ASAP_FineTuningBERT_AugV5_k2_task1_organization_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: 1.4882
• Qwk: -0.0698
• Mse: 1.4885
• Rmse: 1.2201

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	10.4698	-0.0007	10.4674	3.2353
No log	2.0	4	8.1315	0.0	8.1297	2.8513
No log	3.0	6	6.6203	0.0	6.6185	2.5727
No log	4.0	8	5.1594	0.0397	5.1581	2.2711
5.2619	5.0	10	4.2139	0.0204	4.2128	2.0525
5.2619	6.0	12	3.3484	0.0	3.3476	1.8296
5.2619	7.0	14	2.4695	0.0335	2.4690	1.5713
5.2619	8.0	16	2.4274	0.0165	2.4268	1.5578
5.2619	9.0	18	2.0689	-0.0045	2.0685	1.4382
2.1268	10.0	20	1.4960	0.0315	1.4959	1.2231
2.1268	11.0	22	1.4326	0.0106	1.4326	1.1969
2.1268	12.0	24	1.5562	0.0211	1.5563	1.2475
2.1268	13.0	26	1.4471	0.0	1.4472	1.2030
2.1268	14.0	28	1.3652	0.0	1.3653	1.1685
1.7632	15.0	30	1.3694	0.0	1.3695	1.1703
1.7632	16.0	32	1.3967	0.0	1.3969	1.1819
1.7632	17.0	34	1.3075	0.0	1.3077	1.1435
1.7632	18.0	36	1.0959	0.0	1.0962	1.0470
1.7632	19.0	38	1.2807	0.0310	1.2809	1.1318
1.2911	20.0	40	1.2929	0.0268	1.2930	1.1371
1.2911	21.0	42	1.0497	0.0845	1.0498	1.0246
1.2911	22.0	44	0.9889	0.1424	0.9891	0.9945
1.2911	23.0	46	1.4049	0.0318	1.4049	1.1853
1.2911	24.0	48	1.4490	0.0275	1.4489	1.2037
0.7404	25.0	50	1.0279	0.0799	1.0280	1.0139
0.7404	26.0	52	1.1402	0.0429	1.1403	1.0678
0.7404	27.0	54	1.1346	0.0409	1.1347	1.0652
0.7404	28.0	56	1.2277	0.0135	1.2277	1.1080
0.7404	29.0	58	1.3712	-0.0413	1.3712	1.1710
0.3592	30.0	60	1.4526	-0.0638	1.4526	1.2052
0.3592	31.0	62	1.3467	-0.0549	1.3468	1.1605
0.3592	32.0	64	1.6744	-0.1048	1.6743	1.2939
0.3592	33.0	66	1.3546	-0.0932	1.3548	1.1639
0.3592	34.0	68	1.5503	-0.1470	1.5503	1.2451
0.2171	35.0	70	1.9329	-0.1356	1.9329	1.3903
0.2171	36.0	72	1.5089	-0.1392	1.5091	1.2284
0.2171	37.0	74	1.5246	-0.1416	1.5249	1.2349
0.2171	38.0	76	1.7712	-0.1316	1.7713	1.3309
0.2171	39.0	78	1.4046	-0.1219	1.4050	1.1853
0.1885	40.0	80	1.3810	-0.0741	1.3813	1.1753
0.1885	41.0	82	1.5772	-0.0926	1.5773	1.2559
0.1885	42.0	84	1.3764	-0.0644	1.3767	1.1733
0.1885	43.0	86	1.4507	-0.0755	1.4510	1.2046
0.1885	44.0	88	1.7247	-0.0723	1.7249	1.3134
0.1315	45.0	90	1.4254	-0.0527	1.4258	1.1941
0.1315	46.0	92	1.3033	-0.0232	1.3036	1.1418
0.1315	47.0	94	1.3636	-0.0364	1.3639	1.1679
0.1315	48.0	96	1.3356	-0.0357	1.3359	1.1558
0.1315	49.0	98	1.4280	-0.0507	1.4282	1.1951
0.1111	50.0	100	1.4952	-0.0803	1.4955	1.2229
0.1111	51.0	102	1.4609	-0.0782	1.4612	1.2088
0.1111	52.0	104	1.3766	-0.0958	1.3769	1.1734
0.1111	53.0	106	1.3836	-0.0766	1.3838	1.1764
0.1111	54.0	108	1.4240	-0.0730	1.4242	1.1934
0.1028	55.0	110	1.5048	-0.0779	1.5049	1.2267
0.1028	56.0	112	1.4158	-0.0708	1.4160	1.1900
0.1028	57.0	114	1.4916	-0.0688	1.4917	1.2214
0.1028	58.0	116	1.4316	-0.0607	1.4318	1.1966
0.1028	59.0	118	1.4572	-0.0578	1.4573	1.2072
0.0887	60.0	120	1.3877	-0.0395	1.3879	1.1781
0.0887	61.0	122	1.3899	-0.0467	1.3901	1.1790
0.0887	62.0	124	1.4124	-0.0426	1.4127	1.1886
0.0887	63.0	126	1.3312	-0.0644	1.3315	1.1539
0.0887	64.0	128	1.4083	-0.0439	1.4086	1.1868
0.0708	65.0	130	1.4874	-0.0502	1.4877	1.2197
0.0708	66.0	132	1.4187	-0.0635	1.4190	1.1912
0.0708	67.0	134	1.5010	-0.0547	1.5013	1.2253
0.0708	68.0	136	1.6029	-0.0889	1.6032	1.2662
0.0708	69.0	138	1.4475	-0.1025	1.4479	1.2033
0.0716	70.0	140	1.4358	-0.1056	1.4363	1.1984
0.0716	71.0	142	1.5800	-0.0839	1.5804	1.2571
0.0716	72.0	144	1.6272	-0.0918	1.6275	1.2757
0.0716	73.0	146	1.4703	-0.0880	1.4707	1.2127
0.0716	74.0	148	1.4363	-0.0814	1.4367	1.1986
0.0699	75.0	150	1.5460	-0.0866	1.5463	1.2435
0.0699	76.0	152	1.5505	-0.0863	1.5508	1.2453
0.0699	77.0	154	1.4169	-0.0670	1.4174	1.1905
0.0699	78.0	156	1.3448	-0.0726	1.3453	1.1599
0.0699	79.0	158	1.3791	-0.0797	1.3796	1.1746
0.0677	80.0	160	1.5306	-0.0710	1.5309	1.2373
0.0677	81.0	162	1.5896	-0.0796	1.5898	1.2609
0.0677	82.0	164	1.5151	-0.0796	1.5154	1.2310
0.0677	83.0	166	1.4331	-0.0691	1.4335	1.1973
0.0677	84.0	168	1.4458	-0.0642	1.4463	1.2026
0.0605	85.0	170	1.4730	-0.0596	1.4734	1.2139
0.0605	86.0	172	1.4367	-0.0647	1.4371	1.1988
0.0605	87.0	174	1.3804	-0.0774	1.3809	1.1751
0.0605	88.0	176	1.3941	-0.0742	1.3945	1.1809
0.0605	89.0	178	1.4419	-0.0652	1.4423	1.2010
0.0639	90.0	180	1.4717	-0.0652	1.4720	1.2133
0.0639	91.0	182	1.4858	-0.0451	1.4862	1.2191
0.0639	92.0	184	1.4412	-0.0713	1.4416	1.2007
0.0639	93.0	186	1.4027	-0.0522	1.4031	1.1845
0.0639	94.0	188	1.4078	-0.0522	1.4083	1.1867
0.0601	95.0	190	1.4289	-0.0517	1.4293	1.1955
0.0601	96.0	192	1.4334	-0.0532	1.4338	1.1974
0.0601	97.0	194	1.4532	-0.0610	1.4536	1.2057
0.0601	98.0	196	1.4735	-0.0683	1.4739	1.2140
0.0601	99.0	198	1.4854	-0.0725	1.4858	1.2189
0.058	100.0	200	1.4882	-0.0698	1.4885	1.2201

Framework versions

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