ASAP_FineTuningBERT_AugV7_k1_task1_organization_fold0

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: 0.8059
• Qwk: 0.5286
• Mse: 0.8059
• Rmse: 0.8977

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	9.1790	0.0	9.1790	3.0297
No log	2.0	4	7.5622	0.0	7.5622	2.7499
No log	3.0	6	6.7022	0.0	6.7021	2.5889
No log	4.0	8	5.9983	0.0003	5.9983	2.4491
6.5563	5.0	10	5.0291	0.0115	5.0291	2.2426
6.5563	6.0	12	4.2114	0.0039	4.2114	2.0522
6.5563	7.0	14	3.4648	0.0	3.4648	1.8614
6.5563	8.0	16	2.7714	0.0	2.7714	1.6648
6.5563	9.0	18	2.2170	0.1090	2.2170	1.4890
3.2461	10.0	20	1.8380	0.0751	1.8380	1.3557
3.2461	11.0	22	1.5800	0.0484	1.5800	1.2570
3.2461	12.0	24	1.4546	0.0873	1.4546	1.2061
3.2461	13.0	26	1.2681	0.1082	1.2681	1.1261
3.2461	14.0	28	0.9396	0.0548	0.9396	0.9693
2.1813	15.0	30	0.9842	0.1382	0.9842	0.9921
2.1813	16.0	32	0.8782	0.3354	0.8782	0.9371
2.1813	17.0	34	0.7749	0.3330	0.7749	0.8803
2.1813	18.0	36	0.8129	0.4211	0.8129	0.9016
2.1813	19.0	38	0.6519	0.4863	0.6519	0.8074
1.6751	20.0	40	0.6363	0.5042	0.6363	0.7977
1.6751	21.0	42	0.6322	0.4950	0.6322	0.7951
1.6751	22.0	44	0.6680	0.5144	0.6680	0.8173
1.6751	23.0	46	0.6949	0.4808	0.6949	0.8336
1.6751	24.0	48	0.6420	0.4945	0.6420	0.8013
0.8911	25.0	50	0.5866	0.5016	0.5866	0.7659
0.8911	26.0	52	0.5959	0.4516	0.5959	0.7719
0.8911	27.0	54	0.5807	0.4918	0.5807	0.7621
0.8911	28.0	56	0.6066	0.4872	0.6066	0.7789
0.8911	29.0	58	0.7152	0.4409	0.7152	0.8457
0.5156	30.0	60	0.6388	0.5067	0.6388	0.7993
0.5156	31.0	62	0.7674	0.4672	0.7674	0.8760
0.5156	32.0	64	0.6551	0.5372	0.6551	0.8094
0.5156	33.0	66	0.7107	0.4842	0.7107	0.8430
0.5156	34.0	68	0.6066	0.5603	0.6066	0.7789
0.3885	35.0	70	0.6315	0.5525	0.6315	0.7947
0.3885	36.0	72	0.7609	0.4917	0.7609	0.8723
0.3885	37.0	74	0.7871	0.4815	0.7871	0.8872
0.3885	38.0	76	0.7139	0.5121	0.7139	0.8449
0.3885	39.0	78	0.8381	0.4814	0.8381	0.9155
0.2285	40.0	80	0.8618	0.4744	0.8618	0.9283
0.2285	41.0	82	0.7924	0.4887	0.7924	0.8902
0.2285	42.0	84	0.8791	0.4734	0.8791	0.9376
0.2285	43.0	86	0.8044	0.5120	0.8044	0.8969
0.2285	44.0	88	0.7574	0.5093	0.7574	0.8703
0.2073	45.0	90	0.7303	0.5006	0.7303	0.8546
0.2073	46.0	92	0.9183	0.4750	0.9183	0.9583
0.2073	47.0	94	0.7668	0.5284	0.7668	0.8756
0.2073	48.0	96	0.6956	0.5392	0.6956	0.8340
0.2073	49.0	98	0.8266	0.5179	0.8266	0.9092
0.1907	50.0	100	0.8488	0.5185	0.8488	0.9213
0.1907	51.0	102	0.7394	0.5525	0.7394	0.8599
0.1907	52.0	104	0.7050	0.5575	0.7050	0.8397
0.1907	53.0	106	0.7331	0.5493	0.7331	0.8562
0.1907	54.0	108	0.8801	0.4962	0.8801	0.9381
0.1388	55.0	110	0.7808	0.5312	0.7808	0.8836
0.1388	56.0	112	0.6952	0.5436	0.6952	0.8338
0.1388	57.0	114	0.7777	0.5475	0.7777	0.8819
0.1388	58.0	116	1.1561	0.4466	1.1561	1.0752
0.1388	59.0	118	1.1235	0.4581	1.1235	1.0600
0.1562	60.0	120	0.8506	0.5275	0.8506	0.9223
0.1562	61.0	122	0.8378	0.5279	0.8378	0.9153
0.1562	62.0	124	1.0405	0.4969	1.0405	1.0201
0.1562	63.0	126	1.0574	0.4925	1.0574	1.0283
0.1562	64.0	128	0.8182	0.5294	0.8182	0.9045
0.1167	65.0	130	0.8369	0.5146	0.8369	0.9148
0.1167	66.0	132	1.0348	0.4684	1.0348	1.0173
0.1167	67.0	134	0.9722	0.4790	0.9722	0.9860
0.1167	68.0	136	0.6957	0.5544	0.6957	0.8341
0.1167	69.0	138	0.6585	0.5656	0.6585	0.8115
0.1264	70.0	140	0.7116	0.5322	0.7116	0.8436
0.1264	71.0	142	0.8784	0.4927	0.8784	0.9372
0.1264	72.0	144	0.8202	0.5074	0.8202	0.9057
0.1264	73.0	146	0.7470	0.5440	0.7470	0.8643
0.1264	74.0	148	0.7443	0.5483	0.7443	0.8627
0.0847	75.0	150	0.8673	0.5159	0.8673	0.9313
0.0847	76.0	152	0.8903	0.5059	0.8903	0.9436
0.0847	77.0	154	0.7470	0.5389	0.7470	0.8643
0.0847	78.0	156	0.7185	0.5423	0.7185	0.8476
0.0847	79.0	158	0.8161	0.5091	0.8161	0.9034
0.0807	80.0	160	0.8405	0.5110	0.8405	0.9168
0.0807	81.0	162	0.7393	0.5355	0.7393	0.8598
0.0807	82.0	164	0.7343	0.5361	0.7343	0.8569
0.0807	83.0	166	0.8363	0.5072	0.8363	0.9145
0.0807	84.0	168	0.8586	0.5023	0.8586	0.9266
0.0711	85.0	170	0.7990	0.5168	0.7990	0.8939
0.0711	86.0	172	0.8104	0.5168	0.8104	0.9002
0.0711	87.0	174	0.7832	0.5247	0.7832	0.8850
0.0711	88.0	176	0.7746	0.5351	0.7746	0.8801
0.0711	89.0	178	0.8195	0.5132	0.8195	0.9052
0.0817	90.0	180	0.7966	0.5265	0.7966	0.8925
0.0817	91.0	182	0.7573	0.5415	0.7573	0.8702
0.0817	92.0	184	0.7486	0.5468	0.7486	0.8652
0.0817	93.0	186	0.7649	0.5450	0.7649	0.8746
0.0817	94.0	188	0.7979	0.5296	0.7979	0.8933
0.0795	95.0	190	0.8433	0.4999	0.8433	0.9183
0.0795	96.0	192	0.8578	0.5051	0.8578	0.9262
0.0795	97.0	194	0.8461	0.4999	0.8461	0.9199
0.0795	98.0	196	0.8277	0.5065	0.8277	0.9098
0.0795	99.0	198	0.8110	0.5193	0.8110	0.9006
0.059	100.0	200	0.8059	0.5286	0.8059	0.8977

Framework versions

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