ASAP_FineTuningBERT_AugV8_k1_task1_organization_fold4

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: 0.7045
• Qwk: 0.5504
• Mse: 0.7045
• Rmse: 0.8393

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	11.0407	-0.0131	11.0407	3.3228
No log	2.0	4	8.7735	0.0018	8.7735	2.9620
No log	3.0	6	7.0277	0.0018	7.0277	2.6510
No log	4.0	8	5.8415	0.0209	5.8415	2.4169
8.098	5.0	10	4.4750	0.0156	4.4750	2.1154
8.098	6.0	12	3.5770	0.0040	3.5770	1.8913
8.098	7.0	14	2.7907	0.0040	2.7907	1.6705
8.098	8.0	16	2.2653	0.1818	2.2653	1.5051
8.098	9.0	18	1.9849	0.1175	1.9849	1.4089
2.8801	10.0	20	1.5656	0.0445	1.5656	1.2513
2.8801	11.0	22	1.2622	0.0342	1.2622	1.1235
2.8801	12.0	24	1.1443	0.0445	1.1443	1.0697
2.8801	13.0	26	1.0136	0.0445	1.0136	1.0068
2.8801	14.0	28	0.8939	0.0745	0.8939	0.9454
2.0493	15.0	30	0.9923	0.1462	0.9923	0.9961
2.0493	16.0	32	1.0432	0.2595	1.0432	1.0214
2.0493	17.0	34	0.7552	0.4743	0.7552	0.8690
2.0493	18.0	36	0.7138	0.4497	0.7138	0.8449
2.0493	19.0	38	0.7190	0.4508	0.7190	0.8480
1.3545	20.0	40	0.7112	0.4539	0.7112	0.8433
1.3545	21.0	42	0.6355	0.4921	0.6355	0.7972
1.3545	22.0	44	0.6886	0.5092	0.6886	0.8298
1.3545	23.0	46	0.7642	0.5030	0.7642	0.8742
1.3545	24.0	48	0.6184	0.5036	0.6184	0.7864
0.7254	25.0	50	0.6344	0.4686	0.6344	0.7965
0.7254	26.0	52	0.7767	0.4339	0.7767	0.8813
0.7254	27.0	54	0.8166	0.4505	0.8166	0.9037
0.7254	28.0	56	0.6497	0.5533	0.6497	0.8060
0.7254	29.0	58	0.7141	0.4990	0.7141	0.8451
0.4658	30.0	60	0.8919	0.4246	0.8919	0.9444
0.4658	31.0	62	0.6958	0.5112	0.6958	0.8342
0.4658	32.0	64	0.7743	0.5201	0.7743	0.8799
0.4658	33.0	66	0.7299	0.4952	0.7299	0.8544
0.4658	34.0	68	0.7437	0.5200	0.7437	0.8624
0.3718	35.0	70	0.7287	0.5328	0.7287	0.8536
0.3718	36.0	72	0.6515	0.5723	0.6515	0.8071
0.3718	37.0	74	0.8151	0.5695	0.8151	0.9028
0.3718	38.0	76	0.6675	0.5833	0.6675	0.8170
0.3718	39.0	78	0.6127	0.5743	0.6127	0.7827
0.2417	40.0	80	0.6557	0.5389	0.6557	0.8098
0.2417	41.0	82	0.6872	0.5519	0.6872	0.8290
0.2417	42.0	84	0.8474	0.5675	0.8474	0.9206
0.2417	43.0	86	0.7554	0.5880	0.7554	0.8691
0.2417	44.0	88	0.6056	0.6134	0.6056	0.7782
0.2153	45.0	90	0.6411	0.5770	0.6411	0.8007
0.2153	46.0	92	0.6812	0.5184	0.6812	0.8253
0.2153	47.0	94	0.7739	0.5524	0.7739	0.8797
0.2153	48.0	96	0.6718	0.5424	0.6718	0.8196
0.2153	49.0	98	0.6527	0.5487	0.6527	0.8079
0.1333	50.0	100	0.6730	0.5797	0.6730	0.8204
0.1333	51.0	102	0.6744	0.5839	0.6744	0.8212
0.1333	52.0	104	0.6735	0.5646	0.6735	0.8206
0.1333	53.0	106	0.7030	0.5385	0.7030	0.8384
0.1333	54.0	108	0.6898	0.5281	0.6898	0.8306
0.0932	55.0	110	0.7152	0.5504	0.7152	0.8457
0.0932	56.0	112	0.6699	0.5532	0.6699	0.8185
0.0932	57.0	114	0.6275	0.5512	0.6275	0.7921
0.0932	58.0	116	0.6551	0.5631	0.6551	0.8094
0.0932	59.0	118	0.6807	0.5597	0.6807	0.8250
0.0777	60.0	120	0.6628	0.5299	0.6628	0.8141
0.0777	61.0	122	0.6907	0.5329	0.6907	0.8311
0.0777	62.0	124	0.7874	0.5619	0.7874	0.8873
0.0777	63.0	126	0.7811	0.5705	0.7811	0.8838
0.0777	64.0	128	0.6596	0.5606	0.6596	0.8122
0.0719	65.0	130	0.6273	0.5734	0.6273	0.7920
0.0719	66.0	132	0.6422	0.5553	0.6422	0.8014
0.0719	67.0	134	0.6538	0.5366	0.6538	0.8086
0.0719	68.0	136	0.6693	0.5216	0.6693	0.8181
0.0719	69.0	138	0.7009	0.5208	0.7009	0.8372
0.0646	70.0	140	0.7257	0.5242	0.7257	0.8519
0.0646	71.0	142	0.6926	0.5358	0.6926	0.8322
0.0646	72.0	144	0.6586	0.5615	0.6586	0.8116
0.0646	73.0	146	0.6369	0.5681	0.6369	0.7981
0.0646	74.0	148	0.6408	0.5780	0.6408	0.8005
0.0648	75.0	150	0.6731	0.5749	0.6731	0.8204
0.0648	76.0	152	0.7162	0.5721	0.7162	0.8463
0.0648	77.0	154	0.7090	0.5376	0.7090	0.8420
0.0648	78.0	156	0.7102	0.5178	0.7102	0.8427
0.0648	79.0	158	0.7078	0.5382	0.7078	0.8413
0.0538	80.0	160	0.6901	0.5525	0.6901	0.8307
0.0538	81.0	162	0.6965	0.5605	0.6965	0.8346
0.0538	82.0	164	0.6709	0.5677	0.6709	0.8191
0.0538	83.0	166	0.6603	0.5677	0.6603	0.8126
0.0538	84.0	168	0.6514	0.5656	0.6514	0.8071
0.0437	85.0	170	0.6361	0.5834	0.6361	0.7976
0.0437	86.0	172	0.6403	0.5788	0.6403	0.8002
0.0437	87.0	174	0.6667	0.5729	0.6667	0.8165
0.0437	88.0	176	0.6894	0.5612	0.6894	0.8303
0.0437	89.0	178	0.6886	0.5645	0.6886	0.8298
0.0615	90.0	180	0.6826	0.5664	0.6826	0.8262
0.0615	91.0	182	0.6799	0.5614	0.6799	0.8246
0.0615	92.0	184	0.6790	0.5541	0.6790	0.8240
0.0615	93.0	186	0.6772	0.5547	0.6772	0.8229
0.0615	94.0	188	0.6775	0.5666	0.6775	0.8231
0.0495	95.0	190	0.6871	0.5620	0.6871	0.8289
0.0495	96.0	192	0.6991	0.5526	0.6991	0.8361
0.0495	97.0	194	0.7048	0.5508	0.7048	0.8395
0.0495	98.0	196	0.7073	0.5504	0.7073	0.8410
0.0495	99.0	198	0.7061	0.5504	0.7061	0.8403
0.0395	100.0	200	0.7045	0.5504	0.7045	0.8393

Framework versions

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