ASAP_FineTuningBERT_AugV5_k2_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: 1.6688
• Qwk: 0.0798
• Mse: 1.6690
• Rmse: 1.2919

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	11.8036	-0.0219	11.8032	3.4356
No log	2.0	4	9.4543	0.0005	9.4541	3.0748
No log	3.0	6	7.5752	0.0	7.5749	2.7523
No log	4.0	8	6.1170	0.0067	6.1167	2.4732
5.9959	5.0	10	4.8381	0.0102	4.8378	2.1995
5.9959	6.0	12	3.8420	0.0	3.8418	1.9600
5.9959	7.0	14	3.2353	0.0	3.2352	1.7987
5.9959	8.0	16	2.3429	0.1320	2.3429	1.5307
5.9959	9.0	18	1.8504	0.0411	1.8505	1.3603
2.2784	10.0	20	1.6708	0.0213	1.6708	1.2926
2.2784	11.0	22	1.4056	0.0107	1.4057	1.1856
2.2784	12.0	24	1.4469	0.0107	1.4470	1.2029
2.2784	13.0	26	1.4678	0.0107	1.4679	1.2116
2.2784	14.0	28	1.4902	0.0107	1.4903	1.2208
1.7634	15.0	30	1.5058	0.0107	1.5059	1.2272
1.7634	16.0	32	1.3240	0.0107	1.3242	1.1507
1.7634	17.0	34	1.6746	0.0163	1.6747	1.2941
1.7634	18.0	36	1.3913	0.0187	1.3915	1.1796
1.7634	19.0	38	1.2316	0.0170	1.2318	1.1099
1.4927	20.0	40	1.5749	0.0267	1.5750	1.2550
1.4927	21.0	42	1.5754	0.0344	1.5754	1.2552
1.4927	22.0	44	1.2014	0.0936	1.2016	1.0962
1.4927	23.0	46	1.8726	-0.0002	1.8725	1.3684
1.4927	24.0	48	1.6835	0.0228	1.6835	1.2975
1.0521	25.0	50	1.1252	0.1631	1.1255	1.0609
1.0521	26.0	52	1.4824	0.0591	1.4827	1.2176
1.0521	27.0	54	1.5195	0.0320	1.5198	1.2328
1.0521	28.0	56	1.5815	0.0111	1.5818	1.2577
1.0521	29.0	58	1.1740	0.1158	1.1745	1.0837
0.5879	30.0	60	1.5495	0.0154	1.5499	1.2450
0.5879	31.0	62	1.5259	0.0165	1.5263	1.2354
0.5879	32.0	64	1.6797	0.0150	1.6800	1.2961
0.5879	33.0	66	1.7852	0.0221	1.7854	1.3362
0.5879	34.0	68	1.3256	0.0816	1.3258	1.1514
0.2797	35.0	70	2.1394	0.0068	2.1393	1.4626
0.2797	36.0	72	2.0788	0.0164	2.0787	1.4418
0.2797	37.0	74	1.4404	0.0917	1.4406	1.2002
0.2797	38.0	76	2.0262	0.0136	2.0263	1.4235
0.2797	39.0	78	1.8784	0.0513	1.8785	1.3706
0.2315	40.0	80	1.3245	0.1323	1.3247	1.1510
0.2315	41.0	82	1.7096	0.0701	1.7096	1.3075
0.2315	42.0	84	1.7248	0.0842	1.7248	1.3133
0.2315	43.0	86	1.3965	0.1440	1.3965	1.1818
0.2315	44.0	88	1.9503	0.0575	1.9502	1.3965
0.1805	45.0	90	1.9117	0.0683	1.9116	1.3826
0.1805	46.0	92	1.4692	0.1345	1.4693	1.2122
0.1805	47.0	94	1.8481	0.0742	1.8481	1.3595
0.1805	48.0	96	1.7055	0.0650	1.7057	1.3060
0.1805	49.0	98	1.3218	0.1456	1.3222	1.1499
0.1404	50.0	100	1.6603	0.0836	1.6605	1.2886
0.1404	51.0	102	1.7183	0.0587	1.7186	1.3110
0.1404	52.0	104	1.4972	0.0796	1.4976	1.2238
0.1404	53.0	106	1.5214	0.0817	1.5218	1.2336
0.1404	54.0	108	1.8001	0.0543	1.8004	1.3418
0.1064	55.0	110	1.8255	0.0688	1.8257	1.3512
0.1064	56.0	112	1.5601	0.0924	1.5604	1.2492
0.1064	57.0	114	1.8597	0.0807	1.8598	1.3638
0.1064	58.0	116	1.7706	0.0920	1.7707	1.3307
0.1064	59.0	118	1.5674	0.1011	1.5676	1.2521
0.0972	60.0	120	1.6479	0.1030	1.6481	1.2838
0.0972	61.0	122	2.0275	0.0579	2.0275	1.4239
0.0972	62.0	124	1.9893	0.0644	1.9893	1.4104
0.0972	63.0	126	1.6465	0.0782	1.6466	1.2832
0.0972	64.0	128	1.6710	0.0732	1.6711	1.2927
0.0998	65.0	130	1.8190	0.0702	1.8191	1.3487
0.0998	66.0	132	1.5492	0.0797	1.5494	1.2448
0.0998	67.0	134	1.5774	0.0784	1.5776	1.2560
0.0998	68.0	136	1.8456	0.0557	1.8457	1.3586
0.0998	69.0	138	1.6691	0.0619	1.6693	1.2920
0.0848	70.0	140	1.5915	0.0675	1.5918	1.2616
0.0848	71.0	142	1.7273	0.0637	1.7275	1.3144
0.0848	72.0	144	1.5440	0.0725	1.5442	1.2427
0.0848	73.0	146	1.5512	0.0839	1.5515	1.2456
0.0848	74.0	148	1.7600	0.0690	1.7602	1.3267
0.0741	75.0	150	1.6885	0.0546	1.6887	1.2995
0.0741	76.0	152	1.6309	0.0715	1.6311	1.2771
0.0741	77.0	154	1.8321	0.0608	1.8321	1.3536
0.0741	78.0	156	1.8216	0.0671	1.8217	1.3497
0.0741	79.0	158	1.6690	0.0623	1.6691	1.2919
0.0649	80.0	160	1.6678	0.0689	1.6679	1.2915
0.0649	81.0	162	1.8035	0.0763	1.8036	1.3430
0.0649	82.0	164	1.8821	0.0607	1.8822	1.3719
0.0649	83.0	166	1.8157	0.0794	1.8159	1.3475
0.0649	84.0	168	1.6528	0.0742	1.6530	1.2857
0.0611	85.0	170	1.4986	0.0941	1.4988	1.2243
0.0611	86.0	172	1.5243	0.0801	1.5246	1.2347
0.0611	87.0	174	1.6910	0.0689	1.6912	1.3005
0.0611	88.0	176	1.8519	0.0530	1.8521	1.3609
0.0611	89.0	178	1.8470	0.0661	1.8472	1.3591
0.0689	90.0	180	1.7224	0.0709	1.7225	1.3125
0.0689	91.0	182	1.6250	0.0686	1.6252	1.2748
0.0689	92.0	184	1.5852	0.0852	1.5855	1.2591
0.0689	93.0	186	1.6203	0.0698	1.6205	1.2730
0.0689	94.0	188	1.6683	0.0696	1.6685	1.2917
0.0662	95.0	190	1.7378	0.0733	1.7380	1.3183
0.0662	96.0	192	1.7331	0.0733	1.7333	1.3166
0.0662	97.0	194	1.7048	0.0556	1.7050	1.3057
0.0662	98.0	196	1.6821	0.0715	1.6823	1.2970
0.0662	99.0	198	1.6706	0.0798	1.6708	1.2926
0.0677	100.0	200	1.6688	0.0798	1.6690	1.2919

Framework versions

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