ASAP_FineTuningBERT_AugV8_k1_task1_organization_fold3

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: 0.6575
• Qwk: 0.5649
• Mse: 0.6574
• Rmse: 0.8108

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	12.2814	-0.0223	12.2803	3.5043
No log	2.0	4	10.0937	-0.0020	10.0930	3.1769
No log	3.0	6	8.1764	0.0	8.1758	2.8593
No log	4.0	8	6.7151	0.0	6.7146	2.5913
7.1684	5.0	10	5.3786	0.0137	5.3784	2.3191
7.1684	6.0	12	4.2192	0.0038	4.2191	2.0541
7.1684	7.0	14	3.5270	0.0	3.5270	1.8780
7.1684	8.0	16	2.6048	0.0307	2.6051	1.6140
7.1684	9.0	18	2.0913	0.0417	2.0917	1.4463
3.0253	10.0	20	1.7826	0.0202	1.7831	1.3353
3.0253	11.0	22	1.4219	0.0202	1.4226	1.1927
3.0253	12.0	24	1.1764	0.0202	1.1772	1.0850
3.0253	13.0	26	1.0163	0.0202	1.0171	1.0085
3.0253	14.0	28	0.9967	0.0436	0.9974	0.9987
2.0355	15.0	30	0.9642	0.0964	0.9649	0.9823
2.0355	16.0	32	0.8791	0.2211	0.8797	0.9379
2.0355	17.0	34	0.7556	0.4140	0.7561	0.8696
2.0355	18.0	36	0.7340	0.4475	0.7345	0.8570
2.0355	19.0	38	0.9855	0.3384	0.9859	0.9929
1.4827	20.0	40	1.1479	0.3128	1.1482	1.0716
1.4827	21.0	42	0.9725	0.3434	0.9728	0.9863
1.4827	22.0	44	0.7810	0.4272	0.7813	0.8839
1.4827	23.0	46	0.6868	0.4644	0.6871	0.8289
1.4827	24.0	48	0.6353	0.4949	0.6355	0.7972
1.1846	25.0	50	0.6199	0.4940	0.6201	0.7874
1.1846	26.0	52	0.7625	0.4774	0.7627	0.8733
1.1846	27.0	54	0.7490	0.4757	0.7492	0.8656
1.1846	28.0	56	0.6751	0.4732	0.6753	0.8218
1.1846	29.0	58	0.9275	0.4123	0.9279	0.9633
0.6492	30.0	60	0.9467	0.4151	0.9472	0.9732
0.6492	31.0	62	0.6755	0.5337	0.6757	0.8220
0.6492	32.0	64	0.6802	0.5095	0.6804	0.8249
0.6492	33.0	66	0.7737	0.4565	0.7740	0.8798
0.6492	34.0	68	0.9195	0.4237	0.9200	0.9591
0.3391	35.0	70	0.7852	0.4744	0.7855	0.8863
0.3391	36.0	72	0.7530	0.4669	0.7532	0.8679
0.3391	37.0	74	0.8341	0.4488	0.8343	0.9134
0.3391	38.0	76	0.8239	0.4794	0.8241	0.9078
0.3391	39.0	78	1.0876	0.3813	1.0881	1.0431
0.1596	40.0	80	0.8198	0.4823	0.8198	0.9054
0.1596	41.0	82	0.8225	0.4857	0.8226	0.9070
0.1596	42.0	84	0.8194	0.4850	0.8195	0.9053
0.1596	43.0	86	0.6995	0.5482	0.6993	0.8362
0.1596	44.0	88	0.7225	0.5167	0.7226	0.8500
0.1472	45.0	90	0.7375	0.4925	0.7376	0.8588
0.1472	46.0	92	0.6847	0.5319	0.6847	0.8275
0.1472	47.0	94	0.6680	0.5297	0.6679	0.8172
0.1472	48.0	96	0.6939	0.5312	0.6938	0.8329
0.1472	49.0	98	0.6878	0.5345	0.6875	0.8292
0.1115	50.0	100	0.7215	0.5366	0.7215	0.8494
0.1115	51.0	102	0.8120	0.4701	0.8122	0.9012
0.1115	52.0	104	0.6935	0.5378	0.6935	0.8328
0.1115	53.0	106	0.7051	0.5696	0.7047	0.8395
0.1115	54.0	108	0.6542	0.5842	0.6539	0.8087
0.1286	55.0	110	0.6667	0.5460	0.6668	0.8166
0.1286	56.0	112	0.6924	0.5359	0.6925	0.8322
0.1286	57.0	114	0.6213	0.5740	0.6211	0.7881
0.1286	58.0	116	0.7564	0.5515	0.7559	0.8694
0.1286	59.0	118	0.7086	0.5614	0.7082	0.8416
0.1238	60.0	120	0.6432	0.5649	0.6432	0.8020
0.1238	61.0	122	0.7118	0.5357	0.7119	0.8438
0.1238	62.0	124	0.6511	0.5673	0.6510	0.8069
0.1238	63.0	126	0.6470	0.5964	0.6467	0.8042
0.1238	64.0	128	0.6318	0.5990	0.6315	0.7947
0.1125	65.0	130	0.7099	0.5364	0.7100	0.8426
0.1125	66.0	132	0.7745	0.5226	0.7746	0.8801
0.1125	67.0	134	0.6715	0.5714	0.6714	0.8194
0.1125	68.0	136	0.6944	0.5886	0.6938	0.8330
0.1125	69.0	138	0.7824	0.5537	0.7817	0.8841
0.1295	70.0	140	0.6983	0.5896	0.6977	0.8353
0.1295	71.0	142	0.6452	0.5739	0.6449	0.8031
0.1295	72.0	144	0.6964	0.5512	0.6964	0.8345
0.1295	73.0	146	0.6765	0.5530	0.6765	0.8225
0.1295	74.0	148	0.6395	0.5650	0.6393	0.7996
0.0837	75.0	150	0.6467	0.5897	0.6464	0.8040
0.0837	76.0	152	0.6308	0.5864	0.6304	0.7940
0.0837	77.0	154	0.6270	0.5705	0.6269	0.7918
0.0837	78.0	156	0.6386	0.5523	0.6385	0.7991
0.0837	79.0	158	0.6545	0.5564	0.6544	0.8089
0.0665	80.0	160	0.6649	0.5682	0.6647	0.8153
0.0665	81.0	162	0.6705	0.5536	0.6703	0.8187
0.0665	82.0	164	0.6690	0.5578	0.6688	0.8178
0.0665	83.0	166	0.6636	0.5604	0.6634	0.8145
0.0665	84.0	168	0.6542	0.5617	0.6540	0.8087
0.0578	85.0	170	0.6475	0.5663	0.6473	0.8046
0.0578	86.0	172	0.6394	0.5609	0.6392	0.7995
0.0578	87.0	174	0.6378	0.5612	0.6376	0.7985
0.0578	88.0	176	0.6352	0.5617	0.6350	0.7968
0.0578	89.0	178	0.6360	0.5634	0.6358	0.7974
0.0568	90.0	180	0.6427	0.5710	0.6425	0.8016
0.0568	91.0	182	0.6441	0.5736	0.6440	0.8025
0.0568	92.0	184	0.6461	0.5736	0.6459	0.8037
0.0568	93.0	186	0.6480	0.5751	0.6479	0.8049
0.0568	94.0	188	0.6515	0.5696	0.6513	0.8070
0.0624	95.0	190	0.6531	0.5627	0.6529	0.8080
0.0624	96.0	192	0.6536	0.5678	0.6534	0.8083
0.0624	97.0	194	0.6561	0.5648	0.6559	0.8099
0.0624	98.0	196	0.6583	0.5637	0.6581	0.8112
0.0624	99.0	198	0.6580	0.5637	0.6579	0.8111
0.0487	100.0	200	0.6575	0.5649	0.6574	0.8108

Framework versions

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