.7351	1.3172
0.0587	92.0	184	1.6529	0.0279	1.6543	1.2862
0.0587	93.0	186	1.6662	0.0271	1.6675	1.2913
0.0587	94.0	188	1.7339	0.0189	1.7353	1.3173
0.0518	95.0	190	1.8113	0.0153	1.8126	1.3463
0.0518	96.0	192	1.8286	0.0189	1.8300	1.3528
0.0518	97.0	194	1.8246	0.0175	1.8260	1.3513
0.0518	98.0	196	1.8293	0.0153	1.8307	1.3530
0.0518	99.0	198	1.8348	0.0068	1.8362	1.3551
0.046	100.0	200	1.8308	0.0153	1.8322	1.3536

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.2.0
• Tokenizers 0.19.1