ASAP_FineTuningBERT_AugV7_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: 0.6529
• Qwk: 0.5722
• Mse: 0.6529
• Rmse: 0.8080

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	11.1531	-0.0178	11.1531	3.3396
No log	2.0	4	8.8229	0.0018	8.8229	2.9703
No log	3.0	6	7.0425	0.0018	7.0425	2.6538
No log	4.0	8	5.7362	0.0356	5.7362	2.3950
7.8873	5.0	10	4.4099	0.0156	4.4099	2.1000
7.8873	6.0	12	3.5360	0.0040	3.5360	1.8804
7.8873	7.0	14	2.7160	0.0040	2.7160	1.6480
7.8873	8.0	16	2.1840	0.1859	2.1840	1.4778
7.8873	9.0	18	1.7700	0.0445	1.7700	1.3304
2.9539	10.0	20	1.6198	0.0212	1.6198	1.2727
2.9539	11.0	22	1.2996	0.0316	1.2996	1.1400
2.9539	12.0	24	1.1607	0.0420	1.1607	1.0774
2.9539	13.0	26	1.0441	0.0316	1.0441	1.0218
2.9539	14.0	28	0.9839	0.0771	0.9839	0.9919
2.1845	15.0	30	1.4030	0.1753	1.4030	1.1845
2.1845	16.0	32	1.1417	0.1437	1.1417	1.0685
2.1845	17.0	34	0.8290	0.1804	0.8290	0.9105
2.1845	18.0	36	0.7905	0.2315	0.7905	0.8891
2.1845	19.0	38	0.8258	0.3241	0.8258	0.9087
1.7493	20.0	40	0.9273	0.3076	0.9273	0.9629
1.7493	21.0	42	0.6768	0.5033	0.6768	0.8227
1.7493	22.0	44	0.5716	0.4657	0.5716	0.7561
1.7493	23.0	46	0.5599	0.4572	0.5599	0.7482
1.7493	24.0	48	0.5467	0.5632	0.5467	0.7394
1.1276	25.0	50	0.6533	0.5644	0.6533	0.8083
1.1276	26.0	52	0.6450	0.5180	0.6450	0.8031
1.1276	27.0	54	0.5788	0.4493	0.5788	0.7608
1.1276	28.0	56	0.6139	0.4561	0.6139	0.7835
1.1276	29.0	58	0.5524	0.5010	0.5524	0.7432
0.7007	30.0	60	0.6009	0.5301	0.6009	0.7752
0.7007	31.0	62	0.5737	0.5252	0.5737	0.7575
0.7007	32.0	64	0.6676	0.4947	0.6676	0.8171
0.7007	33.0	66	0.6592	0.4832	0.6592	0.8119
0.7007	34.0	68	0.6462	0.5313	0.6462	0.8039
0.3977	35.0	70	0.6066	0.5625	0.6066	0.7789
0.3977	36.0	72	0.6122	0.5539	0.6122	0.7824
0.3977	37.0	74	0.5906	0.5737	0.5906	0.7685
0.3977	38.0	76	0.6485	0.5801	0.6485	0.8053
0.3977	39.0	78	0.6587	0.5524	0.6587	0.8116
0.221	40.0	80	0.6910	0.5167	0.6910	0.8312
0.221	41.0	82	0.6622	0.5251	0.6622	0.8138
0.221	42.0	84	0.6506	0.5586	0.6506	0.8066
0.221	43.0	86	0.6452	0.5718	0.6452	0.8032
0.221	44.0	88	0.6779	0.5446	0.6779	0.8233
0.1751	45.0	90	0.6648	0.5478	0.6648	0.8153
0.1751	46.0	92	0.6795	0.5382	0.6795	0.8243
0.1751	47.0	94	0.6720	0.5339	0.6720	0.8198
0.1751	48.0	96	0.6661	0.5576	0.6661	0.8161
0.1751	49.0	98	0.6518	0.5657	0.6518	0.8073
0.1663	50.0	100	0.6628	0.5742	0.6628	0.8141
0.1663	51.0	102	0.6204	0.5943	0.6204	0.7876
0.1663	52.0	104	0.6449	0.6010	0.6449	0.8031
0.1663	53.0	106	0.7483	0.5558	0.7483	0.8650
0.1663	54.0	108	0.8276	0.5202	0.8276	0.9097
0.1178	55.0	110	0.7410	0.5387	0.7410	0.8608
0.1178	56.0	112	0.7021	0.5605	0.7021	0.8379
0.1178	57.0	114	0.6834	0.5687	0.6834	0.8267
0.1178	58.0	116	0.6517	0.5827	0.6517	0.8073
0.1178	59.0	118	0.6283	0.5858	0.6283	0.7926
0.1041	60.0	120	0.6145	0.5902	0.6145	0.7839
0.1041	61.0	122	0.6197	0.5473	0.6197	0.7872
0.1041	62.0	124	0.6745	0.5212	0.6745	0.8213
0.1041	63.0	126	0.6876	0.5294	0.6876	0.8292
0.1041	64.0	128	0.6173	0.5484	0.6173	0.7857
0.0887	65.0	130	0.6046	0.5775	0.6046	0.7776
0.0887	66.0	132	0.6078	0.5701	0.6078	0.7796
0.0887	67.0	134	0.6590	0.5675	0.6590	0.8118
0.0887	68.0	136	0.6969	0.5911	0.6969	0.8348
0.0887	69.0	138	0.6934	0.5851	0.6934	0.8327
0.0903	70.0	140	0.6733	0.5842	0.6733	0.8205
0.0903	71.0	142	0.6771	0.5878	0.6771	0.8228
0.0903	72.0	144	0.7216	0.5948	0.7216	0.8495
0.0903	73.0	146	0.7313	0.5883	0.7313	0.8552
0.0903	74.0	148	0.6849	0.5769	0.6849	0.8276
0.0891	75.0	150	0.6838	0.5727	0.6838	0.8269
0.0891	76.0	152	0.7271	0.5445	0.7271	0.8527
0.0891	77.0	154	0.7749	0.5486	0.7749	0.8803
0.0891	78.0	156	0.7341	0.5491	0.7341	0.8568
0.0891	79.0	158	0.6715	0.5637	0.6715	0.8195
0.0761	80.0	160	0.6340	0.5772	0.6340	0.7962
0.0761	81.0	162	0.6267	0.5794	0.6267	0.7917
0.0761	82.0	164	0.6575	0.5977	0.6575	0.8109
0.0761	83.0	166	0.7063	0.5769	0.7063	0.8404
0.0761	84.0	168	0.7010	0.5783	0.7010	0.8373
0.0715	85.0	170	0.6718	0.5818	0.6718	0.8196
0.0715	86.0	172	0.6503	0.5875	0.6503	0.8064
0.0715	87.0	174	0.6527	0.5709	0.6527	0.8079
0.0715	88.0	176	0.6573	0.5641	0.6573	0.8107
0.0715	89.0	178	0.6695	0.5667	0.6695	0.8182
0.0729	90.0	180	0.6526	0.5646	0.6526	0.8079
0.0729	91.0	182	0.6399	0.5743	0.6399	0.8000
0.0729	92.0	184	0.6394	0.5743	0.6394	0.7996
0.0729	93.0	186	0.6445	0.5732	0.6445	0.8028
0.0729	94.0	188	0.6500	0.5722	0.6500	0.8062
0.0612	95.0	190	0.6535	0.5711	0.6535	0.8084
0.0612	96.0	192	0.6532	0.5722	0.6532	0.8082
0.0612	97.0	194	0.6477	0.5728	0.6477	0.8048
0.0612	98.0	196	0.6478	0.5728	0.6478	0.8049
0.0612	99.0	198	0.6515	0.5722	0.6515	0.8071
0.0451	100.0	200	0.6529	0.5722	0.6529	0.8080

Framework versions

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